{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GAIYDM3UYTB2Y7QESR3I4FCBAK","short_pith_number":"pith:GAIYDM3U","schema_version":"1.0","canonical_sha256":"301181b374c4c3ac7e0494768e144102991e2e68770a2237cb32db27a3e17ca9","source":{"kind":"arxiv","id":"2305.10683","version":4},"attestation_state":"computed","paper":{"title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ansel Blume, Genglin Liu, Heng Ji, Jaemin Cho, Mohit Bansal, Sha Li, Zhenhailong Wang, Zineng Tang","submitted_at":"2023-05-18T03:53:59Z","abstract_excerpt":"Action knowledge involves the understanding of textual, visual, and temporal aspects of actions. We introduce the Action Dynamics Benchmark (ActionBench) containing two carefully designed probing tasks: Action Antonym and Video Reversal, which targets multimodal alignment capabilities and temporal understanding skills of the model, respectively. Despite recent video-language models' (VidLM) impressive performance on various benchmark tasks, our diagnostic tasks reveal their surprising deficiency (near-random performance) in action knowledge, suggesting that current models rely on object recogn"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.10683","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T03:53:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"024cfe6ce3206ef0469c2746203d1f7e5af583d16e986252668cbb9d6d5ca915","abstract_canon_sha256":"9d2b00c29fe7beadd4d7f0aaf5e8903984ba4bbe8e20513cab83a76766ceb90d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:24.746077Z","signature_b64":"Gloh9x7p2j1DXQwlfVLAbQluzgV4O41DzTi2KB6xQyCcyc24WTeMs8knSO9/qGH0sMUFwwZbcAOuWHhOhS9RBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"301181b374c4c3ac7e0494768e144102991e2e68770a2237cb32db27a3e17ca9","last_reissued_at":"2026-07-05T07:03:24.745598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:24.745598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ansel Blume, Genglin Liu, Heng Ji, Jaemin Cho, Mohit Bansal, Sha Li, Zhenhailong Wang, Zineng Tang","submitted_at":"2023-05-18T03:53:59Z","abstract_excerpt":"Action knowledge involves the understanding of textual, visual, and temporal aspects of actions. We introduce the Action Dynamics Benchmark (ActionBench) containing two carefully designed probing tasks: Action Antonym and Video Reversal, which targets multimodal alignment capabilities and temporal understanding skills of the model, respectively. Despite recent video-language models' (VidLM) impressive performance on various benchmark tasks, our diagnostic tasks reveal their surprising deficiency (near-random performance) in action knowledge, suggesting that current models rely on object recogn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10683","kind":"arxiv","version":4},"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/2305.10683/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.10683","created_at":"2026-07-05T07:03:24.745654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10683v4","created_at":"2026-07-05T07:03:24.745654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10683","created_at":"2026-07-05T07:03:24.745654+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAIYDM3UYTB2","created_at":"2026-07-05T07:03:24.745654+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAIYDM3UYTB2Y7QE","created_at":"2026-07-05T07:03:24.745654+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAIYDM3U","created_at":"2026-07-05T07:03:24.745654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17283","citing_title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAIYDM3UYTB2Y7QESR3I4FCBAK","json":"https://pith.science/pith/GAIYDM3UYTB2Y7QESR3I4FCBAK.json","graph_json":"https://pith.science/api/pith-number/GAIYDM3UYTB2Y7QESR3I4FCBAK/graph.json","events_json":"https://pith.science/api/pith-number/GAIYDM3UYTB2Y7QESR3I4FCBAK/events.json","paper":"https://pith.science/paper/GAIYDM3U"},"agent_actions":{"view_html":"https://pith.science/pith/GAIYDM3UYTB2Y7QESR3I4FCBAK","download_json":"https://pith.science/pith/GAIYDM3UYTB2Y7QESR3I4FCBAK.json","view_paper":"https://pith.science/paper/GAIYDM3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10683&json=true","fetch_graph":"https://pith.science/api/pith-number/GAIYDM3UYTB2Y7QESR3I4FCBAK/graph.json","fetch_events":"https://pith.science/api/pith-number/GAIYDM3UYTB2Y7QESR3I4FCBAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAIYDM3UYTB2Y7QESR3I4FCBAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAIYDM3UYTB2Y7QESR3I4FCBAK/action/storage_attestation","attest_author":"https://pith.science/pith/GAIYDM3UYTB2Y7QESR3I4FCBAK/action/author_attestation","sign_citation":"https://pith.science/pith/GAIYDM3UYTB2Y7QESR3I4FCBAK/action/citation_signature","submit_replication":"https://pith.science/pith/GAIYDM3UYTB2Y7QESR3I4FCBAK/action/replication_record"}},"created_at":"2026-07-05T07:03:24.745654+00:00","updated_at":"2026-07-05T07:03:24.745654+00:00"}