{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BJER74A3BUVQX2ZBYQ35RPWFS4","short_pith_number":"pith:BJER74A3","canonical_record":{"source":{"id":"2305.19595","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T06:36:41Z","cross_cats_sorted":[],"title_canon_sha256":"aef6c2a7c20e06093aaec239852b2ad82bb3b26c6060622717b7ac04b094dbe6","abstract_canon_sha256":"d9116fc8ac747c30f15f2ecff499df3da60884ec2a772a6e46ebfacf43fff0ef"},"schema_version":"1.0"},"canonical_sha256":"0a491ff01b0d2b0beb21c437d8bec59708b1c3ba01e0ad3f19b3349bb534f636","source":{"kind":"arxiv","id":"2305.19595","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19595","created_at":"2026-07-05T06:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19595v2","created_at":"2026-07-05T06:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19595","created_at":"2026-07-05T06:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"BJER74A3BUVQ","created_at":"2026-07-05T06:16:19Z"},{"alias_kind":"pith_short_16","alias_value":"BJER74A3BUVQX2ZB","created_at":"2026-07-05T06:16:19Z"},{"alias_kind":"pith_short_8","alias_value":"BJER74A3","created_at":"2026-07-05T06:16:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BJER74A3BUVQX2ZBYQ35RPWFS4","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19595","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T06:36:41Z","cross_cats_sorted":[],"title_canon_sha256":"aef6c2a7c20e06093aaec239852b2ad82bb3b26c6060622717b7ac04b094dbe6","abstract_canon_sha256":"d9116fc8ac747c30f15f2ecff499df3da60884ec2a772a6e46ebfacf43fff0ef"},"schema_version":"1.0"},"canonical_sha256":"0a491ff01b0d2b0beb21c437d8bec59708b1c3ba01e0ad3f19b3349bb534f636","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:19.899723Z","signature_b64":"OqxUEGK9FTAFDDVWEhgxIu4IuW8LgPLfRZeWg/u4xQDebZJJzdjVijspBa3Ln4gZIruEAysqR+Df+yIAN1bGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a491ff01b0d2b0beb21c437d8bec59708b1c3ba01e0ad3f19b3349bb534f636","last_reissued_at":"2026-07-05T06:16:19.899211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:19.899211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19595","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:16:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q1hRiXRsS8X1rNcDy+yO08PDUwRnih0MC6fUQgFDHUBhJpYlDcFyJs/PDUDNU90IymCaOE70iYa/n4pvb4isDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:32:00.361479Z"},"content_sha256":"9a11fab29be3059c3bab67501903c0beef88f9e9a72804d6da2d92a50c35b394","schema_version":"1.0","event_id":"sha256:9a11fab29be3059c3bab67501903c0beef88f9e9a72804d6da2d92a50c35b394"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BJER74A3BUVQX2ZBYQ35RPWFS4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit Alfassy, Assaf Arbelle, Donghyun Kim, Leonid Karlinsky, Paola Cascante-Bonilla, Raja Giryes, Rameswar Panda, Roei Herzig, Rogerio Feris, Shimon Ullman, Sivan Doveh, Sivan Harary","submitted_at":"2023-05-31T06:36:41Z","abstract_excerpt":"Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text, leading to numerous applications such as cross-modal retrieval, visual question answering, captioning, and more. However, the aligned image-text spaces learned by all the popular VL models are still suffering from the so-called `object bias' - their representations behave as `bags of nouns', mostly ignoring or downsizing the attributes, relations, and states of objects described/appearing in texts/images. Although some great attempts at fixing these `compositional reasoning' issues "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19595","kind":"arxiv","version":2},"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/2305.19595/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":"2026-07-05T06:16:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mq1JxpjwPVlkhLea0Xk1C/Q70a8d2G9IbystkqayRoZeqB7gBC6fO5iNM8QCdpupEsOLqRbQAWYoI6of/6H1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:32:00.362219Z"},"content_sha256":"59f8b855e89d4ec45e0dddad8226613cd04a1f692404253ac97713cb0ea37c5e","schema_version":"1.0","event_id":"sha256:59f8b855e89d4ec45e0dddad8226613cd04a1f692404253ac97713cb0ea37c5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BJER74A3BUVQX2ZBYQ35RPWFS4/bundle.json","state_url":"https://pith.science/pith