The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
Error code: DatasetGenerationError
Exception: CastError
Message: Couldn't cast
item_id: string
question_id: string
context_length: string
family_id: string
evidence_type: string
memory_operation: string
subtype: string
question_text: string
query_timestamp: timestamp[s]
expected_response: string
gold_json: string
answer_type: string
answer_normalization: string
evidence_session_ids: list<item: string>
child 0, item: string
evidence_session_indices: list<item: int64>
child 0, item: int64
evidence_relative_positions: list<item: double>
child 0, item: double
session_count: int64
evidence_session_count: int64
filler_session_count: int64
topical_haystack_session_count: int64
samekey_haystack_session_count: int64
history_audio_tokens: int64
history_duration_seconds: double
paired_question_id: string
benchmark_version: string
benchmark: string
messages: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
evidence_messages: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
session_ids: list<item: string>
child 0, item: string
dependency_keys: list<item: string>
child 0, item: string
dependency_group: string
question_modality: string
query_transform: struct<messages: struct<audio_part_index: int64, question_audio: string, historical_turns_sha256: st (... 347 chars omitted)
child 0, messages: struct<audio_part_index: int64, question_audio: string, historical_turns_sha256: string, original_me (... 104 chars omitted)
child 0, audio_part_index: int64
child 1, question_audio: string
child 2, historical_turns_sha256: string
child 3, original_messages_sha256: string
child 4, transformed_messages_sha256: string
child 5, system_before: string
child 6, system_after: string
child 1, evidence_messages: struct<audio_part_index: int64, question_audio: string, historical_turns_sha256: string, original_me (... 104 chars omitted)
child 0, audio_part_index: int64
child 1, question_audio: string
child 2, historical_turns_sha256: string
child 3, original_messages_sha256: string
child 4, transformed_messages_sha256: string
child 5, system_before: string
child 6, system_after: string
file_id: string
position: string
support_indices: list<item: int64>
child 0, item: int64
query: string
kept_indices: list<item: int64>
child 0, item: int64
split: string
answer_text: string
supporting_text: string
to
{'file_id': Value('string'), 'query': Value('string'), 'split': Value('string'), 'position': Value('string'), 'question_text': Value('string'), 'answer_text': Value('string'), 'supporting_text': Value('string'), 'benchmark': Value('string'), 'item_id': Value('string'), 'messages': List({'role': Value('string'), 'content': Json(decode=True)}), 'evidence_messages': List({'role': Value('string'), 'content': Json(decode=True)}), 'support_indices': List(Value('int64')), 'kept_indices': List(Value('int64')), 'expected_response': Value('string'), 'gold_json': Value('string'), 'answer_type': Value('string'), 'answer_normalization': Value('string'), 'evidence_type': Value('string'), 'memory_operation': Value('string'), 'dependency_keys': List(Value('string')), 'dependency_group': Value('string'), 'question_modality': Value('string'), 'query_transform': {'messages': {'audio_part_index': Value('int64'), 'question_audio': Value('string'), 'historical_turns_sha256': Value('string'), 'original_messages_sha256': Value('string'), 'transformed_messages_sha256': Value('string'), 'system_before': Value('string'), 'system_after': Value('string')}, 'evidence_messages': {'audio_part_index': Value('int64'), 'question_audio': Value('string'), 'historical_turns_sha256': Value('string'), 'original_messages_sha256': Value('string'), 'transformed_messages_sha256': Value('string'), 'system_before': Value('string'), 'system_after': Value('string')}}}
because column names don't match
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1835, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 621, in wrapped
for item in generator(*args, **kwargs):
~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 361, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2381, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2309, in cast_table_to_schema
raise CastError(
...<3 lines>...
