{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CFUQLVASMVBT3QGXOYPVJHZZKN","short_pith_number":"pith:CFUQLVAS","canonical_record":{"source":{"id":"2410.20502","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-27T16:28:28Z","cross_cats_sorted":[],"title_canon_sha256":"0969678ebb21a44ae6dae83a47b6ba76da05421ad94de068b167e569dcbbf59d","abstract_canon_sha256":"3aaa921c36c10a45a2a9b8ae88af12426992976cfd098ed789ca97a21e342053"},"schema_version":"1.0"},"canonical_sha256":"116905d41265433dc0d7761f549f395379034dbac686acdf805dd422be912bfa","source":{"kind":"arxiv","id":"2410.20502","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20502","created_at":"2026-07-05T10:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20502v3","created_at":"2026-07-05T10:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20502","created_at":"2026-07-05T10:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"CFUQLVASMVBT","created_at":"2026-07-05T10:49:10Z"},{"alias_kind":"pith_short_16","alias_value":"CFUQLVASMVBT3QGX","created_at":"2026-07-05T10:49:10Z"},{"alias_kind":"pith_short_8","alias_value":"CFUQLVAS","created_at":"2026-07-05T10:49:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CFUQLVASMVBT3QGXOYPVJHZZKN","target":"record","payload":{"canonical_record":{"source":{"id":"2410.20502","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-27T16:28:28Z","cross_cats_sorted":[],"title_canon_sha256":"0969678ebb21a44ae6dae83a47b6ba76da05421ad94de068b167e569dcbbf59d","abstract_canon_sha256":"3aaa921c36c10a45a2a9b8ae88af12426992976cfd098ed789ca97a21e342053"},"schema_version":"1.0"},"canonical_sha256":"116905d41265433dc0d7761f549f395379034dbac686acdf805dd422be912bfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:10.553174Z","signature_b64":"pnDLlFbOqA8cVy89M858Uak38i+cbpQah6PKqBMN+eRFUYpmZz/zcjy196DG8UGOPUyq56CPxwoQzHmZyG8yDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"116905d41265433dc0d7761f549f395379034dbac686acdf805dd422be912bfa","last_reissued_at":"2026-07-05T10:49:10.552701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:10.552701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.20502","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PNPl17Nm8mYD6CgkLjHULj9lhjZaLBGGelvWv4UrDmoUx91+kWASkK26i/CylkE6GlTKW3WvFW0HznLMY2RBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T14:53:09.668620Z"},"content_sha256":"014af77eac7f13b886a7f7728ec2c366396bd67b6652aee925c2f056eb50e4de","schema_version":"1.0","event_id":"sha256:014af77eac7f13b886a7f7728ec2c366396bd67b6652aee925c2f056eb50e4de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CFUQLVASMVBT3QGXOYPVJHZZKN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Furu Wei, Hefei Ling, Jeongsoo Choi, Jinyu Li, Lingwei Meng, Long Zhou, Shujie Hu, Shujie Liu, Xun Guo, Zongyi Li","submitted_at":"2024-10-27T16:28:28Z","abstract_excerpt":"Text-to-video models have recently undergone rapid and substantial advancements. Nevertheless, due to limitations in data and computational resources, achieving efficient generation of long videos with rich motion dynamics remains a significant challenge. To generate high-quality, dynamic, and temporally consistent long videos, this paper presents ARLON, a novel framework that boosts diffusion Transformers with autoregressive models for long video generation, by integrating the coarse spatial and long-range temporal information provided by the AR model to guide the DiT model. Specifically, ARL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20502","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/2410.20502/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3K8I63hemNSnRd6oiE0RpI5pxxeqaJieGox+JH7f7v78TolHfiltsMH37wZLJ4A8qeAfAX9gouiW9SN/3LXjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T14:53:09.669144Z"},"content_sha256":"ed1a6812b239de3523363a1b04ce0ed0852fe391431dccf3ac7d79d88c8b047b","schema_version":"1.0","event_id":"sha256:ed1a6812b239de3523363a1b04ce0ed0852fe391431dccf3ac7d79d88c8b047b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/bundle.json","state_url":