/BJER74A3BUVQX2ZBYQ35RPWFS4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BJER74A3BUVQX2ZBYQ35RPWFS4/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":"2026-07-07T05:32:00Z","links":{"resolver":"https://pith.science/pith/BJER74A3BUVQX2ZBYQ35RPWFS4","bundle":"https://pith.science/pith/BJER74A3BUVQX2ZBYQ35RPWFS4/bundle.json","state":"https://pith.science/pith/BJER74A3BUVQX2ZBYQ35RPWFS4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BJER74A3BUVQX2ZBYQ35RPWFS4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BJER74A3BUVQX2ZBYQ35RPWFS4","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":"d9116fc8ac747c30f15f2ecff499df3da60884ec2a772a6e46ebfacf43fff0ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T06:36:41Z","title_canon_sha256":"aef6c2a7c20e06093aaec239852b2ad82bb3b26c6060622717b7ac04b094dbe6"},"schema_version":"1.0","source":{"id":"2305.19595","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19595","created_at":"2026-07-05T06:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19595v2","created_at":"2026-07-05T06:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19595","created_at":"2026-07-05T06:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"BJER74A3BUVQ","created_at":"2026-07-05T06:16:19Z"},{"alias_kind":"pith_short_16","alias_value":"BJER74A3BUVQX2ZB","created_at":"2026-07-05T06:16:19Z"},{"alias_kind":"pith_short_8","alias_value":"BJER74A3","created_at":"2026-07-05T06:16:19Z"}],"graph_snapshots":[{"event_id":"sha256:59f8b855e89d4ec45e0dddad8226613cd04a1f692404253ac97713cb0ea37c5e","target":"graph","created_at":"2026-07-05T06:16:19Z","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/2305.19595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text, leading to numerous applications such as cross-modal retrieval, visual question answering, captioning, and more. However, the aligned image-text spaces learned by all the popular VL models are still suffering from the so-called `object bias' - their representations behave as `bags of nouns', mostly ignoring or downsizing the attributes, relations, and states of objects described/appearing in texts/images. Although some great attempts at fixing these `compositional reasoning' issues ","authors_text":"Amit Alfassy, Assaf Arbelle, Donghyun Kim, Leonid Karlinsky, Paola Cascante-Bonilla, Raja Giryes, Rameswar Panda, Roei Herzig, Rogerio Feris, Shimon Ullman, Sivan Doveh, Sivan Harary","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T06:36:41Z","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19595","kind":"arxiv","version":2},"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":"sha256:9a11fab29be3059c3bab67501903c0beef88f9e9a72804d6da2d92a50c35b394","target":"record","created_at":"2026-07-05T06:16:19Z","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":"d9116fc8ac747c30f15f2ecff499df3da60884ec2a772a6e46ebfacf43fff0ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T06:36:41Z","title_canon_sha256":"aef6c2a7c20e06093aaec239852b2ad82bb3b26c6060622717b7ac04b094dbe6"},"schema_version":"1.0","source":{"id":"2305.19595","kind":"arxiv","version":2}},"canonical_sha256":"0a491ff01b0d2b0beb21c437d8bec59708b1c3ba01e0ad3f19b3349bb534f636","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a491ff01b0d2b0beb21c437d8bec59708b1c3ba01e0ad3f19b3349bb534f636","first_computed_at":"2026-07-05T06:16:19.899211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:19.899211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OqxUEGK9FTAFDDVWEhgxIu4IuW8LgPLfRZeWg/u4xQDebZJJzdjVijspBa3Ln4gZIruEAysqR+Df+yIAN1bGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:19.899723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19595","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a11fab29be3059c3bab67501903c0beef88f9e9a72804d6da2d92a50c35b394","sha256:59f8b855e89d4ec45e0dddad8226613cd04a1f692404253ac97713cb0ea37c5e"],"state_sha256":"0550446fa6f690f69e1e9732449753072ac7a7fe6dc25de292ecac4f81d8870c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FexEQBMGK1zJK3Xhr26bzzJI3IH7t2uy1ZBScxUk5H83mIIk57l/rsjPzmu1DimlUAjfnvJgQ+jMhb5z1CrmDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:32:00.365831Z","bundle_sha256":"0a3e6c4740fcdf618b9ab453cfdb292a2ed50a2f24e55f98f721daeb07844911"}}