)
datasets.table.CastError: Couldn't cast
item_id: string
question_id: string
context_length: string
family_id: string
evidence_type: string
memory_operation: string
subtype: string
question_text: string
query_timestamp: timestamp[s]
expected_response: string
gold_json: string
answer_type: string
answer_normalization: string
evidence_session_ids: list<item: string>
child 0, item: string
evidence_session_indices: list<item: int64>
child 0, item: int64
evidence_relative_positions: list<item: double>
child 0, item: double
session_count: int64
evidence_session_count: int64
filler_session_count: int64
topical_haystack_session_count: int64
samekey_haystack_session_count: int64
history_audio_tokens: int64
history_duration_seconds: double
paired_question_id: string
benchmark_version: string
benchmark: string
messages: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
evidence_messages: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
session_ids: list<item: string>
child 0, item: string
dependency_keys: list<item: string>
child 0, item: string
dependency_group: string
question_modality: string
query_transform: struct<messages: struct<audio_part_index: int64, question_audio: string, historical_turns_sha256: st (... 347 chars omitted)
child 0, messages: struct<audio_part_index: int64, question_audio: string, historical_turns_sha256: string, original_me (... 104 chars omitted)
child 0, audio_part_index: int64
child 1, question_audio: string
child 2, historical_turns_sha256: string
child 3, original_messages_sha256: string
child 4, transformed_messages_sha256: string
child 5, system_before: string
child 6, system_after: string
child 1, evidence_messages: struct<audio_part_index: int64, question_audio: string, historical_turns_sha256: string, original_me (... 104 chars omitted)
child 0, audio_part_index: int64
child 1, question_audio: string
child 2, historical_turns_sha256: string
child 3, original_messages_sha256: string
child 4, transformed_messages_sha256: string
child 5, system_before: string
child 6, system_after: string
file_id: string
position: string
support_indices: list<item: int64>
child 0, item: int64
query: string
kept_indices: list<item: int64>
child 0, item: int64
split: string
answer_text: string
supporting_text: string
to
{'file_id': Value('string'), 'query': Value('string'), 'split': Value('string'), 'position': Value('string'), 'question_text': Value('string'), 'answer_text': Value('string'), 'supporting_text': Value('string'), 'benchmark': Value('string'), 'item_id': Value('string'), 'messages': List({'role': Value('string'), 'content': Json(decode=True)}), 'evidence_messages': List({'role': Value('string'), 'content': Json(decode=True)}), 'support_indices': List(Value('int64')), 'kept_indices': List(Value('int64')), 'expected_response': Value('string'), 'gold_json': Value('string'), 'answer_type': Value('string'), 'answer_normalization': Value('string'), 'evidence_type': Value('string'), 'memory_operation': Value('string'), 'dependency_keys': List(Value('string')), 'dependency_group': Value('string'), 'question_modality': Value('string'), 'query_transform': {'messages': {'audio_part_index': Value('int64'), 'question_audio': Value('string'), 'historical_turns_sha256': Value('string'), 'original_messages_sha256': Value('string'), 'transformed_messages_sha256': Value('string'), 'system_before': Value('string'), 'system_after': Value('string')}, 'evidence_messages': {'audio_part_index': Value('int64'), 'question_audio': Value('string'), 'historical_turns_sha256': Value('string'), 'original_messages_sha256': Value('string'), 'transformed_messages_sha256': Value('string'), 'system_before': Value('string'), 'system_after': Value('string')}}}
because column names don't match
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1379, in compute_config_parquet_and_info_response
parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
~~~~~~~~~~~~~~~~~~~~~~~~~^
builder, max_dataset_size_bytes=max_dataset_size_bytes
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 956, in stream_convert_to_parquet
builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1702, in _prepare_split
for job_id, done, content in self._prepare_split_single(
~~~~~~~~~~~~~~~~~~~~~~~~~~^
gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1887, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
file_id string | query string | split string | position string | question_text string | answer_text string | supporting_text string | benchmark string | item_id string | messages list | evidence_messages list | support_indices list | kept_indices list | expected_response string | gold_json string | answer_type string | answer_normalization string | evidence_type string | memory_operation string | dependency_keys list | dependency_group string | question_modality string | query_transform dict |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
