bradduy commited on
Commit
9bed4ee
·
verified ·
1 Parent(s): d3cba71

R1 revision: selected caption of every rule in the revised paper

Browse files

predictions_r1/<benchmark>/<rule>__<split>.json in the IFCap evaluation format, rebuilt with the corrected MBR agent; manifest.json lists every rule.

This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. predictions_r1/coco/blip2cap__overall.json +3 -0
  2. predictions_r1/coco/blip_top1__overall.json +3 -0
  3. predictions_r1/coco/borda3_lm_bigG_blip__overall.json +3 -0
  4. predictions_r1/coco/cot500_s1_alone__overall.json +3 -0
  5. predictions_r1/coco/cot500_s2_alone__overall.json +3 -0
  6. predictions_r1/coco/cot500_six_blip2__overall.json +3 -0
  7. predictions_r1/coco/cot500_six_s1__overall.json +3 -0
  8. predictions_r1/coco/cot500_six_s2__overall.json +3 -0
  9. predictions_r1/coco/cot500_zsum3__overall.json +3 -0
  10. predictions_r1/coco/cot500_zsum3_s1__overall.json +3 -0
  11. predictions_r1/coco/cot500_zsum3_s2__overall.json +3 -0
  12. predictions_r1/coco/itmflickr_blip_top1__overall.json +3 -0
  13. predictions_r1/coco/itmflickr_stack5_noLM_blip_bigG_vqa_mbr_ground__overall.json +3 -0
  14. predictions_r1/coco/itmflickr_stack6_all_equal__overall.json +3 -0
  15. predictions_r1/coco/itmflickr_zsum3_lm_bigG_blip__overall.json +3 -0
  16. predictions_r1/coco/ladder_stack6_bigG2siglip2__overall.json +3 -0
  17. predictions_r1/coco/ladder_stack6_plus_blip2itm__overall.json +3 -0
  18. predictions_r1/coco/ladder_stack8_all__overall.json +3 -0
  19. predictions_r1/coco/ladder_zsum3_bigG2siglip2__overall.json +3 -0
  20. predictions_r1/coco/ladder_zsum3_plus_blip2itm__overall.json +3 -0
  21. predictions_r1/coco/ladder_zsum3_plus_siglip2__overall.json +3 -0
  22. predictions_r1/coco/lm_top1__overall.json +3 -0
  23. predictions_r1/coco/loo_minus_BLIP__overall.json +3 -0
  24. predictions_r1/coco/loo_minus_MBR__overall.json +3 -0
  25. predictions_r1/coco/loo_minus_VQA__overall.json +3 -0
  26. predictions_r1/coco/loo_minus_bigG__overall.json +3 -0
  27. predictions_r1/coco/loo_minus_ground__overall.json +3 -0
  28. predictions_r1/coco/m4_align2_21__overall.json +3 -0
  29. predictions_r1/coco/m4_align2s1_21__overall.json +3 -0
  30. predictions_r1/coco/m4_bigG21__overall.json +3 -0
  31. predictions_r1/coco/m4_blip21__overall.json +3 -0
  32. predictions_r1/coco/m4_five20__overall.json +3 -0
  33. predictions_r1/coco/m4_five21__overall.json +3 -0
  34. predictions_r1/coco/m4_four21_noMBR__overall.json +3 -0
  35. predictions_r1/coco/m4_s1_21__overall.json +3 -0
  36. predictions_r1/coco/oracle20_approx__overall.json +3 -0
  37. predictions_r1/coco/rel6_mallows__overall.json +3 -0
  38. predictions_r1/coco/rel6_spectral__overall.json +3 -0
  39. predictions_r1/coco/sj_qwen2vl2b_alone__overall.json +3 -0
  40. predictions_r1/coco/sj_qwen2vl2b_stack6swap__overall.json +3 -0
  41. predictions_r1/coco/sj_qwen2vl2b_zsum3plus__overall.json +3 -0
  42. predictions_r1/coco/sj_smolvlm256m_alone__overall.json +3 -0
  43. predictions_r1/coco/sj_smolvlm256m_stack6swap__overall.json +3 -0
  44. predictions_r1/coco/sj_smolvlm256m_zsum3plus__overall.json +3 -0
  45. predictions_r1/coco/sj_smolvlm500m_alone__overall.json +3 -0
  46. predictions_r1/coco/sj_smolvlm500m_stack6swap__overall.json +3 -0
  47. predictions_r1/coco/sj_smolvlm500m_zsum3plus__overall.json +3 -0
  48. predictions_r1/coco/stack4_noLM_blip_bigG_vqa_mbr__overall.json +3 -0
  49. predictions_r1/coco/stack4_zsum3_ground__overall.json +3 -0
  50. predictions_r1/coco/stack4_zsum3_mbr__overall.json +3 -0
predictions_r1/coco/blip2cap__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dfdb7bd186d5a8d75c4e5cda0bef12b00e63126139f2fba99f293934efdeceb
3
+ size 2012198
predictions_r1/coco/blip_top1__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd18cc09bc28d55fd3d1aac2984ad75e7b09536194f74f1b3cc448f0b04da569
3
+ size 2052183
predictions_r1/coco/borda3_lm_bigG_blip__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50195f1685f4fd53e8efdb9265699f4e315a31e2bd29b6cac233a3b5da495111
3
+ size 2051285
