{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3ZYRJRMIMHWWAX2HXWH6UOKGX6","short_pith_number":"pith:3ZYRJRMI","canonical_record":{"source":{"id":"2410.22315","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:54:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"388699f60e380eceb44a7b8bfe2551bdc189bb160a2516df43cb452ffec41203","abstract_canon_sha256":"5297ff6c9501a45c7537055b3764c26236b3a50af935b88fc984f056df914122"},"schema_version":"1.0"},"canonical_sha256":"de7114c58861ed605f47bd8fea3946bf91de795bec04bdf4b1fe1fe935891aee","source":{"kind":"arxiv","id":"2410.22315","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22315","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22315v1","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22315","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_12","alias_value":"3ZYRJRMIMHWW","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_16","alias_value":"3ZYRJRMIMHWWAX2H","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_8","alias_value":"3ZYRJRMI","created_at":"2026-07-05T09:28:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3ZYRJRMIMHWWAX2HXWH6UOKGX6","target":"record","payload":{"canonical_record":{"source":{"id":"2410.22315","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:54:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"388699f60e380eceb44a7b8bfe2551bdc189bb160a2516df43cb452ffec41203","abstract_canon_sha256":"5297ff6c9501a45c7537055b3764c26236b3a50af935b88fc984f056df914122"},"schema_version":"1.0"},"canonical_sha256":"de7114c58861ed605f47bd8fea3946bf91de795bec04bdf4b1fe1fe935891aee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:07.273252Z","signature_b64":"yecgBg865hDId78fieFxo1Z4Nvo/G0fyQDYju2+pqX5H/Nzs4pr4tXdxLYnVkmKVe8B7xykNccH4JkCZs7qXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de7114c58861ed605f47bd8fea3946bf91de795bec04bdf4b1fe1fe935891aee","last_reissued_at":"2026-07-05T09:28:07.272762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:07.272762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.22315","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":"2026-07-05T09:28:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vRKl7JxefdusNQ+nZm3Pyf2C1SFy7dWXOQeU+QyEo6IFkOquqAQBUy2K/eosBBBV1N2AYIKMaV46hFQfO/K3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:52:43.632663Z"},"content_sha256":"2cfd62034c3a22fdec4c295985218c8a00b99beeaed83a1b5f8ef67aa4f70296","schema_version":"1.0","event_id":"sha256:2cfd62034c3a22fdec4c295985218c8a00b99beeaed83a1b5f8ef67aa4f70296"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3ZYRJRMIMHWWAX2HXWH6UOKGX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Language Inference Improves Compositionality in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Hal Daum\\'e III, Paola Cascante-Bonilla, Rachel Rudinger, Yang Trista Cao, Yu Hou","submitted_at":"2024-10-29T17:54:17Z","abstract_excerpt":"Compositional reasoning in Vision-Language Models (VLMs) remains challenging as these models often struggle to relate objects, attributes, and spatial relationships. Recent methods aim to address these limitations by relying on the semantics of the textual description, using Large Language Models (LLMs) to break them down into subsets of questions and answers. However, these methods primarily operate on the surface level, failing to incorporate deeper lexical understanding while introducing incorrect assumptions generated by the LLM. In response to these issues, we present Caption Expansion wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22315","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/2410.22315/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":"2026-07-05T09:28:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9w7TPJ5dvcmwHo+uMx31dpNkLQVzxDdDn2fi0zZ72PZU92DbOTo1W5o6Op0oLi4GenGerWQjAe5OY5cL1SMNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:52:43.633030Z"},"content_sha256":"09c596e0b3a087f86f89c6f73978492235fb6fb4bcd6158900f0a7f9674cd2aa","schema_version":"1.0","event_id":"sha256:09c596e0b3a087f86f89c6f73978492235fb6fb4bcd6158900f0a7f9674cd2aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ZYRJRMIMHWWAX2HXWH6UOKGX6/bundle.