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-02T14:53:09Z","links":{"resolver":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN","bundle":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/bundle.json","state":"https://pith.science/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CFUQLVASMVBT3QGXOYPVJHZZKN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CFUQLVASMVBT3QGXOYPVJHZZKN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3aaa921c36c10a45a2a9b8ae88af12426992976cfd098ed789ca97a21e342053","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-27T16:28:28Z","title_canon_sha256":"0969678ebb21a44ae6dae83a47b6ba76da05421ad94de068b167e569dcbbf59d"},"schema_version":"1.0","source":{"id":"2410.20502","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20502","created_at":"2026-07-05T10:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20502v3","created_at":"2026-07-05T10:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20502","created_at":"2026-07-05T10:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"CFUQLVASMVBT","created_at":"2026-07-05T10:49:10Z"},{"alias_kind":"pith_short_16","alias_value":"CFUQLVASMVBT3QGX","created_at":"2026-07-05T10:49:10Z"},{"alias_kind":"pith_short_8","alias_value":"CFUQLVAS","created_at":"2026-07-05T10:49:10Z"}],"graph_snapshots":[{"event_id":"sha256:ed1a6812b239de3523363a1b04ce0ed0852fe391431dccf3ac7d79d88c8b047b","target":"graph","created_at":"2026-07-05T10:49:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.20502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-video models have recently undergone rapid and substantial advancements. Nevertheless, due to limitations in data and computational resources, achieving efficient generation of long videos with rich motion dynamics remains a significant challenge. To generate high-quality, dynamic, and temporally consistent long videos, this paper presents ARLON, a novel framework that boosts diffusion Transformers with autoregressive models for long video generation, by integrating the coarse spatial and long-range temporal information provided by the AR model to guide the DiT model. Specifically, ARL","authors_text":"Furu Wei, Hefei Ling, Jeongsoo Choi, Jinyu Li, Lingwei Meng, Long Zhou, Shujie Hu, Shujie Liu, Xun Guo, Zongyi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-27T16:28:28Z","title":"ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20502","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:014af77eac7f13b886a7f7728ec2c366396bd67b6652aee925c2f056eb50e4de","target":"record","created_at":"2026-07-05T10:49:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3aaa921c36c10a45a2a9b8ae88af12426992976cfd098ed789ca97a21e342053","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-27T16:28:28Z","title_canon_sha256":"0969678ebb21a44ae6dae83a47b6ba76da05421ad94de068b167e569dcbbf59d"},"schema_version":"1.0","source":{"id":"2410.20502","kind":"arxiv","version":3}},"canonical_sha256":"116905d41265433dc0d7761f549f395379034dbac686acdf805dd422be912bfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"116905d41265433dc0d7761f549f395379034dbac686acdf805dd422be912bfa","first_computed_at":"2026-07-05T10:49:10.552701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:10.552701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pnDLlFbOqA8cVy89M858Uak38i+cbpQah6PKqBMN+eRFUYpmZz/zcjy196DG8UGOPUyq56CPxwoQzHmZyG8yDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:10.553174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20502","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:014af77eac7f13b886a7f7728ec2c366396bd67b6652aee925c2f056eb50e4de","sha256:ed1a6812b239de3523363a1b04ce0ed0852fe391431dccf3ac7d79d88c8b047b"],"state_sha256":"640aecc1deb912e3b9714874554f7d66c3de5fdf12aa4326231a51cfb1f4b264"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wti+YaXpAjv8wy8+ZN4g9R5Ki3qGrdz92G2Z0xyH29POQRMWiGwGFEKOj9xfe+y/vEJ3cJOD1YxwDuYhvylkCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T14:53:09.674238Z","bundle_sha256":"1ae48d2b3be1a489b03cce914b386e506539704c12ecb3419a03aef883c1c468"}}