{ "format": "iclr_video.locked_evaluation_protocol.v1", "protocol_id": "recent4_full_v1", "status": "template", "applies_to": "all baseline and candidate checkpoints", "inference": { "causal_prefix_only": true, "sampling_fps": 1.0, "context_policy": "recent_n", "recent_frames": 4, "timestamp_rule": "match the SimpleStream release: decode a four-second half-open causal prefix window [max(0,t-4),t) at nominal 1 FPS and retain exactly four independently encoded image frames; only prefixes shorter than two raw frames repeat frame zero", "allow_future_frames": false, "allow_global_frames": false, "allow_extra_frame_inspection": false, "allow_persistent_visual_or_text_memory": false, "visual_input_mode": "four independent image frames using qwen-vl-utils fetch_video (image_patch_size=14), never Qwen video tokens", "processor_contract": { "preprocessor_config_sha256": "", "image_processor_type": "Qwen2VLImageProcessorFast", "patch_size": 16, "merge_size": 2, "temporal_patch_size": 2, "shortest_edge": 65536, "longest_edge": 16777216, "reference_visual_tokens_per_frame": 576, "reason": "Bind the processor used by your evaluation before inference." }, "prompt_source": "StreamingBench SimpleStream release MCQ template; OVO backward/realtime SimpleStream release one-letter template; OVO forward frozen official task wrapper; no system message", "decode": { "do_sample": false, "temperature": 0.0 } }, "benchmarks": { "streamingbench": { "scope": "Real-Time full", "export": "data/streamingbench/queries.jsonl", "export_sha256": "", "expected_queries": 2495, "expected_groups": { "real_time_visual": 2495 }, "primary_metric": "official Real-Time accuracy" }, "ovo": { "scope": "all 12 tasks: Real-Time, Backward, and Forward", "export": "data/ovo/queries.jsonl", "export_sha256": "", "expected_queries": 3035, "expected_tasks": { "ACR": 109, "ASI": 148, "ATR": 116, "CRR": 240, "EPM": 297, "FPD": 101, "HLD": 186, "OCR": 149, "OJR": 184, "REC": 698, "SSR": 629, "STU": 178 }, "primary_metric": "official Total Avg", "secondary_metrics": [ "micro Overall", "Real-Time Avg", "Backward Avg", "Forward Avg", "RT/BT Avg" ] } } }