{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NVNF2P3FHJUGN32DJA36XPKM4E","short_pith_number":"pith:NVNF2P3F","schema_version":"1.0","canonical_sha256":"6d5a5d3f653a6866ef434837ebbd4ce13ca4c2f3cd7a91193a90c35e1080839c","source":{"kind":"arxiv","id":"2503.17641","version":1},"attestation_state":"computed","paper":{"title":"InstructVEdit: A Holistic Approach for Instructional Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjian Feng, Chi Zhang, Feng Yan, Jing Zhang, Lin Ma, Mingjin Zhang, Qiming Zhang, Yujie Zhong","submitted_at":"2025-03-22T04:12:20Z","abstract_excerpt":"Video editing according to instructions is a highly challenging task due to the difficulty in collecting large-scale, high-quality edited video pair data. This scarcity not only limits the availability of training data but also hinders the systematic exploration of model architectures and training strategies. While prior work has improved specific aspects of video editing (e.g., synthesizing a video dataset using image editing techniques or decomposed video editing training), a holistic framework addressing the above challenges remains underexplored. In this study, we introduce InstructVEdit, "},"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":"2503.17641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-22T04:12:20Z","cross_cats_sorted":[],"title_canon_sha256":"3fc95232a707466040ca2bc18d9f03d228fcd38124d2a31c59dbd87737879749","abstract_canon_sha256":"2c76bd4dd6d74cb850d88d466ce0f942c8cf1382f7ce6665bc81d9ba74d7ef38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:51.123482Z","signature_b64":"4yuZhbHq4gRID6XfsZbCeJ9pmEp8y4viFxBABUGMrIAmQxPPHnzp3NpIYhpHddcJALgg2OrsNkxH+ikXesPFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d5a5d3f653a6866ef434837ebbd4ce13ca4c2f3cd7a91193a90c35e1080839c","last_reissued_at":"2026-07-05T10:37:51.122580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:51.122580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructVEdit: A Holistic Approach for Instructional Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjian Feng, Chi Zhang, Feng Yan, Jing Zhang, Lin Ma, Mingjin Zhang, Qiming Zhang, Yujie Zhong","submitted_at":"2025-03-22T04:12:20Z","abstract_excerpt":"Video editing according to instructions is a highly challenging task due to the difficulty in collecting large-scale, high-quality edited video pair data. This scarcity not only limits the availability of training data but also hinders the systematic exploration of model architectures and training strategies. While prior work has improved specific aspects of video editing (e.g., synthesizing a video dataset using image editing techniques or decomposed video editing training), a holistic framework addressing the above challenges remains underexplored. In this study, we introduce InstructVEdit, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17641","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/2503.17641/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":"2503.17641","created_at":"2026-07-05T10:37:51.122676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17641v1","created_at":"2026-07-05T10:37:51.122676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17641","created_at":"2026-07-05T10:37:51.122676+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVNF2P3FHJUG","created_at":"2026-07-05T10:37:51.122676+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVNF2P3FHJUGN32D","created_at":"2026-07-05T10:37:51.122676+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVNF2P3F","created_at":"2026-07-05T10:37:51.122676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17021","citing_title":"LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NVNF2P3FHJUGN32DJA36XPKM4E","json":"https://pith.science/pith/NVNF2P3FHJUGN32DJA36XPKM4E.json","graph_json":"https://pith.science/api/pith-number/NVNF2P3FHJUGN32DJA36XPKM4E/graph.json","events_json":"https://pith.science/api/pith-number/NVNF2P3FHJUGN32DJA36XPKM4E/events.json","paper":"https://pith.science/paper/NVNF2P3F"},"agent_actions":{"view_html":"https://pith.science/pith/NVNF2P3FHJUGN32DJA36XPKM4E","download_json":"https://pith.science/pith/NVNF2P3FHJUGN32DJA36XPKM4E.json","view_paper":"https://pith.science/paper/NVNF2P3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17641&json=true","fetch_graph":"https://pith.science/api/pith-number/NVNF2P3FHJUGN32DJA36XPKM4E/graph.json","fetch_events":"https://pith.science/api/pith-number/NVNF2P3FHJUGN32DJA36XPKM4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVNF2P3FHJUGN32DJA36XPKM4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVNF2P3FHJUGN32DJA36XPKM4E/action/storage_attestation","attest_author":"https://pith.science/pith/NVNF2P3FHJUGN32DJA36XPKM4E/action/author_attestation","sign_citation":"https://pith.science/pith/NVNF2P3FHJUGN32DJA36XPKM4E/action/citation_signature","submit_replication":"https://pith.science/pith/NVNF2P3FHJUGN32DJA36XPKM4E/action/replication_record"}},"created_at":"2026-07-05T10:37:51.122676+00:00","updated_at":"2026-07-05T10:37:51.122676+00:00"}