{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EDXX3U3T2ZXBCL3CNDD3666OYU","short_pith_number":"pith:EDXX3U3T","schema_version":"1.0","canonical_sha256":"20ef7dd373d66e112f6268c7bf7bcec52a52397aebb74f7f41d2fa43fde6fd8f","source":{"kind":"arxiv","id":"2608.13205","version":1},"attestation_state":"computed","paper":{"title":"HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Jiazi Bu, Pengyang Ling, Shengyuan Ding, Tianyi Wei, Tong Wu, Xiaohang Zhan, Xingang Pan, Xuanlang Dai, Yibin Wang, Yuhang Zang, Yujie Zhou","submitted_at":"2026-08-13T13:08:27Z","abstract_excerpt":"Text-Image-to-Video (TI2V) models are an emerging unified architecture, where a single model simultaneously supports text-to-video (T2V) and image-to-video (I2V) generation. Given a high-quality first frame or a detailed textual prompt, TI2V models unlock substantially better visual quality than their T2V mode, raising a natural question: can the capability elicited by such privileged conditions be internalized into the model's own base generation ability? A common approach toward this goal is model self-distillation. However, the most straightforward solution, supervised fine-tuning, follows "},"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":"2608.13205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T13:08:27Z","cross_cats_sorted":[],"title_canon_sha256":"7131be7b22adf8f61892ec320be1174ca83d383eeeae733968a0d6f264328ac2","abstract_canon_sha256":"bcec146b43e5229fb106e1a20c4d45c46368704dca302ba9e490a73af5ee75eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:39.786024Z","signature_b64":"Yt4v5gL3POUR7SUh9ObguoAKWwRgk6Oox/1PfyeuK349SucMZl6d/W4i7vTLOwSh6BNTS17S0CWDMMnsxUtiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20ef7dd373d66e112f6268c7bf7bcec52a52397aebb74f7f41d2fa43fde6fd8f","last_reissued_at":"2026-08-14T01:00:39.784067Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:39.784067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Jiazi Bu, Pengyang Ling, Shengyuan Ding, Tianyi Wei, Tong Wu, Xiaohang Zhan, Xingang Pan, Xuanlang Dai, Yibin Wang, Yuhang Zang, Yujie Zhou","submitted_at":"2026-08-13T13:08:27Z","abstract_excerpt":"Text-Image-to-Video (TI2V) models are an emerging unified architecture, where a single model simultaneously supports text-to-video (T2V) and image-to-video (I2V) generation. Given a high-quality first frame or a detailed textual prompt, TI2V models unlock substantially better visual quality than their T2V mode, raising a natural question: can the capability elicited by such privileged conditions be internalized into the model's own base generation ability? A common approach toward this goal is model self-distillation. However, the most straightforward solution, supervised fine-tuning, follows "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13205","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/2608.13205/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":"2608.13205","created_at":"2026-08-14T01:00:39.785023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.13205v1","created_at":"2026-08-14T01:00:39.785023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13205","created_at":"2026-08-14T01:00:39.785023+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDXX3U3T2ZXB","created_at":"2026-08-14T01:00:39.785023+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDXX3U3T2ZXBCL3C","created_at":"2026-08-14T01:00:39.785023+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDXX3U3T","created_at":"2026-08-14T01:00:39.785023+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/EDXX3U3T2ZXBCL3CNDD3666OYU","json":"https://pith.science/pith/EDXX3U3T2ZXBCL3CNDD3666OYU.json","graph_json":"https://pith.science/api/pith-number/EDXX3U3T2ZXBCL3CNDD3666OYU/graph.json","events_json":"https://pith.science/api/pith-number/EDXX3U3T2ZXBCL3CNDD3666OYU/events.json","paper":"https://pith.science/paper/EDXX3U3T"},"agent_actions":{"view_html":"https://pith.science/pith/EDXX3U3T2ZXBCL3CNDD3666OYU","download_json":"https://pith.science/pith/EDXX3U3T2ZXBCL3CNDD3666OYU.json","view_paper":"https://pith.science/paper/EDXX3U3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.13205&json=true","fetch_graph":"https://pith.science/api/pith-number/EDXX3U3T2ZXBCL3CNDD3666OYU/graph.json","fetch_events":"https://pith.science/api/pith-number/EDXX3U3T2ZXBCL3CNDD3666OYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDXX3U3T2ZXBCL3CNDD3666OYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDXX3U3T2ZXBCL3CNDD3666OYU/action/storage_attestation","attest_author":"https://pith.science/pith/EDXX3U3T2ZXBCL3CNDD3666OYU/action/author_attestation","sign_citation":"https://pith.science/pith/EDXX3U3T2ZXBCL3CNDD3666OYU/action/citation_signature","submit_replication":"https://pith.science/pith/EDXX3U3T2ZXBCL3CNDD3666OYU/action/replication_record"}},"created_at":"2026-08-14T01:00:39.785023+00:00","updated_at":"2026-08-14T01:00:39.785023+00:00"}