{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2NHLVJJERDRCPC23ZTBVKYTF4Z","short_pith_number":"pith:2NHLVJJE","schema_version":"1.0","canonical_sha256":"d34ebaa52488e2278b5bccc3556265e64ad9f23e517062b55aa545f76a368215","source":{"kind":"arxiv","id":"2606.28016","version":1},"attestation_state":"computed","paper":{"title":"TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiajun Liang, Jing Wang, Kaiqi Liu, Tianyu Pang, Wanyun Pang, Xiangxin Zhou, Xiaodan Liang, Zhenyu Xie","submitted_at":"2026-06-26T12:19:28Z","abstract_excerpt":"Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context, but this chunk-wise formulation makes temporal instruction following ambiguous. A single global prompt does not specify which sub-event should be realized in each chunk, while naively switching to step-wise prompts often leads to delayed reactions, blended step semantics, and error propagation across prompt transitions. These failures are difficult to address with supervised fine-tuning or distillation alone: SFT suffers from exposure bias, while "},"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":"2606.28016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T12:19:28Z","cross_cats_sorted":[],"title_canon_sha256":"9c92e9f5e4bb6bca4757680c0bb495a603f15419b3ba27d181fe505bf336df47","abstract_canon_sha256":"8546794bc29be96b63603cfb19e06a5272e6b4c470266b3c800c6b77a389a749"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:55.253079Z","signature_b64":"bbq4f0ALMPtSKS+A5sQ0RzLAsA9XYfDKl+G1Cwyp/xPdCiUnu3lz/TKpRj8wSD2DkMAUNbE8CqGur9dT/2/qCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d34ebaa52488e2278b5bccc3556265e64ad9f23e517062b55aa545f76a368215","last_reissued_at":"2026-06-29T01:14:55.252705Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:55.252705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiajun Liang, Jing Wang, Kaiqi Liu, Tianyu Pang, Wanyun Pang, Xiangxin Zhou, Xiaodan Liang, Zhenyu Xie","submitted_at":"2026-06-26T12:19:28Z","abstract_excerpt":"Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context, but this chunk-wise formulation makes temporal instruction following ambiguous. A single global prompt does not specify which sub-event should be realized in each chunk, while naively switching to step-wise prompts often leads to delayed reactions, blended step semantics, and error propagation across prompt transitions. These failures are difficult to address with supervised fine-tuning or distillation alone: SFT suffers from exposure bias, while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28016","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/2606.28016/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":"2606.28016","created_at":"2026-06-29T01:14:55.252755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28016v1","created_at":"2026-06-29T01:14:55.252755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28016","created_at":"2026-06-29T01:14:55.252755+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NHLVJJERDRC","created_at":"2026-06-29T01:14:55.252755+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NHLVJJERDRCPC23","created_at":"2026-06-29T01:14:55.252755+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NHLVJJE","created_at":"2026-06-29T01:14:55.252755+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/2NHLVJJERDRCPC23ZTBVKYTF4Z","json":"https://pith.science/pith/2NHLVJJERDRCPC23ZTBVKYTF4Z.json","graph_json":"https://pith.science/api/pith-number/2NHLVJJERDRCPC23ZTBVKYTF4Z/graph.json","events_json":"https://pith.science/api/pith-number/2NHLVJJERDRCPC23ZTBVKYTF4Z/events.json","paper":"https://pith.science/paper/2NHLVJJE"},"agent_actions":{"view_html":"https://pith.science/pith/2NHLVJJERDRCPC23ZTBVKYTF4Z","download_json":"https://pith.science/pith/2NHLVJJERDRCPC23ZTBVKYTF4Z.json","view_paper":"https://pith.science/paper/2NHLVJJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28016&json=true","fetch_graph":"https://pith.science/api/pith-number/2NHLVJJERDRCPC23ZTBVKYTF4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/2NHLVJJERDRCPC23ZTBVKYTF4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NHLVJJERDRCPC23ZTBVKYTF4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NHLVJJERDRCPC23ZTBVKYTF4Z/action/storage_attestation","attest_author":"https://pith.science/pith/2NHLVJJERDRCPC23ZTBVKYTF4Z/action/author_attestation","sign_citation":"https://pith.science/pith/2NHLVJJERDRCPC23ZTBVKYTF4Z/action/citation_signature","submit_replication":"https://pith.science/pith/2NHLVJJERDRCPC23ZTBVKYTF4Z/action/replication_record"}},"created_at":"2026-06-29T01:14:55.252755+00:00","updated_at":"2026-06-29T01:14:55.252755+00:00"}