{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YRRGPM3NRSDIUZGTGTNOSHORTB","short_pith_number":"pith:YRRGPM3N","schema_version":"1.0","canonical_sha256":"c46267b36d8c868a64d334dae91dd19875f964e820d39105a0f75f21b12225e5","source":{"kind":"arxiv","id":"2504.16016","version":1},"attestation_state":"computed","paper":{"title":"Efficient Temporal Consistency in Diffusion-Based Video Editing with Adaptor Modules: A Theoretical Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binxu Li, Hongyang He, Jianhui Wang, Jiaqi Chen, Keqin Li, Kuan Lu, Menghao Huo, Pei Liu, Ruoyu Wang, Sida Li, Xinhang Yuan, Xinyuan Song, Yangfan He","submitted_at":"2025-04-22T16:28:35Z","abstract_excerpt":"Adapter-based methods are commonly used to enhance model performance with minimal additional complexity, especially in video editing tasks that require frame-to-frame consistency. By inserting small, learnable modules into pretrained diffusion models, these adapters can maintain temporal coherence without extensive retraining. Approaches that incorporate prompt learning with both shared and frame-specific tokens are particularly effective in preserving continuity across frames at low training cost. In this work, we want to provide a general theoretical framework for adapters that maintain fram"},"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":"2504.16016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T16:28:35Z","cross_cats_sorted":[],"title_canon_sha256":"f45695085539412daad5e4a9fb0a5b5fc23f240dda2920f67f4e08fc41eb243f","abstract_canon_sha256":"ca4f842fabae348295c5cfbea37ff5e407c55e8b95420401e0827acf08b117b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:33.582154Z","signature_b64":"FgCQ9BhFeeOYgFybDA0UD11FvFApikbuvRagOgmAgMEzeO+Cc6AvF3WD8m2xo0MpobQNa8YQGhhaX43nN5GLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c46267b36d8c868a64d334dae91dd19875f964e820d39105a0f75f21b12225e5","last_reissued_at":"2026-07-05T10:52:33.581626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:33.581626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Temporal Consistency in Diffusion-Based Video Editing with Adaptor Modules: A Theoretical Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binxu Li, Hongyang He, Jianhui Wang, Jiaqi Chen, Keqin Li, Kuan Lu, Menghao Huo, Pei Liu, Ruoyu Wang, Sida Li, Xinhang Yuan, Xinyuan Song, Yangfan He","submitted_at":"2025-04-22T16:28:35Z","abstract_excerpt":"Adapter-based methods are commonly used to enhance model performance with minimal additional complexity, especially in video editing tasks that require frame-to-frame consistency. By inserting small, learnable modules into pretrained diffusion models, these adapters can maintain temporal coherence without extensive retraining. Approaches that incorporate prompt learning with both shared and frame-specific tokens are particularly effective in preserving continuity across frames at low training cost. In this work, we want to provide a general theoretical framework for adapters that maintain fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16016","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/2504.16016/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":"2504.16016","created_at":"2026-07-05T10:52:33.581688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16016v1","created_at":"2026-07-05T10:52:33.581688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16016","created_at":"2026-07-05T10:52:33.581688+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRRGPM3NRSDI","created_at":"2026-07-05T10:52:33.581688+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRRGPM3NRSDIUZGT","created_at":"2026-07-05T10:52:33.581688+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRRGPM3N","created_at":"2026-07-05T10:52:33.581688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28938","citing_title":"EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Control","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRRGPM3NRSDIUZGTGTNOSHORTB","json":"https://pith.science/pith/YRRGPM3NRSDIUZGTGTNOSHORTB.json","graph_json":"https://pith.science/api/pith-number/YRRGPM3NRSDIUZGTGTNOSHORTB/graph.json","events_json":"https://pith.science/api/pith-number/YRRGPM3NRSDIUZGTGTNOSHORTB/events.json","paper":"https://pith.science/paper/YRRGPM3N"},"agent_actions":{"view_html":"https://pith.science/pith/YRRGPM3NRSDIUZGTGTNOSHORTB","download_json":"https://pith.science/pith/YRRGPM3NRSDIUZGTGTNOSHORTB.json","view_paper":"https://pith.science/paper/YRRGPM3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16016&json=true","fetch_graph":"https://pith.science/api/pith-number/YRRGPM3NRSDIUZGTGTNOSHORTB/graph.json","fetch_events":"https://pith.science/api/pith-number/YRRGPM3NRSDIUZGTGTNOSHORTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRRGPM3NRSDIUZGTGTNOSHORTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRRGPM3NRSDIUZGTGTNOSHORTB/action/storage_attestation","attest_author":"https://pith.science/pith/YRRGPM3NRSDIUZGTGTNOSHORTB/action/author_attestation","sign_citation":"https://pith.science/pith/YRRGPM3NRSDIUZGTGTNOSHORTB/action/citation_signature","submit_replication":"https://pith.science/pith/YRRGPM3NRSDIUZGTGTNOSHORTB/action/replication_record"}},"created_at":"2026-07-05T10:52:33.581688+00:00","updated_at":"2026-07-05T10:52:33.581688+00:00"}