t_5bb79360-9e3b-400c-a072-41c0985211f3 | system | test_freq | front | Could you remind me about what you mentioned regarding Tom Brady's book? | Sure. I mentioned that Tom Brady has a book entitled "The Athlete's Bible." | Yes. I just learned Tom Brady has a book entitled "The Athlete's Bible". | contextdialog | t_5bb79360-9e3b-400c-a072-41c0985211f3|system|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
1
] | [
0,
1
] | answer | "Sure. I mentioned that Tom Brady has a book entitled \"The Athlete's Bible.\"" | text | semantic | system | recall | [
"dialog:t_5bb79360-9e3b-400c-a072-41c0985211f3"
] | group_00413 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/93e2d212c82b0226a9e9d61f3bad7dec7a6b59d41f3368199477d28ebfb7e6e2.wav",
"historical_turns_sha256": "0b99fe0d5f91c5fc134ee1b27f2f845eab60ff3c7e186c9deddfc15402d... |
t_11c26cbc-8461-468c-bb13-e379e6e2ec95 | user | test_freq | back | Could you remind me what I said about the highest college football score earlier in our conversation? | You mentioned that it was when Georgia Tech beat Cumberland two hundred twenty-two to zero. | Yeah it was when Georgia Tech beat Cumberland 222-0. What a defeat. | contextdialog | t_11c26cbc-8461-468c-bb13-e379e6e2ec95|user|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
10
] | [
10,
11
] | answer | "You mentioned that it was when Georgia Tech beat Cumberland two hundred twenty-two to zero." | text | semantic | user | recall | [
"dialog:t_11c26cbc-8461-468c-bb13-e379e6e2ec95"
] | group_00306 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/281d513b0384d233d8c90f56efd0dd5ad4fb77500491648303b2597e1c3153a1.wav",
"historical_turns_sha256": "e9eef5eec7025da26744ed40717eb5223feaa83d001f80a8b04d903ac04... |
t_1c0bf5ac-e3ed-4fb1-921b-d813a0301aba | system | test_freq | back | Could you remind me where Baker Mayfield is currently playing as a professional player? | Yes, Baker Mayfield plays with the Cleveland Browns. | Yes, young player. with a lot of hype. He plays with the Cleveland Browns. I believe it's his first year. | contextdialog | t_1c0bf5ac-e3ed-4fb1-921b-d813a0301aba|system|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
15
] | [
14,
15
] | answer | "Yes, Baker Mayfield plays with the Cleveland Browns." | text | semantic | system | recall | [
"dialog:t_1c0bf5ac-e3ed-4fb1-921b-d813a0301aba"
] | group_00322 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/1afc2e3c8e936ba07981004b9075ff723cdce7e91d5f45d77f114f68112c94af.wav",
"historical_turns_sha256": "e80dadae567e0ee46126c94bfb05aa4d7f3a800b47f613221632a62e4e9... |
t_1e8269cd-1b3c-4d0a-a113-84e09de14712 | system | test_rare | back | Could you remind me what surprising fact you mentioned about Roger Federer related to Swiss stamps? | Roger Federer is the first living person in Switzerland to be honored with a stamp. | What? LOL He is the first living person in Switzerland to be honored with a stamp. How neat! | contextdialog | t_1e8269cd-1b3c-4d0a-a113-84e09de14712|system|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
11
] | [
10,
11
] | answer | "Roger Federer is the first living person in Switzerland to be honored with a stamp." | text | semantic | system | recall | [
"dialog:t_1e8269cd-1b3c-4d0a-a113-84e09de14712"
] | group_00031 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/3eb97b7f4ffc1472c6570b7f64701f2f0f5cd892a1dd8922199e86cde9d1b978.wav",
"historical_turns_sha256": "e7c9930ce3328305d7e9cb708c709120982332bbc6876ab281bcc14dd03... |
t_de97d521-a6af-430d-81b9-a8b8836b82b9 | system | test_rare | front | Could you remind me what you said earlier about when you got your first Xbox and why you prefer it over other systems? | I prefer Xbox because it's the only system I've had, and I got one way back in two thousand one. | I like xbox more because honestly it's the only system I've had. I remember getting one way back in 2001. | contextdialog | t_de97d521-a6af-430d-81b9-a8b8836b82b9|system|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
3
] | [
2,
3
] | answer | "I prefer Xbox because it's the only system I've had, and I got one way back in two thousand one." | text | semantic | system | recall | [
"dialog:t_de97d521-a6af-430d-81b9-a8b8836b82b9"
] | group_00244 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/084095c51b5b58bc40e42c7d7b6bb01d17e7a76fc6499ec0639f4b8559d6e1e5.wav",
"historical_turns_sha256": "b04ab6007bc694ea97ab72a8967aded6f5221210deb31e6d0bc6dacdc97... |
