{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H72LKVXKGRVEE62CTZZKCEKQMD","short_pith_number":"pith:H72LKVXK","schema_version":"1.0","canonical_sha256":"3ff4b556ea346a427b429e72a1115060da4f7be0c798044fd3c64adce67a851b","source":{"kind":"arxiv","id":"2603.08403","version":3},"attestation_state":"computed","paper":{"title":"SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baisen Wang, Botian Shi, Gim Hee Lee, Hanlin Chen, Jianbiao Mei, Jiangning Zhang, Liang Lv, Licheng Wen, Shuicheng Yan, Xiangtai Li, Xuemeng Yang, Yong Liu, Yue Liao, Yu Yang","submitted_at":"2026-03-09T14:00:36Z","abstract_excerpt":"Long-horizon action-conditioned video generation aims to synthesize temporally coherent videos that follow complex action instructions over extended horizons, requiring procedural ordering, persistent action execution, and scene consistency beyond conventional TI2V's short-term fidelity. Existing single-shot video generation models typically operate in an open-loop manner, leading to incomplete action execution, hallucinated motions, and temporal drift. To address this, we propose SPIRAL, a closed-loop framework that performs sequential planning and iterative reflection for action-conditioned "},"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":"2603.08403","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-09T14:00:36Z","cross_cats_sorted":[],"title_canon_sha256":"e0aa23bb916a1f01c23d1770be7d4957ac4e159db6214abe440c2d956cee607c","abstract_canon_sha256":"c33b7469c6de9a4a3710cebe6b56cc8d019ac6b7cd4600c0a6a4328ff889bd4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:59.875098Z","signature_b64":"EebgKGTCzbp+ETzw5Hiu5nnGxIr8Nbc1McOzCSvo2le56hf7IB1Xl9vjcc0bK3M0HqzS/nCxmj2f3eC96KzdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ff4b556ea346a427b429e72a1115060da4f7be0c798044fd3c64adce67a851b","last_reissued_at":"2026-05-22T01:03:59.874394Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:59.874394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baisen Wang, Botian Shi, Gim Hee Lee, Hanlin Chen, Jianbiao Mei, Jiangning Zhang, Liang Lv, Licheng Wen, Shuicheng Yan, Xiangtai Li, Xuemeng Yang, Yong Liu, Yue Liao, Yu Yang","submitted_at":"2026-03-09T14:00:36Z","abstract_excerpt":"Long-horizon action-conditioned video generation aims to synthesize temporally coherent videos that follow complex action instructions over extended horizons, requiring procedural ordering, persistent action execution, and scene consistency beyond conventional TI2V's short-term fidelity. Existing single-shot video generation models typically operate in an open-loop manner, leading to incomplete action execution, hallucinated motions, and temporal drift. To address this, we propose SPIRAL, a closed-loop framework that performs sequential planning and iterative reflection for action-conditioned "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.08403","kind":"arxiv","version":3},"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/2603.08403/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":"2603.08403","created_at":"2026-05-22T01:03:59.874496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.08403v3","created_at":"2026-05-22T01:03:59.874496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.08403","created_at":"2026-05-22T01:03:59.874496+00:00"},{"alias_kind":"pith_short_12","alias_value":"H72LKVXKGRVE","created_at":"2026-05-22T01:03:59.874496+00:00"},{"alias_kind":"pith_short_16","alias_value":"H72LKVXKGRVEE62C","created_at":"2026-05-22T01:03:59.874496+00:00"},{"alias_kind":"pith_short_8","alias_value":"H72LKVXK","created_at":"2026-05-22T01:03:59.874496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.21725","citing_title":"AEL: Agent Evolving Learning for Open-Ended Environments","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H72LKVXKGRVEE62CTZZKCEKQMD","json":"https://pith.science/pith/H72LKVXKGRVEE62CTZZKCEKQMD.json","graph_json":"https://pith.science/api/pith-number/H72LKVXKGRVEE62CTZZKCEKQMD/graph.json","events_json":"https://pith.science/api/pith-number/H72LKVXKGRVEE62CTZZKCEKQMD/events.json","paper":"https://pith.science/paper/H72LKVXK"},"agent_actions":{"view_html":"https://pith.science/pith/H72LKVXKGRVEE62CTZZKCEKQMD","download_json":"https://pith.science/pith/H72LKVXKGRVEE62CTZZKCEKQMD.json","view_paper":"https://pith.science/paper/H72LKVXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.08403&json=true","fetch_graph":"https://pith.science/api/pith-number/H72LKVXKGRVEE62CTZZKCEKQMD/graph.json","fetch_events":"https://pith.science/api/pith-number/H72LKVXKGRVEE62CTZZKCEKQMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H72LKVXKGRVEE62CTZZKCEKQMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H72LKVXKGRVEE62CTZZKCEKQMD/action/storage_attestation","attest_author":"https://pith.science/pith/H72LKVXKGRVEE62CTZZKCEKQMD/action/author_attestation","sign_citation":"https://pith.science/pith/H72LKVXKGRVEE62CTZZKCEKQMD/action/citation_signature","submit_replication":"https://pith.science/pith/H72LKVXKGRVEE62CTZZKCEKQMD/action/replication_record"}},"created_at":"2026-05-22T01:03:59.874496+00:00","updated_at":"2026-05-22T01:03:59.874496+00:00"}