{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VDSO5MNIZZJ7OZRQ2PVEGVIDHM","short_pith_number":"pith:VDSO5MNI","schema_version":"1.0","canonical_sha256":"a8e4eeb1a8ce53f76630d3ea4355033b35af3934942c152348c8d8aef9e5175c","source":{"kind":"arxiv","id":"2606.03971","version":1},"attestation_state":"computed","paper":{"title":"Video-Mirai: Autoregressive Video Diffusion Models Need Foresight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lang Huang, Runyi Li, Toshihiko Yamasaki, Yonghao Yu, Zerun Wang","submitted_at":"2026-06-02T17:55:13Z","abstract_excerpt":"Causal video generators must predict from the past, but they need not learn only from it. In streaming autoregressive video diffusion, each emitted segment becomes a commitment that future segments must preserve. Standard training, however, only asks each causal state to explain the present. This creates what we call a representation-level planning gap: states that fit the current segment may discard identity, layout, and motion information needed for a consistent future. We introduce Video-Mirai, a training-only method that closes this gap without changing causal inference: the generator roll"},"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":"2606.03971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T17:55:13Z","cross_cats_sorted":[],"title_canon_sha256":"badfea1688e8b6e30efefeb9992d591e5a5f24294e95d753af0547dd3e71acca","abstract_canon_sha256":"386546d30be3533975871c5faba67b35d34e4d110e805de6780d4e79096c441f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:08.305615Z","signature_b64":"4YK3R16Y6WjAtTeQkd2CZGOAsLmRmzBcErPIDEHmkkQs65yZwmFqrxNCcB1AQfc/KBsp/sAaeezDfTYptHiBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8e4eeb1a8ce53f76630d3ea4355033b35af3934942c152348c8d8aef9e5175c","last_reissued_at":"2026-06-03T02:06:08.305205Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:08.305205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-Mirai: Autoregressive Video Diffusion Models Need Foresight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lang Huang, Runyi Li, Toshihiko Yamasaki, Yonghao Yu, Zerun Wang","submitted_at":"2026-06-02T17:55:13Z","abstract_excerpt":"Causal video generators must predict from the past, but they need not learn only from it. In streaming autoregressive video diffusion, each emitted segment becomes a commitment that future segments must preserve. Standard training, however, only asks each causal state to explain the present. This creates what we call a representation-level planning gap: states that fit the current segment may discard identity, layout, and motion information needed for a consistent future. We introduce Video-Mirai, a training-only method that closes this gap without changing causal inference: the generator roll"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03971","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/2606.03971/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":"2606.03971","created_at":"2026-06-03T02:06:08.305266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03971v1","created_at":"2026-06-03T02:06:08.305266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03971","created_at":"2026-06-03T02:06:08.305266+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDSO5MNIZZJ7","created_at":"2026-06-03T02:06:08.305266+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDSO5MNIZZJ7OZRQ","created_at":"2026-06-03T02:06:08.305266+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDSO5MNI","created_at":"2026-06-03T02:06:08.305266+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/VDSO5MNIZZJ7OZRQ2PVEGVIDHM","json":"https://pith.science/pith/VDSO5MNIZZJ7OZRQ2PVEGVIDHM.json","graph_json":"https://pith.science/api/pith-number/VDSO5MNIZZJ7OZRQ2PVEGVIDHM/graph.json","events_json":"https://pith.science/api/pith-number/VDSO5MNIZZJ7OZRQ2PVEGVIDHM/events.json","paper":"https://pith.science/paper/VDSO5MNI"},"agent_actions":{"view_html":"https://pith.science/pith/VDSO5MNIZZJ7OZRQ2PVEGVIDHM","download_json":"https://pith.science/pith/VDSO5MNIZZJ7OZRQ2PVEGVIDHM.json","view_paper":"https://pith.science/paper/VDSO5MNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03971&json=true","fetch_graph":"https://pith.science/api/pith-number/VDSO5MNIZZJ7OZRQ2PVEGVIDHM/graph.json","fetch_events":"https://pith.science/api/pith-number/VDSO5MNIZZJ7OZRQ2PVEGVIDHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDSO5MNIZZJ7OZRQ2PVEGVIDHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDSO5MNIZZJ7OZRQ2PVEGVIDHM/action/storage_attestation","attest_author":"https://pith.science/pith/VDSO5MNIZZJ7OZRQ2PVEGVIDHM/action/author_attestation","sign_citation":"https://pith.science/pith/VDSO5MNIZZJ7OZRQ2PVEGVIDHM/action/citation_signature","submit_replication":"https://pith.science/pith/VDSO5MNIZZJ7OZRQ2PVEGVIDHM/action/replication_record"}},"created_at":"2026-06-03T02:06:08.305266+00:00","updated_at":"2026-06-03T02:06:08.305266+00:00"}