t_17fa19af-d6b8-4f9e-8d0d-27242b12c43c | system | test_freq | front | Could you remind me of what you explained earlier about conferences in the NFL? | I mentioned that they divide teams into two conferences, the AFC and the NFC. | I like watching football. I find it interesting that they divide teams into two conferences (AFC vs NFC). Do you think 17 weeks of the regular is enough football in a season? | contextdialog | t_17fa19af-d6b8-4f9e-8d0d-27242b12c43c|system|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
3
] | [
2,
3
] | answer | "I mentioned that they divide teams into two conferences, the AFC and the NFC." | text | semantic | system | recall | [
"dialog:t_17fa19af-d6b8-4f9e-8d0d-27242b12c43c"
] | group_00318 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/37b491966f7388a5de8341a0785323bd48ff7cf4aece2120b326ad797ffa6917.wav",
"historical_turns_sha256": "7acd0950ae73ff90287702ed50be1958eaa66e6d106ceb1923badab2fa4... |
t_f5ec12d9-b611-4fdd-b662-be5f9f19d437 | user | test_rare | back | Could you remind me the funny Chinese name I mentioned for Guardians of the Galaxy? | You mentioned it was called interplanetary unusual attack team. | That is a long time ago! What do you think about the Chinese name for Guardians of the Galaxy over there? It is the: interplanetary unusual attack team LOL | contextdialog | t_f5ec12d9-b611-4fdd-b662-be5f9f19d437|user|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
18
] | [
18,
19
] | answer | "You mentioned it was called interplanetary unusual attack team." | text | semantic | user | recall | [
"dialog:t_f5ec12d9-b611-4fdd-b662-be5f9f19d437"
] | group_00274 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/62bbd40c201f73a6b11956a568a89edd85c7dd53707ed8a974a1019976363583.wav",
"historical_turns_sha256": "060cac02532059af54769a4f10c0357803f5282e46f383a77a2053f965a... |
t_771bf051-8ff1-4cef-a217-a9324e1e4ae9 | system | test_rare | back | Could you remind me what you mentioned earlier about the free class on AI at Stanford? | I hear that Stanford has a free class on AI. I might have to check that out. | Yeah crazy huh. I bet one day they have robots that are very similiar to humans. It makes me want to learn more about it. I hear that Stanford has a free class on AI. I might have to heck that out. | contextdialog | t_771bf051-8ff1-4cef-a217-a9324e1e4ae9|system|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
11
] | [
10,
11
] | answer | "I hear that Stanford has a free class on AI. I might have to check that out." | text | semantic | system | recall | [
"dialog:t_771bf051-8ff1-4cef-a217-a9324e1e4ae9"
] | group_00122 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/636f291b66e39d551fd9a81b6bdfe821927b052b3d2b5d0ffccaeb7dac835119.wav",
"historical_turns_sha256": "7eba6e2b758f086657a5916d314bdb7ee232ded15c73ce6197fa415b92a... |
t_4663c5bb-22ad-4278-8f80-5f376d28835b | system | test_freq | front | Can you remind me which NFL team you mentioned is your favorite and why you respect them? | I would say the Packers. You have to respect a team that can play outdoors in that kind of weather. | I would say the Packers. You have to respect a team that can play outdoors in that kind of weather. | contextdialog | t_4663c5bb-22ad-4278-8f80-5f376d28835b|system|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
3
] | [
2,
3
] | answer | "I would say the Packers. You have to respect a team that can play outdoors in that kind of weather." | text | semantic | system | recall | [
"dialog:t_4663c5bb-22ad-4278-8f80-5f376d28835b"
] | group_00380 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/11d102aa7d79d71b15c4d62d2e27a804a4fae0df2f6c6b473371b3b464dae22c.wav",
"historical_turns_sha256": "51d231f751726411213e1720a32a47d6a85d4f8be3dafd286abc1009468... |
t_2f9ac4d4-5b63-4e55-b9ef-c3a6b04f6086 | system | test_rare | back | Could you remind me what you mentioned about Lincoln suffering from smallpox during an important event? | I mentioned that Lincoln did the Gettysburg Address while suffering from smallpox. | wow, more eerie also! Almost as eerie as Lincoln doing the gettysburg address while suffering from smallpox. That is like michael jordan and his flu game lol | contextdialog | t_2f9ac4d4-5b63-4e55-b9ef-c3a6b04f6086|system|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
13
] | [
12,
13
] | answer | "I mentioned that Lincoln did the Gettysburg Address while suffering from smallpox." | text | semantic | system | recall | [
"dialog:t_2f9ac4d4-5b63-4e55-b9ef-c3a6b04f6086"
] | group_00058 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/b8ea17ac260453ff9f9183e9846fbb19576db9300de4f0087103b1edfc496cd8.wav",
"historical_turns_sha256": "9525b8266def3433ba4d344519414dfe66cd08b78f146c160062ba68497... |
