{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z7DEXKUITVTFXVTSV6MLZTI5UQ","short_pith_number":"pith:Z7DEXKUI","schema_version":"1.0","canonical_sha256":"cfc64baa889d665bd672af98bccd1da405a1fe6d6f770bc2deb79db7416897fe","source":{"kind":"arxiv","id":"2311.12919","version":2},"attestation_state":"computed","paper":{"title":"SPOT! Revisiting Video-Language Models for Event Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gengyuan Zhang, Jindong Gu, Jinhe Bi, Volker Tresp, Yanyu Chen","submitted_at":"2023-11-21T18:43:07Z","abstract_excerpt":"Understanding videos is an important research topic for multimodal learning. Leveraging large-scale datasets of web-crawled video-text pairs as weak supervision has become a pre-training paradigm for learning joint representations and showcased remarkable potential in video understanding tasks. However, videos can be multi-event and multi-grained, while these video-text pairs usually contain only broad-level video captions. This raises a question: with such weak supervision, can video representation in video-language models gain the ability to distinguish even factual discrepancies in textual "},"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":"2311.12919","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T18:43:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bfa081163df982766a38977d163749c09ddf95dc2c2cfe229bdfd8294cee8953","abstract_canon_sha256":"960ac8354e60e7973ac5afe2e62812038bb20cb10fc2ede2623e6844751b359e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:24.163548Z","signature_b64":"gRIoFm7HjwuZAYo+AQdybDKAlyW3pCNMzcXlWbga7clYpeFBpis+3GU9q0m47WKtUMjrYv95D7suFXf2Qb3yDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfc64baa889d665bd672af98bccd1da405a1fe6d6f770bc2deb79db7416897fe","last_reissued_at":"2026-07-05T07:19:24.162518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:24.162518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPOT! Revisiting Video-Language Models for Event Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gengyuan Zhang, Jindong Gu, Jinhe Bi, Volker Tresp, Yanyu Chen","submitted_at":"2023-11-21T18:43:07Z","abstract_excerpt":"Understanding videos is an important research topic for multimodal learning. Leveraging large-scale datasets of web-crawled video-text pairs as weak supervision has become a pre-training paradigm for learning joint representations and showcased remarkable potential in video understanding tasks. However, videos can be multi-event and multi-grained, while these video-text pairs usually contain only broad-level video captions. This raises a question: with such weak supervision, can video representation in video-language models gain the ability to distinguish even factual discrepancies in textual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12919","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/2311.12919/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":"2311.12919","created_at":"2026-07-05T07:19:24.162588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12919v2","created_at":"2026-07-05T07:19:24.162588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12919","created_at":"2026-07-05T07:19:24.162588+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7DEXKUITVTF","created_at":"2026-07-05T07:19:24.162588+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7DEXKUITVTFXVTS","created_at":"2026-07-05T07:19:24.162588+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7DEXKUI","created_at":"2026-07-05T07:19:24.162588+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11689","citing_title":"RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08144","citing_title":"IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7DEXKUITVTFXVTSV6MLZTI5UQ","json":"https://pith.science/pith/Z7DEXKUITVTFXVTSV6MLZTI5UQ.json","graph_json":"https://pith.science/api/pith-number/Z7DEXKUITVTFXVTSV6MLZTI5UQ/graph.json","events_json":"https://pith.science/api/pith-number/Z7DEXKUITVTFXVTSV6MLZTI5UQ/events.json","paper":"https://pith.science/paper/Z7DEXKUI"},"agent_actions":{"view_html":"https://pith.science/pith/Z7DEXKUITVTFXVTSV6MLZTI5UQ","download_json":"https://pith.science/pith/Z7DEXKUITVTFXVTSV6MLZTI5UQ.json","view_paper":"https://pith.science/paper/Z7DEXKUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12919&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7DEXKUITVTFXVTSV6MLZTI5UQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7DEXKUITVTFXVTSV6MLZTI5UQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7DEXKUITVTFXVTSV6MLZTI5UQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7DEXKUITVTFXVTSV6MLZTI5UQ/action/storage_attestation","attest_author":"https://pith.science/pith/Z7DEXKUITVTFXVTSV6MLZTI5UQ/action/author_attestation","sign_citation":"https://pith.science/pith/Z7DEXKUITVTFXVTSV6MLZTI5UQ/action/citation_signature","submit_replication":"https://pith.science/pith/Z7DEXKUITVTFXVTSV6MLZTI5UQ/action/replication_record"}},"created_at":"2026-07-05T07:19:24.162588+00:00","updated_at":"2026-07-05T07:19:24.162588+00:00"}