predictions_r1/coco/cot500_s1_alone__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff39c678bc2aff83b1debb47005a9bbdf8d785ea753d49d9547ae45d2b354c48
3
+ size 205189
predictions_r1/coco/cot500_s2_alone__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41d1c23d1b4f64677cfa02c8769c933e7b70b2a46025db6069fef872b10acd98
3
+ size 205840
predictions_r1/coco/cot500_six_blip2__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93032576ecb3c78289fe86106f2a836e8211f34a927073ebee565ad4189abc78
3
+ size 205416
predictions_r1/coco/cot500_six_s1__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e97b972a83bf0c6a64db64a0bf7a378223439c8953829181e8cfc2aa07ab778
3
+ size 205419
predictions_r1/coco/cot500_six_s2__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:116c5257ce71dfd24184abc07944865aa3821e121488b81dee2449580e5d6cf3
3
+ size 205564
predictions_r1/coco/cot500_zsum3__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd14fcb24420b78bb3f091f0c8c46d7210691280c9323a9e0f30b9aff7b24bd7
3
+ size 205699
predictions_r1/coco/cot500_zsum3_s1__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8861c502227207ddb0441ff5181fbb714c9171b529ce90d90e8fd38e3f8302b7
3
+ size 205624
predictions_r1/coco/cot500_zsum3_s2__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19dbe47a67cc45c18f04d568d1c2e7bc9f2e3ddff8a2363caa982a41bedfd1ec
3
+ size 205842
predictions_r1/coco/itmflickr_blip_top1__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe4541fd93872fa1a95966ec62d37c07f46f9ade3d427508da5c087fea880ad
3
+ size 2037393
predictions_r1/coco/itmflickr_stack5_noLM_blip_bigG_vqa_mbr_ground__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee32ed066fbbe331fa9e4f161cf191c3bbcd768f2b65f456196314e81f25dbb
3
+ size 2038801
predictions_r1/coco/itmflickr_stack6_all_equal__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d08e82260254e9485411a27c355f99c5253b697d6fc0caecaa64ad3f4d9a96
3
+ size 2042134
predictions_r1/coco/itmflickr_zsum3_lm_bigG_blip__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef69e6b474c7187cb27a9ec4b21734a067c16a066027302e3a0970e387ffc9d
3
+ size 2043158
predictions_r1/coco/ladder_stack6_bigG2siglip2__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8528c3dbfcc13ba56bb8c7e8f451862bdfd4242046e92d70622331c616dd8f7a
3
+ size 2046143
predictions_r1/coco/ladder_stack6_plus_blip2itm__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1979de1be891b84a431d9c3a304f49c2a5e004f0df478f766124cd992b35d8a
3
+ size 2046548
predictions_r1/coco/ladder_stack8_all__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a3de45ccd9165c9136279307eea394bd8c5e47580176353cae71a14414b530a
3
+ size 2047010
predictions_r1/coco/ladder_zsum3_bigG2siglip2__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3742a6f509ae556112869977837c5d4c5a696a2db79c16e1de63bb92b35618
3
+ size 2050242
predictions_r1/coco/ladder_zsum3_plus_blip2itm__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7da87949b526cda75a79429cb015a05ef10254cf43b8c4afd9915df22e2205a
3
+ size 2050422
predictions_r1/coco/ladder_zsum3_plus_siglip2__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f464d91708b469a2d4c422d09369d720b1d67dc05473c97b1e94bb0249829f91
3
+ size 2050098
predictions_r1/coco/lm_top1__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c180e7941141a8996df638f16ba725c2b054e79578c6f563eb7775786208026a
3
+ size 2051104
predictions_r1/coco/loo_minus_BLIP__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44fa38ecf6167763273fb7a001bb3dc0010a3d767976501583656d8377a76ebd
3
+ size 2045849
predictions_r1/coco/loo_minus_MBR__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e273d8aa361bd77f30f8bb3b7a29f30f92444f5f697892479ef6258a0f1c334
3
+ size 2045642
predictions_r1/coco/loo_minus_VQA__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eddef76b622cfa961eafd0fdad85c71c507f1a53d9b2af5bd62a60238a20445
3
+ size 2048023
predictions_r1/coco/loo_minus_bigG__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5241513e311c2b8f1d3132b5225c37847b983542296a53b30d260af15be4f46
3
+ size 2045873