json","state_url":"https://pith.science/pith/3ZYRJRMIMHWWAX2HXWH6UOKGX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ZYRJRMIMHWWAX2HXWH6UOKGX6/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":"2026-07-07T06:52:43Z","links":{"resolver":"https://pith.science/pith/3ZYRJRMIMHWWAX2HXWH6UOKGX6","bundle":"https://pith.science/pith/3ZYRJRMIMHWWAX2HXWH6UOKGX6/bundle.json","state":"https://pith.science/pith/3ZYRJRMIMHWWAX2HXWH6UOKGX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ZYRJRMIMHWWAX2HXWH6UOKGX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3ZYRJRMIMHWWAX2HXWH6UOKGX6","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":"5297ff6c9501a45c7537055b3764c26236b3a50af935b88fc984f056df914122","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:54:17Z","title_canon_sha256":"388699f60e380eceb44a7b8bfe2551bdc189bb160a2516df43cb452ffec41203"},"schema_version":"1.0","source":{"id":"2410.22315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22315","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22315v1","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22315","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_12","alias_value":"3ZYRJRMIMHWW","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_16","alias_value":"3ZYRJRMIMHWWAX2H","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_8","alias_value":"3ZYRJRMI","created_at":"2026-07-05T09:28:07Z"}],"graph_snapshots":[{"event_id":"sha256:09c596e0b3a087f86f89c6f73978492235fb6fb4bcd6158900f0a7f9674cd2aa","target":"graph","created_at":"2026-07-05T09:28:07Z","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/2410.22315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compositional reasoning in Vision-Language Models (VLMs) remains challenging as these models often struggle to relate objects, attributes, and spatial relationships. Recent methods aim to address these limitations by relying on the semantics of the textual description, using Large Language Models (LLMs) to break them down into subsets of questions and answers. However, these methods primarily operate on the surface level, failing to incorporate deeper lexical understanding while introducing incorrect assumptions generated by the LLM. In response to these issues, we present Caption Expansion wi","authors_text":"Hal Daum\\'e III, Paola Cascante-Bonilla, Rachel Rudinger, Yang Trista Cao, Yu Hou","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:54:17Z","title":"Natural Language Inference Improves Compositionality in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22315","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":"sha256:2cfd62034c3a22fdec4c295985218c8a00b99beeaed83a1b5f8ef67aa4f70296","target":"record","created_at":"2026-07-05T09:28:07Z","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":"5297ff6c9501a45c7537055b3764c26236b3a50af935b88fc984f056df914122","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:54:17Z","title_canon_sha256":"388699f60e380eceb44a7b8bfe2551bdc189bb160a2516df43cb452ffec41203"},"schema_version":"1.0","source":{"id":"2410.22315","kind":"arxiv","version":1}},"canonical_sha256":"de7114c58861ed605f47bd8fea3946bf91de795bec04bdf4b1fe1fe935891aee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de7114c58861ed605f47bd8fea3946bf91de795bec04bdf4b1fe1fe935891aee","first_computed_at":"2026-07-05T09:28:07.272762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:07.272762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yecgBg865hDId78fieFxo1Z4Nvo/G0fyQDYju2+pqX5H/Nzs4pr4tXdxLYnVkmKVe8B7xykNccH4JkCZs7qXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:07.273252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cfd62034c3a22fdec4c295985218c8a00b99beeaed83a1b5f8ef67aa4f70296","sha256:09c596e0b3a087f86f89c6f73978492235fb6fb4bcd6158900f0a7f9674cd2aa"],"state_sha256":"234398b8f15b12814bec2d9bde3bad1b79003110712fd7c3d14af14b1cb899c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I4i6GjJv4ehPeseRRLS1cqU0Id1o23U1lMLbC5IqQ1XbklwqnkCD2o6KM9ulARy/lMgPvYxeZRbqiRYH/BQvCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:52:43.635112Z","bundle_sha256":"483c7a487aaf870389ff72fc39a711dbfba59e66bf654a33f4e2d23f2126c39d"}}