{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RJ4XG3LTU2OOSPJZFWANRJ5O6D","short_pith_number":"pith:RJ4XG3LT","canonical_record":{"source":{"id":"2402.17793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-26T18:37:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"09f8bb9bfac20610a09b86919fb556c6cafa47ce4fa80b6bb48e668e57336e2f","abstract_canon_sha256":"119b3c96dcf3726562bb7207adf6585434293b732a521f27bb9dfe6159004684"},"schema_version":"1.0"},"canonical_sha256":"8a79736d73a69ce93d392d80d8a7aef0cd333dcc00d8be64b351d6177ca74d65","source":{"kind":"arxiv","id":"2402.17793","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17793","created_at":"2026-07-05T07:50:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17793v1","created_at":"2026-07-05T07:50:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17793","created_at":"2026-07-05T07:50:08Z"},{"alias_kind":"pith_short_12","alias_value":"RJ4XG3LTU2OO","created_at":"2026-07-05T07:50:08Z"},{"alias_kind":"pith_short_16","alias_value":"RJ4XG3LTU2OOSPJZ","created_at":"2026-07-05T07:50:08Z"},{"alias_kind":"pith_short_8","alias_value":"RJ4XG3LT","created_at":"2026-07-05T07:50:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RJ4XG3LTU2OOSPJZFWANRJ5O6D","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-26T18:37:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"09f8bb9bfac20610a09b86919fb556c6cafa47ce4fa80b6bb48e668e57336e2f","abstract_canon_sha256":"119b3c96dcf3726562bb7207adf6585434293b732a521f27bb9dfe6159004684"},"schema_version":"1.0"},"canonical_sha256":"8a79736d73a69ce93d392d80d8a7aef0cd333dcc00d8be64b351d6177ca74d65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:08.398608Z","signature_b64":"okJGygz3jiwOPsZ8cJTCt8VYD6S5mgFqydpR/XgQ6pVQA+no0g4dXk6Fo5P41AGYxGeqLPIVM21Y8/vze1y5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a79736d73a69ce93d392d80d8a7aef0cd333dcc00d8be64b351d6177ca74d65","last_reissued_at":"2026-07-05T07:50:08.398160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:08.398160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17793","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:50:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aT1qMP2QOeMVu4+N9zhhPVQIwjbc8gzCVwtCdcveIwnMky/63OlyZCC3zZGd8Hp8tj2GrjgyWZ/Q0wsnWenlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T13:44:14.650399Z"},"content_sha256":"b2e3113edb4c872293208b2f363cb6a83808a65d0c7dec7ceb789b76aff3c52a","schema_version":"1.0","event_id":"sha256:b2e3113edb4c872293208b2f363cb6a83808a65d0c7dec7ceb789b76aff3c52a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RJ4XG3LTU2OOSPJZFWANRJ5O6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Surprising Failure? Multimodal LLMs and the NLVR Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Anne Wu, Kiant\\'e Brantley, Yoav Artzi","submitted_at":"2024-02-26T18:37:18Z","abstract_excerpt":"This study evaluates three state-of-the-art MLLMs -- GPT-4V, Gemini Pro, and the open-source model IDEFICS -- on the compositional natural language vision reasoning task NLVR. Given a human-written sentence paired with a synthetic image, this task requires the model to determine the truth value of the sentence with respect to the image. Despite the strong performance demonstrated by these models, we observe they perform poorly on NLVR, which was constructed to require compositional and spatial reasoning, and to be robust for semantic and systematic biases."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17793","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.17793/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:50:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8o4gN7Bez1+bpnZJo0Tp9IW1V8RiNZxev3Fnz6OE/DrlbIwBi4t33aHgG8CNpH8aW6+e7rzHPUjVi1sYSk+eCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T13:44:14.651269Z"},"content_sha256":"034dbe2b153c0eaa45a2f1b2fbdf126f33b3dfaea61cd89bec6139534aeedcd8","schema_version":"1.0","event_id":"sha256:034dbe2b153c0eaa45a2f1b2fbdf126f33b3dfaea61cd89bec6139534aeedcd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJ4XG3LTU2OOSPJZFWANRJ5O6D/bundle.json","state_url":"https://pith.science/pith/RJ4XG3LTU2OOSPJZFWANRJ5