{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VIVJMFQVSBIYOKJF2IYPZ37TZW","short_pith_number":"pith:VIVJMFQV","schema_version":"1.0","canonical_sha256":"aa2a9616159051872925d230fceff3cd972172826452b5ac7cb00f6463d639fa","source":{"kind":"arxiv","id":"2410.03936","version":2},"attestation_state":"computed","paper":{"title":"Learning Truncated Causal History Model for Video Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amirhosein Ghasemabadi, Di Niu, Mohammad Salameh, Muhammad Kamran Janjua","submitted_at":"2024-10-04T21:31:02Z","abstract_excerpt":"One key challenge to video restoration is to model the transition dynamics of video frames governed by motion. In this work, we propose TURTLE to learn the truncated causal history model for efficient and high-performing video restoration. Unlike traditional methods that process a range of contextual frames in parallel, TURTLE enhances efficiency by storing and summarizing a truncated history of the input frame latent representation into an evolving historical state. This is achieved through a sophisticated similarity-based retrieval mechanism that implicitly accounts for inter-frame motion an"},"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":"2410.03936","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T21:31:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"867e70aaa4e4fe995548fb5c71ae1783891756c990ebee957df93ca748dd3043","abstract_canon_sha256":"4b4c74ae02167f048dfc0e8e8957608facb60fbd3fa97279422dc0d04eea3692"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:48.814141Z","signature_b64":"UxG2IYgQttnlwlujlhEcrPj90E++W4hV3gngKtIsJBdEELVsR2qSqqW0eR6RwJ+iYx9WrIBIPBG9QNLlBw5rDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa2a9616159051872925d230fceff3cd972172826452b5ac7cb00f6463d639fa","last_reissued_at":"2026-07-05T09:20:48.813654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:48.813654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Truncated Causal History Model for Video Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amirhosein Ghasemabadi, Di Niu, Mohammad Salameh, Muhammad Kamran Janjua","submitted_at":"2024-10-04T21:31:02Z","abstract_excerpt":"One key challenge to video restoration is to model the transition dynamics of video frames governed by motion. In this work, we propose TURTLE to learn the truncated causal history model for efficient and high-performing video restoration. Unlike traditional methods that process a range of contextual frames in parallel, TURTLE enhances efficiency by storing and summarizing a truncated history of the input frame latent representation into an evolving historical state. This is achieved through a sophisticated similarity-based retrieval mechanism that implicitly accounts for inter-frame motion an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03936","kind":"arxiv","version":2},"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/2410.03936/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":"2410.03936","created_at":"2026-07-05T09:20:48.813717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03936v2","created_at":"2026-07-05T09:20:48.813717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03936","created_at":"2026-07-05T09:20:48.813717+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIVJMFQVSBIY","created_at":"2026-07-05T09:20:48.813717+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIVJMFQVSBIYOKJF","created_at":"2026-07-05T09:20:48.813717+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIVJMFQV","created_at":"2026-07-05T09:20:48.813717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.09228","citing_title":"Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportation","ref_index":188,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VIVJMFQVSBIYOKJF2IYPZ37TZW","json":"https://pith.science/pith/VIVJMFQVSBIYOKJF2IYPZ37TZW.json","graph_json":"https://pith.science/api/pith-number/VIVJMFQVSBIYOKJF2IYPZ37TZW/graph.json","events_json":"https://pith.science/api/pith-number/VIVJMFQVSBIYOKJF2IYPZ37TZW/events.json","paper":"https://pith.science/paper/VIVJMFQV"},"agent_actions":{"view_html":"https://pith.science/pith/VIVJMFQVSBIYOKJF2IYPZ37TZW","download_json":"https://pith.science/pith/VIVJMFQVSBIYOKJF2IYPZ37TZW.json","view_paper":"https://pith.science/paper/VIVJMFQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03936&json=true","fetch_graph":"https://pith.science/api/pith-number/VIVJMFQVSBIYOKJF2IYPZ37TZW/graph.json","fetch_events":"https://pith.science/api/pith-number/VIVJMFQVSBIYOKJF2IYPZ37TZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIVJMFQVSBIYOKJF2IYPZ37TZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIVJMFQVSBIYOKJF2IYPZ37TZW/action/storage_attestation","attest_author":"https://pith.science/pith/VIVJMFQVSBIYOKJF2IYPZ37TZW/action/author_attestation","sign_citation":"https://pith.science/pith/VIVJMFQVSBIYOKJF2IYPZ37TZW/action/citation_signature","submit_replication":"https://pith.science/pith/VIVJMFQVSBIYOKJF2IYPZ37TZW/action/replication_record"}},"created_at":"2026-07-05T09:20:48.813717+00:00","updated_at":"2026-07-05T09:20:48.813717+00:00"}