t_9964e4f9-b803-43d2-9ebf-1542108fd9ad | user | test_rare | back | What did I mention earlier about how Deadpool described himself in the comic? | You noted that the Deadpool comic described himself as Ryan Reynolds crossed with a shar-pei. | Well the Deadpool comic described himself as Ryan Reynold crossed with a shar-pei | contextdialog | t_9964e4f9-b803-43d2-9ebf-1542108fd9ad|user|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
16
] | [
16,
17
] | answer | "You noted that the Deadpool comic described himself as Ryan Reynolds crossed with a shar-pei." | text | semantic | user | recall | [
"dialog:t_9964e4f9-b803-43d2-9ebf-1542108fd9ad"
] | group_00158 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/f22d8a27db646801adec70b75148380ba0afbb9d6405f61db97d710fc56d76e2.wav",
"historical_turns_sha256": "ddb49d4295ee4cf81cdf9598f866a6ff43f5aaa3b86286abaf1868757d0... |
t_6a3dddc7-01d3-4d4a-ad54-0929454768ab | user | test_freq | front | What was it I said earlier about why I like the Patriots? | You mentioned that you like teams that win, like the Patriots. | ya I watch the big games and we have parties sometimes, but I don't really follow a team, I just like teams that win like the patriots haha | contextdialog | t_6a3dddc7-01d3-4d4a-ad54-0929454768ab|user|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
6
] | [
6,
7
] | answer | "You mentioned that you like teams that win, like the Patriots." | text | semantic | user | recall | [
"dialog:t_6a3dddc7-01d3-4d4a-ad54-0929454768ab"
] | group_00430 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/d67da4ce847bd35cca974b5e9f02c201457331d1cff9cd23068ab5dabc66b136.wav",
"historical_turns_sha256": "25568196fabd4064f05fd2fa9eddab5d9fe073b80708bb3cd11d43b9e71... |
t_2324b94a-8012-4ecc-82ef-12386cc69ef4 | user | test_rare | back | Can you remind me what comic series I mentioned that's about fixing superhero collateral damage? | You mentioned a comic series about fixing collateral damage caused by superheroes. | lol There was a comic series about fixing collateral damage caused by superheroes. I'm not familiar with that one. | contextdialog | t_2324b94a-8012-4ecc-82ef-12386cc69ef4|user|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
12
] | [
12,
13
] | answer | "You mentioned a comic series about fixing collateral damage caused by superheroes." | text | semantic | user | recall | [
"dialog:t_2324b94a-8012-4ecc-82ef-12386cc69ef4"
] | group_00040 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/347787af93663f28344b13265d4cd55a5e6822a934332e5db24f61b7b9e5611e.wav",
"historical_turns_sha256": "98166d98a0c9f96ac546091ef2666715b8947ca1ffed9b7590259fa021c... |
t_43834b22-1626-43a6-a08f-4a2912057a5c | user | test_freq | front | Could you remind me what I said about the historical role of the Vice President before eighteen fifty? | You mentioned liking the way the runner-up became Vice President and how it might have balanced the representation of parties. | Yes, like in the UK. I like the way they did things before 1850 where the runner up became Vice President. Maybe things were a little more balanced then since I assume both parties were represented. | contextdialog | t_43834b22-1626-43a6-a08f-4a2912057a5c|user|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
4
] | [
4,
5
] | answer | "You mentioned liking the way the runner-up became Vice President and how it might have balanced the representation of parties." | text | semantic | user | recall | [
"dialog:t_43834b22-1626-43a6-a08f-4a2912057a5c"
] | group_00378 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/4603022fcaee1cfac9c1d5a89004562069ba7dce2bbd82a52f0dbbd570ad6de9.wav",
"historical_turns_sha256": "ac745a5b17fb3814209e54d6bd2df9be56455c0813c71788c8b4f67132a... |
t_d912e074-c397-44b7-90bc-2072afe5bdc0 | user | test_freq | back | Could you remind me what I mentioned earlier about the Patriots in relation to the playoffs? | You mentioned being sick of seeing the Patriots since it's boring to see them in the playoffs repeatedly, and despite six teams from each conference making the playoffs, you end up with the Patriots again. | I'm sure I will but I'm not excited about it. I'm so sick of seeing the Patriots. It's boring to see them at this point. I'd rather see other teams. Six teams from each conference make the playoffs and we end up with the Patriots again/ | contextdialog | t_d912e074-c397-44b7-90bc-2072afe5bdc0|user|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
18
] | [
18,
19
] | answer | "You mentioned being sick of seeing the Patriots since it's boring to see them in the playoffs repeatedly, and despite six teams from each conference making the playoffs, you end up with the Patriots again." | text | semantic | user | recall | [
