{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PDBYOXSXRJP444ZMJLWIK522YE","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":"78b4eb69cb060aad53af684d586b93bd0dbef58db59e07ce9f3f2a76725e58eb","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-17T15:15:17Z","title_canon_sha256":"99f20e9ad4516d6a7172d426bb801da3ace56e6f92a35d2984f290c1a2c31319"},"schema_version":"1.0","source":{"id":"2003.07758","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.07758","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2003.07758v2","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.07758","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"PDBYOXSXRJP4","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"PDBYOXSXRJP444ZM","created_at":"2026-07-05T01:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"PDBYOXSX","created_at":"2026-07-05T01:00:50Z"}],"graph_snapshots":[{"event_id":"sha256:512adc0bc9b0c80fc4864b5c04947bd070d8832fa96eada436920cce2a20d7a0","target":"graph","created_at":"2026-07-05T01:00:50Z","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/2003.07758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense video captioning is a task of localizing interesting events from an untrimmed video and producing textual description (captions) for each localized event. Most of the previous works in dense video captioning are solely based on visual information and completely ignore the audio track. However, audio, and speech, in particular, are vital cues for a human observer in understanding an environment. In this paper, we present a new dense video captioning approach that is able to utilize any number of modalities for event description. Specifically, we show how audio and speech modalities may im","authors_text":"Esa Rahtu, Vladimir Iashin","cross_cats":["cs.CL","cs.LG","cs.SD","eess.AS","eess.IV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-17T15:15:17Z","title":"Multi-modal Dense Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.07758","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":"sha256:7265a5e2ab5bb85649e153204ec3bd05b3d691f09e6c4aa2d0adfd407428d0cb","target":"record","created_at":"2026-07-05T01:00:50Z","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":"78b4eb69cb060aad53af684d586b93bd0dbef58db59e07ce9f3f2a76725e58eb","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-17T15:15:17Z","title_canon_sha256":"99f20e9ad4516d6a7172d426bb801da3ace56e6f92a35d2984f290c1a2c31319"},"schema_version":"1.0","source":{"id":"2003.07758","kind":"arxiv","version":2}},"canonical_sha256":"78c3875e578a5fce732c4aec85775ac12c0792fc9202c91b8ac96a861265180d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78c3875e578a5fce732c4aec85775ac12c0792fc9202c91b8ac96a861265180d","first_computed_at":"2026-07-05T01:00:50.434173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:50.434173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AKIcxXTOk9sOoC2bi17dfed/0BNGC4czV+jMAmwHIJgBfBgS2tK8BHZBZDpHuwTW4o+k1bx0TWNehjHqM5ojDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:50.434551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.07758","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7265a5e2ab5bb85649e153204ec3bd05b3d691f09e6c4aa2d0adfd407428d0cb","sha256:512adc0bc9b0c80fc4864b5c04947bd070d8832fa96eada436920cce2a20d7a0"],"state_sha256":"f44135dd54bbb4e76968afadbe74af79f68c90682f4bfcebc2b68ba1adb89587"}