{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XMYYPLYY45Z5DE3C4RETHNGQFK","short_pith_number":"pith:XMYYPLYY","schema_version":"1.0","canonical_sha256":"bb3187af18e773d19362e44933b4d02ab53960b7afea74ccef95d7325cb860c4","source":{"kind":"arxiv","id":"2405.04682","version":4},"attestation_state":"computed","paper":{"title":"TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Grover, Hritik Bansal, Idan Szpektor, Kai-Wei Chang, Michal Yarom, Yonatan Bitton","submitted_at":"2024-05-07T21:52:39Z","abstract_excerpt":"Most of these text-to-video (T2V) generative models often produce single-scene video clips that depict an entity performing a particular action (e.g., 'a red panda climbing a tree'). However, it is pertinent to generate multi-scene videos since they are ubiquitous in the real-world (e.g., 'a red panda climbing a tree' followed by 'the red panda sleeps on the top of the tree'). To generate multi-scene videos from the pretrained T2V model, we introduce a simple and effective Time-Aligned Captions (TALC) framework. Specifically, we enhance the text-conditioning mechanism in the T2V architecture t"},"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":"2405.04682","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T21:52:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a68cb8f7b77254dfbefe0056c1aba4b50a092bc30daa8b7e3f1b74bf827323e3","abstract_canon_sha256":"0f9063a36b38e48e434f8407470b63ec2fb3538ac48b5cffefb0cf88de4358f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:44.011731Z","signature_b64":"WeS2hFiEwpmmHbASqUFQefyk/EjqSpqN17BV6z7ifFbG0fVOcCnLGm/TDsAv3gwLuQlF+nx9Kc6LjZ6w6DTBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb3187af18e773d19362e44933b4d02ab53960b7afea74ccef95d7325cb860c4","last_reissued_at":"2026-07-05T09:32:44.011213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:44.011213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Grover, Hritik Bansal, Idan Szpektor, Kai-Wei Chang, Michal Yarom, Yonatan Bitton","submitted_at":"2024-05-07T21:52:39Z","abstract_excerpt":"Most of these text-to-video (T2V) generative models often produce single-scene video clips that depict an entity performing a particular action (e.g., 'a red panda climbing a tree'). However, it is pertinent to generate multi-scene videos since they are ubiquitous in the real-world (e.g., 'a red panda climbing a tree' followed by 'the red panda sleeps on the top of the tree'). To generate multi-scene videos from the pretrained T2V model, we introduce a simple and effective Time-Aligned Captions (TALC) framework. Specifically, we enhance the text-conditioning mechanism in the T2V architecture t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04682","kind":"arxiv","version":4},"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/2405.04682/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":"2405.04682","created_at":"2026-07-05T09:32:44.011270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04682v4","created_at":"2026-07-05T09:32:44.011270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04682","created_at":"2026-07-05T09:32:44.011270+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMYYPLYY45Z5","created_at":"2026-07-05T09:32:44.011270+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMYYPLYY45Z5DE3C","created_at":"2026-07-05T09:32:44.011270+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMYYPLYY","created_at":"2026-07-05T09:32:44.011270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.03520","citing_title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25161","citing_title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12496","citing_title":"CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19473","citing_title":"TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK","json":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK.json","graph_json":"https://pith.science/api/pith-number/XMYYPLYY45Z5DE3C4RETHNGQFK/graph.json","events_json":"https://pith.science/api/pith-number/XMYYPLYY45Z5DE3C4RETHNGQFK/events.json","paper":"https://pith.science/paper/XMYYPLYY"},"agent_actions":{"view_html":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK","download_json":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK.json","view_paper":"https://pith.science/paper/XMYYPLYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04682&json=true","fetch_graph":"https://pith.science/api/pith-number/XMYYPLYY45Z5DE3C4RETHNGQFK/graph.json","fetch_events":"https://pith.science/api/pith-number/XMYYPLYY45Z5DE3C4RETHNGQFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/action/storage_attestation","attest_author":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/action/author_attestation","sign_citation":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/action/citation_signature","submit_replication":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/action/replication_record"}},"created_at":"2026-07-05T09:32:44.011270+00:00","updated_at":"2026-07-05T09:32:44.011270+00:00"}