"dialog:t_d912e074-c397-44b7-90bc-2072afe5bdc0"
] | group_00607 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/9175506437b92de3983f1eec7a3485e31ce4bca5354fffd7be3b821e2c2700ed.wav",
"historical_turns_sha256": "2b01c060060f298aa32e0cb50718409d40aa1d165ccfb91c95be15a9362... |
t_a1a68ae6-7175-49a4-acb1-d6dd0b5546f5 | system | test_rare | back | Could you remind me what you mentioned about Han Solo's background before joining the Millennium Falcon? | Han Solo was a tie fighter before he even became the pilot of the Millennium Falcon. | I see, so Ford is actually lucky, you know Han Solo was a tie fighter before he evenbecame the pilot of the millenium falcon. | contextdialog | t_a1a68ae6-7175-49a4-acb1-d6dd0b5546f5|system|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
19
] | [
18,
19
] | answer | "Han Solo was a tie fighter before he even became the pilot of the Millennium Falcon." | text | semantic | system | recall | [
"dialog:t_a1a68ae6-7175-49a4-acb1-d6dd0b5546f5"
] | group_00168 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/26c15d672abb0d4e7be8e273e283db85fd2f28288fff314f461c83e31dfb055f.wav",
"historical_turns_sha256": "ae70d77953cca811bab0d953eb61843c7acc77f1b227e9d28749fcf1c65... |
t_fdd0ebc4-2455-4354-9955-ae6864d79055 | system | test_rare | front | Can you remind me what you mentioned about the Marvel characters at the theme parks earlier? | Marvel signed a contract with Universal back in the nineteen nineties, so Disney can't show the characters at Disney World, but they can at Disney Land. | You probably did. Marvel signed a contract with Universal back in the 1990s so Disney can't show the characters at Disney World but they can at Disney Land. | contextdialog | t_fdd0ebc4-2455-4354-9955-ae6864d79055|system|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
7
] | [
6,
7
] | answer | "Marvel signed a contract with Universal back in the nineteen nineties, so Disney can't show the characters at Disney World, but they can at Disney Land." | text | semantic | system | recall | [
"dialog:t_fdd0ebc4-2455-4354-9955-ae6864d79055"
] | group_00286 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/b7a5d736017c7d75e57beb7dfe24ec403e5ae166adbef289d6047a9281383200.wav",
"historical_turns_sha256": "087ac482266a20859d1790d82a20c83e75a5ce98d82fd5cdc88012c6e3c... |
t_e26b2fe6-d779-4c99-b2a0-90a4af85dc51 | user | test_rare | front | Could you remind me what I mentioned earlier about the languages Serena Williams speaks? | You mentioned that she speaks Italian and French, as does her sister. | yeah she speaks italian, french, as does her sister | contextdialog | t_e26b2fe6-d779-4c99-b2a0-90a4af85dc51|user|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
8
] | [
8,
9
] | answer | "You mentioned that she speaks Italian and French, as does her sister." | text | semantic | user | recall | [
"dialog:t_e26b2fe6-d779-4c99-b2a0-90a4af85dc51"
] | group_00250 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/ce166c612b8e988063e0b6421bdb019dff8d537f127fb61fd4f2d7736b5202a2.wav",
"historical_turns_sha256": "cf3e7f17ad7c26c1808176be7b8f1a831684b121ed37fda910905f74a72... |
t_d01805f5-8c84-4897-835a-8ed80b465915 | system | test_freq | back | Could you remind me who you mentioned earlier about currently teaching drama master classes in the UK? | Patrick Stewart is the one currently teaching drama master classes in the UK. | Strange how things happen. Patrick Stewart teaches Drama now. He teaches master classes in the UK. He would be amazing to learn from. | contextdialog | t_d01805f5-8c84-4897-835a-8ed80b465915|system|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
19
] | [
18,
19
] | answer | "Patrick Stewart is the one currently teaching drama master classes in the UK." | text | semantic | system | recall | [
"dialog:t_d01805f5-8c84-4897-835a-8ed80b465915"
] | group_00592 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/92c8a0f52af93ce6c3c704f8ed9d7de70a28d42327fc2089592511ecb9ab1f98.wav",
"historical_turns_sha256": "612166a195381f9f11116c9a5deca2d8f18fee955fa723cded36c6facc0... |
t_4685cf42-d65f-4a63-a28a-6ad79c1db28b | user | test_freq | front | Could you remind me what I said earlier about the charity trip that Tom Brady's family went on? | You mentioned that Tom Brady and his family recently went on a charity trip to Qatar. | Yea and they have a couple of children together. They recently went on a charity trip to Qatar. | contextdialog | t_4685cf42-d65f-4a63-a28a-6ad79c1db28b|user|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
8
] | [
8,
9
