{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3WKQGEPZX7DG445XLAAFEBK2PL","short_pith_number":"pith:3WKQGEPZ","schema_version":"1.0","canonical_sha256":"dd950311f9bfc66e73b7580052055a7af7c30e1b517bfdae9f8f74292aa313b9","source":{"kind":"arxiv","id":"2507.15728","version":1},"attestation_state":"computed","paper":{"title":"TokensGen: Harnessing Condensed Tokens for Long Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danni Yang, Jianlou Si, Lei Yang, Shuai Yang, Wenqi Ouyang, Xingang Pan, Yifan Zhou, Zeqi Xiao","submitted_at":"2025-07-21T15:37:33Z","abstract_excerpt":"Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In this paper, we propose TokensGen, a novel two-stage framework that leverages condensed tokens to address these issues. Our method decomposes long video generation into three core tasks: (1) inner-clip semantic control, (2) long-term consistency control, and (3) inter-clip smooth transition. First, we train To2V (Token-to-Video), a short video diffusion mode"},"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":"2507.15728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T15:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"056c28223aea0b130c178a9e40e385b73a1aa058b4537a110226bf244e4435a4","abstract_canon_sha256":"90cbd53768efa3e0dd347bbfa549b6fac324b28baaa2b3a979a2b767d4395a07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:42.849211Z","signature_b64":"UFy7I9Xf0vvEfg4zbjn99xxbusUCHgNMlyVOEiKLlZIRuMvL6VVkyF8/VTKqErnlZtyEDQ+P2732kIjSVlk2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd950311f9bfc66e73b7580052055a7af7c30e1b517bfdae9f8f74292aa313b9","last_reissued_at":"2026-07-05T11:40:42.848729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:42.848729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TokensGen: Harnessing Condensed Tokens for Long Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danni Yang, Jianlou Si, Lei Yang, Shuai Yang, Wenqi Ouyang, Xingang Pan, Yifan Zhou, Zeqi Xiao","submitted_at":"2025-07-21T15:37:33Z","abstract_excerpt":"Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In this paper, we propose TokensGen, a novel two-stage framework that leverages condensed tokens to address these issues. Our method decomposes long video generation into three core tasks: (1) inner-clip semantic control, (2) long-term consistency control, and (3) inter-clip smooth transition. First, we train To2V (Token-to-Video), a short video diffusion mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15728","kind":"arxiv","version":1},"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/2507.15728/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":"2507.15728","created_at":"2026-07-05T11:40:42.848783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15728v1","created_at":"2026-07-05T11:40:42.848783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15728","created_at":"2026-07-05T11:40:42.848783+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WKQGEPZX7DG","created_at":"2026-07-05T11:40:42.848783+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WKQGEPZX7DG445X","created_at":"2026-07-05T11:40:42.848783+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WKQGEPZ","created_at":"2026-07-05T11:40:42.848783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WKQGEPZX7DG445XLAAFEBK2PL","json":"https://pith.science/pith/3WKQGEPZX7DG445XLAAFEBK2PL.json","graph_json":"https://pith.science/api/pith-number/3WKQGEPZX7DG445XLAAFEBK2PL/graph.json","events_json":"https://pith.science/api/pith-number/3WKQGEPZX7DG445XLAAFEBK2PL/events.json","paper":"https://pith.science/paper/3WKQGEPZ"},"agent_actions":{"view_html":"https://pith.science/pith/3WKQGEPZX7DG445XLAAFEBK2PL","download_json":"https://pith.science/pith/3WKQGEPZX7DG445XLAAFEBK2PL.json","view_paper":"https://pith.science/paper/3WKQGEPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15728&json=true","fetch_graph":"https://pith.science/api/pith-number/3WKQGEPZX7DG445XLAAFEBK2PL/graph.json","fetch_events":"https://pith.science/api/pith-number/3WKQGEPZX7DG445XLAAFEBK2PL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WKQGEPZX7DG445XLAAFEBK2PL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WKQGEPZX7DG445XLAAFEBK2PL/action/storage_attestation","attest_author":"https://pith.science/pith/3WKQGEPZX7DG445XLAAFEBK2PL/action/author_attestation","sign_citation":"https://pith.science/pith/3WKQGEPZX7DG445XLAAFEBK2PL/action/citation_signature","submit_replication":"https://pith.science/pith/3WKQGEPZX7DG445XLAAFEBK2PL/action/replication_record"}},"created_at":"2026-07-05T11:40:42.848783+00:00","updated_at":"2026-07-05T11:40:42.848783+00:00"}