predictions_r1/coco/loo_minus_ground__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1654fd6b1dfaa1d35e0ce35631b06a18d2574d14874678062d4c077358c8203e
3
+ size 2046859
predictions_r1/coco/m4_align2_21__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08eae2fa18ceb4cadcd17dbf055e515a42f073c7adc65df3d85d5559b38528ec
3
+ size 2046017
predictions_r1/coco/m4_align2s1_21__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b71b20e6d4bb8cd451a68cdada94cea24566e3da9e36f8b1d78254bef16a323d
3
+ size 2037109
predictions_r1/coco/m4_bigG21__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe8f14fc34ef311f661cb22047c7356cfbd610f429877955632fd5e6598d513
3
+ size 2045920
predictions_r1/coco/m4_blip21__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaa73b89624c506ef7e815372d8f12274311cbc97e6ebfe58cf0b22825153df8
3
+ size 2047680
predictions_r1/coco/m4_five20__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba32d591f70b4f6f8c14746ba85f1e11289a82db3b7879debd7eade7de8e5607
3
+ size 2043044
predictions_r1/coco/m4_five21__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d827f6d8559eb035dfbc4fd26b3367b37e725bb32dd2393637abd1b5995f4f6c
3
+ size 2039131
predictions_r1/coco/m4_four21_noMBR__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3281ab9b002604116c309d8de76da1c381c8be1e3e4477b0c9b1cbd9ff2a225d
3
+ size 2033118
predictions_r1/coco/m4_s1_21__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3c9ebb98960693cd343d2782e8f1df49b655d6afe1863a4798bcf13b87bd98d
3
+ size 2012978
predictions_r1/coco/oracle20_approx__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb8281efb0957f376cafd183543bf3d0428bc63f8cb586062513390036dcc95
3
+ size 2043699
predictions_r1/coco/rel6_mallows__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b81e53c5cbe64f8040c8e042ae65455da5d1cd0649b4c96f6ef60d03d6c6ed4
3
+ size 2046155
predictions_r1/coco/rel6_spectral__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b81192039895d1b9826433bd1a7280f79da9aa2a8bcf709f31930f9526d0f7
3
+ size 2045714
predictions_r1/coco/sj_qwen2vl2b_alone__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f8b83be8ce354e583d00e86850290759c82dd00e1358bf1e781aaeb9a7e0a70
3
+ size 410246
predictions_r1/coco/sj_qwen2vl2b_stack6swap__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bbc7dcccca0a44e81dd54f1f07982b82fd24e13a39d11d6f44c1fe79c4ac52a
3
+ size 410755
predictions_r1/coco/sj_qwen2vl2b_zsum3plus__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d84a667b5e5883488482dcc9a77ada637741b25a758493a1aba0626d12165c
3
+ size 411194
predictions_r1/coco/sj_smolvlm256m_alone__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4000425cd32fda527794b5c8783ba955c35bad18973b91baf7f9d6ac1864c0a
3
+ size 409496
predictions_r1/coco/sj_smolvlm256m_stack6swap__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aadf03801fc0ef0260df091a8634b8a06803f3b57df95ba95bc4218308ff51f
3
+ size 410598
predictions_r1/coco/sj_smolvlm256m_zsum3plus__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3afa956dc00cebe16dea7796efedd1d75f90dc911ea9700a94341b4b9837a66
3
+ size 411147
predictions_r1/coco/sj_smolvlm500m_alone__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2779a8711dc959a0d9ad366d1e6d2ca90548fc4e879c5d6ac70e08ca8cb08c86
3
+ size 408880
predictions_r1/coco/sj_smolvlm500m_stack6swap__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec4561bb9b9b9e60e5e2df5e9e94fff03ec2b73724440fcb8daae48a4e57bcff
3
+ size 410714
predictions_r1/coco/sj_smolvlm500m_zsum3plus__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f862477a6eea9afcce21443843384931fd7a9f8ca2897f2f92dbd1d768fb293
3
+ size 410976
predictions_r1/coco/stack4_noLM_blip_bigG_vqa_mbr__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1bb561d71dbdb4ce8e0a9fbf7a9d9b1a1ac44994a169d016926f3e9fa7afc2b
3
+ size 2045477
predictions_r1/coco/stack4_zsum3_ground__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88cfaa44e5d1884bfa29c30fd34e39d7d424e485f5abe7bef6dd07f685afff04
3
+ size 2048529
predictions_r1/coco/stack4_zsum3_mbr__overall.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3615f83fa054fde5706537ecad977c34aa7c19dc99928483075acfe9038ee2bb
3
+ size 2049126