] | answer | "You mentioned that Tom Brady and his family recently went on a charity trip to Qatar." | text | semantic | user | recall | [
"dialog:t_4685cf42-d65f-4a63-a28a-6ad79c1db28b"
] | group_00381 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/e383eb6b50d0de2045761a73342c6c61d7fff99864b1067a94c641a59d725d10.wav",
"historical_turns_sha256": "f5e2568ee3e7f8cc0a2065b6ed5a179c5e5c9d532af2da9a48764b3d77e... |
t_6a3dddc7-01d3-4d4a-ad54-0929454768ab | system | test_freq | front | Can you remind me what you said earlier about what Tom Brady's book is called or known as? | It is being dubbed as the Athlete's Bible. | Maybe they say it is super healthy. I guess his book is being dubbed as the Athlete's Bible. | contextdialog | t_6a3dddc7-01d3-4d4a-ad54-0929454768ab|system|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
3
] | [
2,
3
] | answer | "It is being dubbed as the Athlete's Bible." | text | semantic | system | recall | [
"dialog:t_6a3dddc7-01d3-4d4a-ad54-0929454768ab"
] | group_00430 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/19c87cf47cac977061d01ec5ad2275a932fd8e69b602c48f6e24a7904f2b3a33.wav",
"historical_turns_sha256": "25568196fabd4064f05fd2fa9eddab5d9fe073b80708bb3cd11d43b9e71... |
t_9070284f-e8ee-4ff6-82e4-ec55607c5379 | system | test_freq | back | Can you remind me what you said about your family's connection to preaching? | I mentioned that several members of my family, brothers and sisters, preach, though a lot of people don't believe in women preaching. | Yes you are right, several members of my family, brothers and sisters preach, though a lot of people don't believe in women preaching. | contextdialog | t_9070284f-e8ee-4ff6-82e4-ec55607c5379|system|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
19
] | [
18,
19
] | answer | "I mentioned that several members of my family, brothers and sisters, preach, though a lot of people don't believe in women preaching." | text | semantic | system | recall | [
"dialog:t_9070284f-e8ee-4ff6-82e4-ec55607c5379"
] | group_00478 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/14cbbf24326eaba1f8e589b1feaee928044b1ba4688b6d605e40850af45ee7fb.wav",
"historical_turns_sha256": "24ef15af32c8dc8b129488432ca5cbafb9f296009b3bf52236d518f26e0... |
t_30cb4669-8dcc-48ee-8d96-0a90ee2bc662 | user | test_freq | front | Can you remind me what I said about my experience with being laid back or passive during a game? | You mentioned that you probably couldn't get more laid back or passive and that you just don't care unless you got beat two hundred twenty-two to zero, which would make you have a team meeting afterward. | Probably not. I am not sure I could get more laid back or passive. I just don't care... I would care if I got beat 222-0. I would have a team meeting after that. | contextdialog | t_30cb4669-8dcc-48ee-8d96-0a90ee2bc662|user|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
6
] | [
6,
7
] | answer | "You mentioned that you probably couldn't get more laid back or passive and that you just don't care unless you got beat two hundred twenty-two to zero, which would make you have a team meeting afterward." | text | semantic | user | recall | [
"dialog:t_30cb4669-8dcc-48ee-8d96-0a90ee2bc662"
] | group_00346 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/1f6ca1d4c33eb689cc2a6cda16b73cbf124a912e5a52470189610d4fdcdd495d.wav",
"historical_turns_sha256": "29fe5973e8925dbfb840e6b178b0511076005dea2cdc942dae80d35cdad... |
t_36066ee7-42fb-413c-bce1-25a6933b938a | user | test_freq | front | What was the funny terminology I mentioned earlier that Keith Jackson used? | You mentioned that Keith Jackson used terms like "bantam rooster" and "Whoa Nellie!" | He had a lot of funny terminology. Like a "bantam rooster" and "Whoa Nellie!" | contextdialog | t_36066ee7-42fb-413c-bce1-25a6933b938a|user|front | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
4
] | [
4,
5
] | answer | "You mentioned that Keith Jackson used terms like \"bantam rooster\" and \"Whoa Nellie!\"" | text | semantic | user | recall | [
"dialog:t_36066ee7-42fb-413c-bce1-25a6933b938a"
] | group_00353 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/a11ad6b9560eff309a5bf77f83ddff709dee9e78674f80af42bd46a521b1d8e1.wav",
"historical_turns_sha256": "066eeb037ae46d6db525726493bcadae88322d2d2ceeb93798d0871137c... |
t_3d40c59b-fdcc-463e-a6f9-929baf5e6338 | system | test_freq | back | Could you remind me what you mentioned about the rule involving NFL cheerleaders and restaurants? | Cheerleaders are not allowed to eat in the same restaurant as any NFL player and if they are already dining in the restaurant and any NFL player comes, the cheerleaders are required to leave. It is the biggest rule in the NFL. | Cheerleader are not allowed to eating in the same restaurant as any NFL player and if they already dining in the restaurant if any NFL player comes the cheerleader required to leave. It is the biggest rule in the NFL. | contextdialog | t_3d40c59b-fdcc-463e-a6f9-929baf5e6338|system|back | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
