{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WAST5FVTWRZHRE2RN3S7ULQIB2","short_pith_number":"pith:WAST5FVT","schema_version":"1.0","canonical_sha256":"b0253e96b3b4727893516ee5fa2e080e8bed14ae022d714412c5545dc94dea2f","source":{"kind":"arxiv","id":"2605.18233","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C. Chen, F. Mao, H. Guo, J. Wu, J. Zhu, K. Huang, M. Wu, X. Chu, X. Feng","submitted_at":"2026-05-18T11:28:45Z","abstract_excerpt":"Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce longer videos. Frame-level autoregressive frameworks, e.g., FIFO-diffusion, offer the advantage of generating infinitely long videos with constant memory consumption. However, the mismatch between training and inference, coupled with the challenge of maintaining long-term consistency, limits the effective utilization of foundation models. To mitigate these concerns, we propose \\textbf{MIGA}, a novel infinite-frame long video generation method. Firs"},"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":"2605.18233","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T11:28:45Z","cross_cats_sorted":[],"title_canon_sha256":"e8c5eaadf83ca6b06219287375d0aa7bb04a2f21ed99b2abea75cf66ed801951","abstract_canon_sha256":"d14420511d79bfd4475ee82a9a433c72da9754a8c324477fa40c106d8745823e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:51.599177Z","signature_b64":"0U7MiFYoEKyePTp2w68/GHrOdGsIqfmaYMg3PpxLSCY0eBB58NZ/vzSuzE4ccecdxZ8K4APQobQFGP6yqe1PCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0253e96b3b4727893516ee5fa2e080e8bed14ae022d714412c5545dc94dea2f","last_reissued_at":"2026-05-20T00:05:51.598586Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:51.598586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C. Chen, F. Mao, H. Guo, J. Wu, J. Zhu, K. Huang, M. Wu, X. Chu, X. Feng","submitted_at":"2026-05-18T11:28:45Z","abstract_excerpt":"Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce longer videos. Frame-level autoregressive frameworks, e.g., FIFO-diffusion, offer the advantage of generating infinitely long videos with constant memory consumption. However, the mismatch between training and inference, coupled with the challenge of maintaining long-term consistency, limits the effective utilization of foundation models. To mitigate these concerns, we propose \\textbf{MIGA}, a novel infinite-frame long video generation method. Firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18233","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/2605.18233/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T23:41:58.928134Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.289676Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d8b46cf6beef7f0c789d936cdc488022d4cd61c9fd586896368ce8171ebe65f0"},"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":"2605.18233","created_at":"2026-05-20T00:05:51.598663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18233v1","created_at":"2026-05-20T00:05:51.598663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18233","created_at":"2026-05-20T00:05:51.598663+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAST5FVTWRZH","created_at":"2026-05-20T00:05:51.598663+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAST5FVTWRZHRE2R","created_at":"2026-05-20T00:05:51.598663+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAST5FVT","created_at":"2026-05-20T00:05:51.598663+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/WAST5FVTWRZHRE2RN3S7ULQIB2","json":"https://pith.science/pith/WAST5FVTWRZHRE2RN3S7ULQIB2.json","graph_json":"https://pith.science/api/pith-number/WAST5FVTWRZHRE2RN3S7ULQIB2/graph.json","events_json":"https://pith.science/api/pith-number/WAST5FVTWRZHRE2RN3S7ULQIB2/events.json","paper":"https://pith.science/paper/WAST5FVT"},"agent_actions":{"view_html":"https://pith.science/pith/WAST5FVTWRZHRE2RN3S7ULQIB2","download_json":"https://pith.science/pith/WAST5FVTWRZHRE2RN3S7ULQIB2.json","view_paper":"https://pith.science/paper/WAST5FVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18233&json=true","fetch_graph":"https://pith.science/api/pith-number/WAST5FVTWRZHRE2RN3S7ULQIB2/graph.json","fetch_events":"https://pith.science/api/pith-number/WAST5FVTWRZHRE2RN3S7ULQIB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAST5FVTWRZHRE2RN3S7ULQIB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAST5FVTWRZHRE2RN3S7ULQIB2/action/storage_attestation","attest_author":"https://pith.science/pith/WAST5FVTWRZHRE2RN3S7ULQIB2/action/author_attestation","sign_citation":"https://pith.science/pith/WAST5FVTWRZHRE2RN3S7ULQIB2/action/citation_signature","submit_replication":"https://pith.science/pith/WAST5FVTWRZHRE2RN3S7ULQIB2/action/replication_record"}},"created_at":"2026-05-20T00:05:51.598663+00:00","updated_at":"2026-05-20T00:05:51.598663+00:00"}