{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2O5SVDKCHVFBYZKXXNASMITIKH","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":"ef8487fa45003bee5c6581364ce9d309977ade1dfddca653917a965194d0d247","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T12:39:04Z","title_canon_sha256":"4cde19dbf71dc9f4993bc63619cf6ec231bbaea85a87f70df3f80123de73362a"},"schema_version":"1.0","source":{"id":"2605.29858","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29858","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29858v1","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29858","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"2O5SVDKCHVFB","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"2O5SVDKCHVFBYZKX","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"2O5SVDKC","created_at":"2026-05-29T02:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:4078e9d4ba4912ceeb641e520a39abb98d552d28d9b4564d41471e73a9f6ebd3","target":"graph","created_at":"2026-05-29T02:05:56Z","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/2605.29858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Temporal action localization (TAL) requires recognizing the target event and localizing its start and end times precisely in untrimmed videos. Recent vision-language formulations improve semantic reasoning and support language-conditioned outputs, but their autoregressive decoders still generate tokens from left to right, preventing later semantic evidence from revising earlier timestamp predictions.\n  We adapt masked diffusion vision-language models (MDVLMs) to TAL so that semantic tokens and boundary tokens remain editable throughout iterative denoising with bidirectional attention, allowing","authors_text":"Fengshun Wang, Zhengbo Zhang, Zhigang Tu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T12:39:04Z","title":"Masked Diffusion Vision-Language Models for Temporal Action Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29858","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":"sha256:6e260fa1106ffd57aa8ec3cf0b1e7a1df170ae8be8f69646347f60d881a6d83e","target":"record","created_at":"2026-05-29T02:05:56Z","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":"ef8487fa45003bee5c6581364ce9d309977ade1dfddca653917a965194d0d247","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T12:39:04Z","title_canon_sha256":"4cde19dbf71dc9f4993bc63619cf6ec231bbaea85a87f70df3f80123de73362a"},"schema_version":"1.0","source":{"id":"2605.29858","kind":"arxiv","version":1}},"canonical_sha256":"d3bb2a8d423d4a1c6557bb4126226851fce5592158e9909b8ca321b131f2fc75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3bb2a8d423d4a1c6557bb4126226851fce5592158e9909b8ca321b131f2fc75","first_computed_at":"2026-05-29T02:05:56.359612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:56.359612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oP5QuAN5dBU2gkI7m9wYZY1+1viNp+ZrN3MRoceNaiXmOpp5cLqCotFxFo71+7R6aQ1PyM7HWaHCStO8z4w+Cg==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:56.360516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29858","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e260fa1106ffd57aa8ec3cf0b1e7a1df170ae8be8f69646347f60d881a6d83e","sha256:4078e9d4ba4912ceeb641e520a39abb98d552d28d9b4564d41471e73a9f6ebd3"],"state_sha256":"a1c3b2ed24fcb18821131f407fce50e935d6468bb71c43ae8ddfa500fb6dc9b9"}