{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A4HH3ZBEO4FG2ZTLAPBEUMEGCJ","short_pith_number":"pith:A4HH3ZBE","schema_version":"1.0","canonical_sha256":"070e7de424770a6d666b03c24a3086126590e40a37b8d35d52e93e4406e41134","source":{"kind":"arxiv","id":"2405.14040","version":2},"attestation_state":"computed","paper":{"title":"Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Biao Wang, Bo Zheng, Chunru Zhan, Dingyi Yang, Qin Jin, Tiezheng Ge, Ziheng Wang","submitted_at":"2024-05-22T22:22:26Z","abstract_excerpt":"Video storytelling is engaging multimedia content that utilizes video and its accompanying narration to attract the audience, where a key challenge is creating narrations for recorded visual scenes. Previous studies on dense video captioning and video story generation have made some progress. However, in practical applications, we typically require synchronized narrations for ongoing visual scenes. In this work, we introduce a new task of Synchronized Video Storytelling, which aims to generate synchronous and informative narrations for videos. These narrations, associated with each video clip,"},"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":"2405.14040","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-05-22T22:22:26Z","cross_cats_sorted":[],"title_canon_sha256":"7454676cb35ef080061bc68de7a37705683321c30b2ec672de7c759511887751","abstract_canon_sha256":"ab0b498344d204895c3481881842b0a2aeea36f2e0bfb95bc7fc621c7f34f65c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:09.502581Z","signature_b64":"1m4QaAmRj5mREz9D4DoYHUQ1ILZfUKlEGCh8fUf2uBis8Bm9iG/Jlw/bLtL/mHR6tTGJDcTrxyRLpRVW2Jo6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"070e7de424770a6d666b03c24a3086126590e40a37b8d35d52e93e4406e41134","last_reissued_at":"2026-07-05T09:55:09.502114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:09.502114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Biao Wang, Bo Zheng, Chunru Zhan, Dingyi Yang, Qin Jin, Tiezheng Ge, Ziheng Wang","submitted_at":"2024-05-22T22:22:26Z","abstract_excerpt":"Video storytelling is engaging multimedia content that utilizes video and its accompanying narration to attract the audience, where a key challenge is creating narrations for recorded visual scenes. Previous studies on dense video captioning and video story generation have made some progress. However, in practical applications, we typically require synchronized narrations for ongoing visual scenes. In this work, we introduce a new task of Synchronized Video Storytelling, which aims to generate synchronous and informative narrations for videos. These narrations, associated with each video clip,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14040","kind":"arxiv","version":2},"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/2405.14040/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":"2405.14040","created_at":"2026-07-05T09:55:09.502169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14040v2","created_at":"2026-07-05T09:55:09.502169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14040","created_at":"2026-07-05T09:55:09.502169+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4HH3ZBEO4FG","created_at":"2026-07-05T09:55:09.502169+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4HH3ZBEO4FG2ZTL","created_at":"2026-07-05T09:55:09.502169+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4HH3ZBE","created_at":"2026-07-05T09:55:09.502169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.25161","citing_title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ","json":"https://pith.science/pith/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ.json","graph_json":"https://pith.science/api/pith-number/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ/graph.json","events_json":"https://pith.science/api/pith-number/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ/events.json","paper":"https://pith.science/paper/A4HH3ZBE"},"agent_actions":{"view_html":"https://pith.science/pith/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ","download_json":"https://pith.science/pith/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ.json","view_paper":"https://pith.science/paper/A4HH3ZBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14040&json=true","fetch_graph":"https://pith.science/api/pith-number/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ/action/storage_attestation","attest_author":"https://pith.science/pith/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ/action/author_attestation","sign_citation":"https://pith.science/pith/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ/action/citation_signature","submit_replication":"https://pith.science/pith/A4HH3ZBEO4FG2ZTLAPBEUMEGCJ/action/replication_record"}},"created_at":"2026-07-05T09:55:09.502169+00:00","updated_at":"2026-07-05T09:55:09.502169+00:00"}