{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DSQMVQ5XPPU3CKBTG5D3IEPKVB","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":"3ac02283aab6226576cecb2ae5eb9625161afe0f3909b1d50486f1731c7d090a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T23:01:26Z","title_canon_sha256":"8ce588f981eb06f356ab2a32e512eff7728366394dfaaeec39e7e0633e875eac"},"schema_version":"1.0","source":{"id":"2307.02682","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02682","created_at":"2026-07-05T06:30:08Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02682v2","created_at":"2026-07-05T06:30:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02682","created_at":"2026-07-05T06:30:08Z"},{"alias_kind":"pith_short_12","alias_value":"DSQMVQ5XPPU3","created_at":"2026-07-05T06:30:08Z"},{"alias_kind":"pith_short_16","alias_value":"DSQMVQ5XPPU3CKBT","created_at":"2026-07-05T06:30:08Z"},{"alias_kind":"pith_short_8","alias_value":"DSQMVQ5X","created_at":"2026-07-05T06:30:08Z"}],"graph_snapshots":[{"event_id":"sha256:4b18036fecb126e9d2186a440edce11b18a60375485f93525484a7ab011499e8","target":"graph","created_at":"2026-07-05T06:30:08Z","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/2307.02682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense video captioning, a task of localizing meaningful moments and generating relevant captions for videos, often requires a large, expensive corpus of annotated video segments paired with text. In an effort to minimize the annotation cost, we propose ZeroTA, a novel method for dense video captioning in a zero-shot manner. Our method does not require any videos or annotations for training; instead, it localizes and describes events within each input video at test time by optimizing solely on the input. This is accomplished by introducing a soft moment mask that represents a temporal segment i","authors_text":"Aiden SJ Lee, Hanseok Oh, Hyunji Lee, Minjoon Seo, Seongyun Lee, Yongrae Jo","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T23:01:26Z","title":"Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02682","kind":"arxiv","version":2},"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:e252703132bb8ea9248385025807a3a2b646326e584dd25da3816a64afe9bbd2","target":"record","created_at":"2026-07-05T06:30:08Z","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":"3ac02283aab6226576cecb2ae5eb9625161afe0f3909b1d50486f1731c7d090a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T23:01:26Z","title_canon_sha256":"8ce588f981eb06f356ab2a32e512eff7728366394dfaaeec39e7e0633e875eac"},"schema_version":"1.0","source":{"id":"2307.02682","kind":"arxiv","version":2}},"canonical_sha256":"1ca0cac3b77be9b128333747b411eaa84e3d9772c1a1e14786181c50602c18af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ca0cac3b77be9b128333747b411eaa84e3d9772c1a1e14786181c50602c18af","first_computed_at":"2026-07-05T06:30:08.043187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:08.043187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qdd+u/VS3N1JY5Chtq0Uf8RHkgbtRdqGFxn1M5G1KfTNz+opNnL3up6H47hJPTfy4fr2+KjY7FDfr8iDuK4/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:08.043624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.02682","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e252703132bb8ea9248385025807a3a2b646326e584dd25da3816a64afe9bbd2","sha256:4b18036fecb126e9d2186a440edce11b18a60375485f93525484a7ab011499e8"],"state_sha256":"8a2555bce98aff10fb1fba2fe2b495bd35702e86a33537bb27be264c9e1391ea"}