{
"role": "system",
"content": "Answer the final user's question using the preceding conversation. Give a concise answer without explaining your reasoning."
},
{
"role": "user",
"content": [
{
"type": "audio",
"audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bot... | [
15
] | [
14,
15
] | answer | "Cheerleaders are not allowed to eat in the same restaurant as any NFL player and if they are already dining in the restaurant and any NFL player comes, the cheerleaders are required to leave. It is the biggest rule in the NFL." | text | semantic | system | recall | [
"dialog:t_3d40c59b-fdcc-463e-a6f9-929baf5e6338"
] | group_00368 | audio | {
"messages": {
"audio_part_index": 0,
"question_audio": "/ossfs/workspace/ccfa-workfiles/experiments/memory-bottleneck/results/public_memory/audio/1a9355b392a0a50f2b362c7b2adc349c4e7ade6060036330586ea7d15033dcd9.wav",
"historical_turns_sha256": "1a0c92bdc76f9724f70dfdda7cfd71c97495c9dbe805902f89553cbaa77... |
Speech-LLM Memory Research Archive
2026-11-04 增量备份: 见 更新目录与上传状态。原 2026-10-28 快照及其校验记录保持不变。
音频大模型历史记忆研究的工作文件归档,快照日期为 2026-10-28。 包括前期历史干扰诊断、RAMI、后续 QA 机制实验和架构研究。
Rebuttal 入口: 历史论文版本、配图与脚本、
原始证据与恢复指南。各版 PDF 和原始源码 ZIP 另有 papers/iclr2027/ 便捷下载副本。
这是按作者要求公开的研究备份,不是已完成的方法发布,也不是匿名投稿包。目录中同时保留成功、 不显著、负向结果及失败运行记录;不要把某个中间目录的存在视为该实验有效或通过。 每项实验应以其冻结方案、逐题原始输出、完成标记及核查记录一起判断。
文件组织
| 压缩包名称前缀 | 内容 |
|---|---|
01_architecture_code_protocols |
近期架构研究的源代码、研究计划、冻结方案、依赖配置和文献笔记 |
02_architecture_experiment_results |
MOSS / MiMo 等实验的逐题输出、统计分析、训练权重、审计记录及冻结源代码 |
03_architecture_training_tensor_cache |
本项目生成的训练状态缓存 |
04_memory_interference_code_protocols |
前作及 QA 机制实验的构造、推理、训练、分析与绘图脚本和方案 |
05_memory_interference_experiment_results |
历史干扰、因果替换、组合预测、后续修正等原始结果、日志、图表和权重 |
06_memory_interference_data |
训练/评测材料、配对清单、来源映射、donor 清单和项目内数据 |
07_rami_benchmark_and_review |
RAMI 数据、200 条审核材料、两份人工审核确认、模型输出与评分脚本 |
08_asr_memory_experiments |
早期转写历史干扰实验、分层定位、mask / Value-patch 及 199 对样本案例导出 |
09_manuscripts_figures_reproducibility |
现存论文源码/PDF、图表、参考文献、旧复现包和官方模板 |
10_legacy_asr_raw_outputs |
早期共享目录中与记忆研究有关的逐题输出、日志和检查点,包括 MOSS 199 对转写原始结果 |
11_preserved_manuscript_builds |
从临时目录额外保存的 2026-10-19 / 2026-10-20 稿件源码、编译 PDF 和日志 |
12_model_runtime_sources |
当前本地 MOSS / MiMo 推理源码、依赖声明及 MiMo 后端兼容修改;不含公共基础权重 |
每个 part-NNN.tar.gz 都是可独立解压的压缩包,不是必须先拼接的二进制分卷。
包内保留原项目的相对路径,避免重新命名源代码、结果或样本后破坏引用关系。
大文件数量和体积以 metadata/archives.json 为准。
清单与完整性检查
metadata/files.jsonl:每个实际归档文件的位置、所属压缩包、大小和 SHA-256。metadata/archives.json:每个压缩包的大小、文件数和 SHA-256。SHA256SUMS:压缩包校验。metadata/payload_SHA256SUMS:解压后文件校验。metadata/scope.json:本次选定的项目目录和范围。metadata/exclusions.json:环境缓存、基础权重下载副本、其他项目等排除项目。metadata/external_symlinks.json:未跟随的外部/符号链接;不会把链接目标所在的其他项目整棵复制进来。metadata/credential_redactions.json:归档副本中的凭据脱敏记录,不含凭据值。metadata/source_artifact_issues.json:原本已存在的截断下载、LFS 指针等材料状态,不与本次传输损坏混淆。metadata/packaging_environment.json:打包时的 Python 依赖版本,不能替代各实验自己的运行配置。metadata/snapshot.json:本次快照的文件数量、体积及生成状态。metadata/manuscript_versions.json:历史 PDF、源码 ZIP 内部文件清单及版本校验。metadata/figure_provenance.json:图表、源脚本与输入结果位置。metadata/convenience_copies.json:便捷下载副本与原始归档文件的逐项对应。metadata/external_runtime_provenance.json:外部模型源码的当前 Git 提交与工作树修改状态,不冒充所有历史实验的精确运行版本。
公开下载示例(上传是否全部完成见 ARCHIVE_STATUS.json):
hf download hongjinsong521/speech-llm-memory-research \
--repo-type dataset --local-dir speech-llm-memory-research
cd speech-llm-memory-research
sha256sum -c SHA256SUMS
mkdir -p restored
for archive in archives/*.tar.gz; do
tar --no-same-owner -xzf "$archive" -C restored
done
(cd restored && sha256sum -c ../metadata/payload_SHA256SUMS)
原始证据与脱敏
本地原文件不被修改。若文本内发现访问令牌,归档副本仅将匹配的凭据替换为
REDACTED_CREDENTIAL,不修改实验数字、模型回答或结论。
清单同时记录源文件与归档文件哈希;被脱敏文件不能再用原源码哈希校验归档副本。
科学记录中的原运行配置、旧路径和历史状态按作者要求保留,因此该备份不是匿名投稿包。
自动扫描不是对所有可能秘密格式的完备识别。
最新的 adapter_source_contrast 双模型运行在归档前已经完成,并有原始输出与
independent_audit.json。adapter_input_exchange 曾发生 MiMo 输入缓存问题:
原失败目录及修复后完整输出均保留,应从 completion_reconciliation.json 查找有效结果,
不要只看原父目录的失败状态。
不包含什么
- 工作区中其他 ACL、音频幻觉、提示注入、ASR 置信度等研究项目。
- API 令牌、会话凭据、Git 内部数据、虚拟环境与可重装的软件缓存。
- 已下载的公共基础模型大权重副本;模型配置和实验记录中的模型标识保留。
- 未显式收集的外部数据和基础模型权重。当前 MOSS / MiMo 推理源码另收集于
12_model_runtime_sources。
本项目训练得到的检查点和生成的张量缓存会保留,不与公共基础模型副本混为一类。 部分脚本原本使用机器绝对路径,恢复后需按实际模型、数据和 Python 环境更新配置。 当前归档不声称已在一台全新机器上从零重新复现全部实验。
使用与许可
原仓库卡的 MIT 标签保留;该标签不改变第三方数据、论文、代码和基础模型的原有许可。 RAMI 原目录中保留数据许可说明;其他材料须遵守各自的上游许可及访问条件。 此仓库用于作者授权的公开研究备份。第三方材料沿用上游许可;该备份不授予额外使用权限。
- Downloads last month
- 557