O6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJ4XG3LTU2OOSPJZFWANRJ5O6D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T13:44:14Z","links":{"resolver":"https://pith.science/pith/RJ4XG3LTU2OOSPJZFWANRJ5O6D","bundle":"https://pith.science/pith/RJ4XG3LTU2OOSPJZFWANRJ5O6D/bundle.json","state":"https://pith.science/pith/RJ4XG3LTU2OOSPJZFWANRJ5O6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJ4XG3LTU2OOSPJZFWANRJ5O6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RJ4XG3LTU2OOSPJZFWANRJ5O6D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"119b3c96dcf3726562bb7207adf6585434293b732a521f27bb9dfe6159004684","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-26T18:37:18Z","title_canon_sha256":"09f8bb9bfac20610a09b86919fb556c6cafa47ce4fa80b6bb48e668e57336e2f"},"schema_version":"1.0","source":{"id":"2402.17793","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17793","created_at":"2026-07-05T07:50:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17793v1","created_at":"2026-07-05T07:50:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17793","created_at":"2026-07-05T07:50:08Z"},{"alias_kind":"pith_short_12","alias_value":"RJ4XG3LTU2OO","created_at":"2026-07-05T07:50:08Z"},{"alias_kind":"pith_short_16","alias_value":"RJ4XG3LTU2OOSPJZ","created_at":"2026-07-05T07:50:08Z"},{"alias_kind":"pith_short_8","alias_value":"RJ4XG3LT","created_at":"2026-07-05T07:50:08Z"}],"graph_snapshots":[{"event_id":"sha256:034dbe2b153c0eaa45a2f1b2fbdf126f33b3dfaea61cd89bec6139534aeedcd8","target":"graph","created_at":"2026-07-05T07:50:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.17793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study evaluates three state-of-the-art MLLMs -- GPT-4V, Gemini Pro, and the open-source model IDEFICS -- on the compositional natural language vision reasoning task NLVR. Given a human-written sentence paired with a synthetic image, this task requires the model to determine the truth value of the sentence with respect to the image. Despite the strong performance demonstrated by these models, we observe they perform poorly on NLVR, which was constructed to require compositional and spatial reasoning, and to be robust for semantic and systematic biases.","authors_text":"Anne Wu, Kiant\\'e Brantley, Yoav Artzi","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-26T18:37:18Z","title":"A Surprising Failure? Multimodal LLMs and the NLVR Challenge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17793","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b2e3113edb4c872293208b2f363cb6a83808a65d0c7dec7ceb789b76aff3c52a","target":"record","created_at":"2026-07-05T07:50:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"119b3c96dcf3726562bb7207adf6585434293b732a521f27bb9dfe6159004684","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-26T18:37:18Z","title_canon_sha256":"09f8bb9bfac20610a09b86919fb556c6cafa47ce4fa80b6bb48e668e57336e2f"},"schema_version":"1.0","source":{"id":"2402.17793","kind":"arxiv","version":1}},"canonical_sha256":"8a79736d73a69ce93d392d80d8a7aef0cd333dcc00d8be64b351d6177ca74d65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a79736d73a69ce93d392d80d8a7aef0cd333dcc00d8be64b351d6177ca74d65","first_computed_at":"2026-07-05T07:50:08.398160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:08.398160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"okJGygz3jiwOPsZ8cJTCt8VYD6S5mgFqydpR/XgQ6pVQA+no0g4dXk6Fo5P41AGYxGeqLPIVM21Y8/vze1y5Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:08.398608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17793","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2e3113edb4c872293208b2f363cb6a83808a65d0c7dec7ceb789b76aff3c52a","sha256:034dbe2b153c0eaa45a2f1b2fbdf126f33b3dfaea61cd89bec6139534aeedcd8"],"state_sha256":"87741c13087ae1375d974eab5247505795c6f8dfe590f01228349b8795d48933"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VmsJNx31Ku0sFcO7g/XCQn0SEeIIKcWYGcp58Y1g2ocTlss4yaIJH+5G8Fl/Mgf40J+2RwYUg/5b7MkUwHulBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T13:44:14.657202Z","bundle_sha256":"50a569c55922cfb52f1fbd09872ee41b4fc077a831f7dd2f99d09c78b21fb582"}}