{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MJ2S6FNJTOGRJREHXCIYKTI7Q4","short_pith_number":"pith:MJ2S6FNJ","schema_version":"1.0","canonical_sha256":"62752f15a99b8d14c487b891854d1f8718d4c8b874d282d6feb6d9c9ad8b3939","source":{"kind":"arxiv","id":"2412.03758","version":3},"attestation_state":"computed","paper":{"title":"ARCON: Advancing Auto-Regressive Continuation for Driving Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianming Hu, Jingwei Wu, Lihui Peng, Ruibo Ming, Shuchang Zhou, Zhewei Huang, Zhuoxuan Ju","submitted_at":"2024-12-04T22:53:56Z","abstract_excerpt":"Recent advancements in auto-regressive large language models (LLMs) have led to their application in video generation. This paper explores the use of Large Vision Models (LVMs) for video continuation, a task essential for building world models and predicting future frames. We introduce ARCON, a scheme that alternates between generating semantic and RGB tokens, allowing the LVM to explicitly learn high-level structural video information. We find high consistency in the RGB images and semantic maps generated without special design. Moreover, we employ an optical flow-based texture stitching meth"},"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":"2412.03758","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T22:53:56Z","cross_cats_sorted":[],"title_canon_sha256":"e32d65793d6c5ad6695574a576f4ce6d940fbb115963895cd06635b562e19b79","abstract_canon_sha256":"5efec49d0e148078906b878df85c54a42e89229450961f1b8d65500f5acfb9d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:17.983568Z","signature_b64":"SJwgxnbumsTZyHigFGv1l6LvAtgnFtzhRQl05k5PVwsOEzzs9eIIsJgN8q53oRVWG9AUn43q741nRksD+O94Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62752f15a99b8d14c487b891854d1f8718d4c8b874d282d6feb6d9c9ad8b3939","last_reissued_at":"2026-07-05T10:20:17.982929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:17.982929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARCON: Advancing Auto-Regressive Continuation for Driving Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianming Hu, Jingwei Wu, Lihui Peng, Ruibo Ming, Shuchang Zhou, Zhewei Huang, Zhuoxuan Ju","submitted_at":"2024-12-04T22:53:56Z","abstract_excerpt":"Recent advancements in auto-regressive large language models (LLMs) have led to their application in video generation. This paper explores the use of Large Vision Models (LVMs) for video continuation, a task essential for building world models and predicting future frames. We introduce ARCON, a scheme that alternates between generating semantic and RGB tokens, allowing the LVM to explicitly learn high-level structural video information. We find high consistency in the RGB images and semantic maps generated without special design. Moreover, we employ an optical flow-based texture stitching meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03758","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/2412.03758/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":"2412.03758","created_at":"2026-07-05T10:20:17.983005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03758v3","created_at":"2026-07-05T10:20:17.983005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03758","created_at":"2026-07-05T10:20:17.983005+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJ2S6FNJTOGR","created_at":"2026-07-05T10:20:17.983005+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJ2S6FNJTOGRJREH","created_at":"2026-07-05T10:20:17.983005+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJ2S6FNJ","created_at":"2026-07-05T10:20:17.983005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.11946","citing_title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MJ2S6FNJTOGRJREHXCIYKTI7Q4","json":"https://pith.science/pith/MJ2S6FNJTOGRJREHXCIYKTI7Q4.json","graph_json":"https://pith.science/api/pith-number/MJ2S6FNJTOGRJREHXCIYKTI7Q4/graph.json","events_json":"https://pith.science/api/pith-number/MJ2S6FNJTOGRJREHXCIYKTI7Q4/events.json","paper":"https://pith.science/paper/MJ2S6FNJ"},"agent_actions":{"view_html":"https://pith.science/pith/MJ2S6FNJTOGRJREHXCIYKTI7Q4","download_json":"https://pith.science/pith/MJ2S6FNJTOGRJREHXCIYKTI7Q4.json","view_paper":"https://pith.science/paper/MJ2S6FNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03758&json=true","fetch_graph":"https://pith.science/api/pith-number/MJ2S6FNJTOGRJREHXCIYKTI7Q4/graph.json","fetch_events":"https://pith.science/api/pith-number/MJ2S6FNJTOGRJREHXCIYKTI7Q4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJ2S6FNJTOGRJREHXCIYKTI7Q4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJ2S6FNJTOGRJREHXCIYKTI7Q4/action/storage_attestation","attest_author":"https://pith.science/pith/MJ2S6FNJTOGRJREHXCIYKTI7Q4/action/author_attestation","sign_citation":"https://pith.science/pith/MJ2S6FNJTOGRJREHXCIYKTI7Q4/action/citation_signature","submit_replication":"https://pith.science/pith/MJ2S6FNJTOGRJREHXCIYKTI7Q4/action/replication_record"}},"created_at":"2026-07-05T10:20:17.983005+00:00","updated_at":"2026-07-05T10:20:17.983005+00:00"}