{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WYGXCI6MZ5QTJMQF3J7S4DVMS4","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":"7a981f4b2170f66bd4f415855b46323bb87117d0549db897727e781f77f5b146","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-06-04T06:20:23Z","title_canon_sha256":"d89d7473ed9f2ce0a555ac676d8588db7367fc967c40f90d633e1a0a350799ab"},"schema_version":"1.0","source":{"id":"2606.05748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05748","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05748v1","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05748","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"WYGXCI6MZ5QT","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"WYGXCI6MZ5QTJMQF","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"WYGXCI6M","created_at":"2026-06-05T01:15:01Z"}],"graph_snapshots":[{"event_id":"sha256:3785568e39cce1273e44dab187093f014d9c09c2efc17321e136ed469f2be6d4","target":"graph","created_at":"2026-06-05T01:15:01Z","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/2606.05748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","authors_text":"Dixin Zheng, Hanzhong Liang, Kaili Zhao, Kejuan Yang, Kenan Xiao, Mingyuan Du, Yang Xiao, Yizhuo Zhang, Yue Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-06-04T06:20:23Z","title":"UNIVID: Unified Vision-Language Model for Video Moderation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05748","kind":"arxiv","version":1},"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":"sha256:200f4cfd3985aa6102704cd38a7c5ccaf66859bc82ae6a1a9310754027205d18","target":"record","created_at":"2026-06-05T01:15:01Z","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":"7a981f4b2170f66bd4f415855b46323bb87117d0549db897727e781f77f5b146","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-06-04T06:20:23Z","title_canon_sha256":"d89d7473ed9f2ce0a555ac676d8588db7367fc967c40f90d633e1a0a350799ab"},"schema_version":"1.0","source":{"id":"2606.05748","kind":"arxiv","version":1}},"canonical_sha256":"b60d7123cccf6134b205da7f2e0eac973d3da15eb6a8d6e2266a6ef138eccb4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b60d7123cccf6134b205da7f2e0eac973d3da15eb6a8d6e2266a6ef138eccb4c","first_computed_at":"2026-06-05T01:15:01.589206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:01.589206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"969sYo8BxiR1qqlj/x66FUD3h9dbRZWBpWHNHgmSt2/OStTZlXXOVgJVn4IPeA/MFCgtiwLOvg0SgJMRU/RTBw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:01.589832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:200f4cfd3985aa6102704cd38a7c5ccaf66859bc82ae6a1a9310754027205d18","sha256:3785568e39cce1273e44dab187093f014d9c09c2efc17321e136ed469f2be6d4"],"state_sha256":"6b270684394c94a45e3c972b8cd4d3ed7a1d61f8b4fac8c854f2d1b697a6c498"}