{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WYGXCI6MZ5QTJMQF3J7S4DVMS4","short_pith_number":"pith:WYGXCI6M","schema_version":"1.0","canonical_sha256":"b60d7123cccf6134b205da7f2e0eac973d3da15eb6a8d6e2266a6ef138eccb4c","source":{"kind":"arxiv","id":"2606.05748","version":1},"attestation_state":"computed","paper":{"title":"UNIVID: Unified Vision-Language Model for Video Moderation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.MM","authors_text":"Dixin Zheng, Hanzhong Liang, Kaili Zhao, Kejuan Yang, Kenan Xiao, Mingyuan Du, Yang Xiao, Yizhuo Zhang, Yue Zhang","submitted_at":"2026-06-04T06:20:23Z","abstract_excerpt":"Global-scale video moderation faces a dual challenge: the need for fine-grained multi-modal reasoning and the demand for interpretable outputs to support downstream enforcement. Traditional moderation systems often rely on fragmented black-box classifiers that are difficult to maintain and lack transparency. In this paper, we present UNIVID, a UNIfied VIsion-language model for video moDeration. Unlike standard classification models, UNIVID generates policy-aware captions that serve as an interpretable intermediate representation, enabling human-verifiable decisions and multi-task reusability. "},"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":"2606.05748","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-06-04T06:20:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d89d7473ed9f2ce0a555ac676d8588db7367fc967c40f90d633e1a0a350799ab","abstract_canon_sha256":"7a981f4b2170f66bd4f415855b46323bb87117d0549db897727e781f77f5b146"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:01.589832Z","signature_b64":"969sYo8BxiR1qqlj/x66FUD3h9dbRZWBpWHNHgmSt2/OStTZlXXOVgJVn4IPeA/MFCgtiwLOvg0SgJMRU/RTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b60d7123cccf6134b205da7f2e0eac973d3da15eb6a8d6e2266a6ef138eccb4c","last_reissued_at":"2026-06-05T01:15:01.589206Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:01.589206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UNIVID: Unified Vision-Language Model for Video Moderation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.MM","authors_text":"Dixin Zheng, Hanzhong Liang, Kaili Zhao, Kejuan Yang, Kenan Xiao, Mingyuan Du, Yang Xiao, Yizhuo Zhang, Yue Zhang","submitted_at":"2026-06-04T06:20:23Z","abstract_excerpt":"Global-scale video moderation faces a dual challenge: the need for fine-grained multi-modal reasoning and the demand for interpretable outputs to support downstream enforcement. Traditional moderation systems often rely on fragmented black-box classifiers that are difficult to maintain and lack transparency. In this paper, we present UNIVID, a UNIfied VIsion-language model for video moDeration. Unlike standard classification models, UNIVID generates policy-aware captions that serve as an interpretable intermediate representation, enabling human-verifiable decisions and multi-task reusability. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05748","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/2606.05748/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":"2606.05748","created_at":"2026-06-05T01:15:01.589303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05748v1","created_at":"2026-06-05T01:15:01.589303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05748","created_at":"2026-06-05T01:15:01.589303+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYGXCI6MZ5QT","created_at":"2026-06-05T01:15:01.589303+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYGXCI6MZ5QTJMQF","created_at":"2026-06-05T01:15:01.589303+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYGXCI6M","created_at":"2026-06-05T01:15:01.589303+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYGXCI6MZ5QTJMQF3J7S4DVMS4","json":"https://pith.science/pith/WYGXCI6MZ5QTJMQF3J7S4DVMS4.json","graph_json":"https://pith.science/api/pith-number/WYGXCI6MZ5QTJMQF3J7S4DVMS4/graph.json","events_json":"https://pith.science/api/pith-number/WYGXCI6MZ5QTJMQF3J7S4DVMS4/events.json","paper":"https://pith.science/paper/WYGXCI6M"},"agent_actions":{"view_html":"https://pith.science/pith/WYGXCI6MZ5QTJMQF3J7S4DVMS4","download_json":"https://pith.science/pith/WYGXCI6MZ5QTJMQF3J7S4DVMS4.json","view_paper":"https://pith.science/paper/WYGXCI6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05748&json=true","fetch_graph":"https://pith.science/api/pith-number/WYGXCI6MZ5QTJMQF3J7S4DVMS4/graph.json","fetch_events":"https://pith.science/api/pith-number/WYGXCI6MZ5QTJMQF3J7S4DVMS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYGXCI6MZ5QTJMQF3J7S4DVMS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYGXCI6MZ5QTJMQF3J7S4DVMS4/action/storage_attestation","attest_author":"https://pith.science/pith/WYGXCI6MZ5QTJMQF3J7S4DVMS4/action/author_attestation","sign_citation":"https://pith.science/pith/WYGXCI6MZ5QTJMQF3J7S4DVMS4/action/citation_signature","submit_replication":"https://pith.science/pith/WYGXCI6MZ5QTJMQF3J7S4DVMS4/action/replication_record"}},"created_at":"2026-06-05T01:15:01.589303+00:00","updated_at":"2026-06-05T01:15:01.589303+00:00"}