{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BN3II3BO7A4LWTYI6LECRIICEZ","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":"b9212b3b5109f8f4a947aae8dc04c75b00a4b7528e5659b6f6a59665f02eaaf2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T17:57:43Z","title_canon_sha256":"859deb6746a4728204b355c9c991309f05600ddf69bdb046d4c1c0faaac815c3"},"schema_version":"1.0","source":{"id":"2303.17590","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.17590","created_at":"2026-07-05T06:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"2303.17590v2","created_at":"2026-07-05T06:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17590","created_at":"2026-07-05T06:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"BN3II3BO7A4L","created_at":"2026-07-05T06:46:02Z"},{"alias_kind":"pith_short_16","alias_value":"BN3II3BO7A4LWTYI","created_at":"2026-07-05T06:46:02Z"},{"alias_kind":"pith_short_8","alias_value":"BN3II3BO","created_at":"2026-07-05T06:46:02Z"}],"graph_snapshots":[{"event_id":"sha256:b551082a66d1d0fd9d672e473ba019052dad5d3432f4bfdd7ba1312108fd2263","target":"graph","created_at":"2026-07-05T06:46:02Z","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/2303.17590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pre-trained Vision & Language (VL) models have shown remarkable performance in many applications, enabling replacing a fixed set of supported classes with zero-shot open vocabulary reasoning over (almost arbitrary) natural language prompts. However, recent works have uncovered a fundamental weakness of these models. For example, their difficulty to understand Visual Language Concepts (VLC) that go 'beyond nouns' such as the meaning of non-object words (e.g., attributes, actions, relations, states, etc.), or difficulty in performing compositional reasoning such as understanding the ","authors_text":"Aude Oliva, Donghyun Kim, G\\\"ul Varol, James Seale Smith, Khaled Shehada, Leonid Karlinsky, Paola Cascante-Bonilla, Rameswar Panda, Rogerio Feris, Sivan Doveh, Vicente Ordonez","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T17:57:43Z","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17590","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:c4403afa1fd89830f39f868d3ff21dca67120b6ab552e1d2f204b98d0098b483","target":"record","created_at":"2026-07-05T06:46:02Z","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":"b9212b3b5109f8f4a947aae8dc04c75b00a4b7528e5659b6f6a59665f02eaaf2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T17:57:43Z","title_canon_sha256":"859deb6746a4728204b355c9c991309f05600ddf69bdb046d4c1c0faaac815c3"},"schema_version":"1.0","source":{"id":"2303.17590","kind":"arxiv","version":2}},"canonical_sha256":"0b76846c2ef838bb4f08f2c828a1022675d0b0047a31962a5d098047b184b438","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b76846c2ef838bb4f08f2c828a1022675d0b0047a31962a5d098047b184b438","first_computed_at":"2026-07-05T06:46:02.080739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:02.080739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cIdbHUyfdMrSYkEHpZWJH8Etel8yCsQkq+JyrAdeGXGvRx13XdK5vMgb+TCXqIr2HXTkfkyWTqoZM7DFttUvBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:02.081209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.17590","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4403afa1fd89830f39f868d3ff21dca67120b6ab552e1d2f204b98d0098b483","sha256:b551082a66d1d0fd9d672e473ba019052dad5d3432f4bfdd7ba1312108fd2263"],"state_sha256":"e31e2bb114a77df818af3c101ea854ef4188951da413355891b975faaf11ee8b"}