{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TOT47FNI7I6ADOCZ4FF2HFHPGX","short_pith_number":"pith:TOT47FNI","schema_version":"1.0","canonical_sha256":"9ba7cf95a8fa3c01b859e14ba394ef35c644ab7bf2a992a237dd58c43adbbca0","source":{"kind":"arxiv","id":"2503.20287","version":2},"attestation_state":"computed","paper":{"title":"InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxi Xie, Lei Zhang, Liyi Chen, Ruibin Li, Shihao Wang, Yuhui Wu","submitted_at":"2025-03-26T07:30:58Z","abstract_excerpt":"Instruction-based video editing allows effective and interactive editing of videos using only instructions without extra inputs such as masks or attributes. However, collecting high-quality training triplets (source video, edited video, instruction) is a challenging task. Existing datasets mostly consist of low-resolution, short duration, and limited amount of source videos with unsatisfactory editing quality, limiting the performance of trained editing models. In this work, we present a high-quality Instruction-based Video Editing dataset with 1M triplets, namely InsViE-1M. We first curate hi"},"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":"2503.20287","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T07:30:58Z","cross_cats_sorted":[],"title_canon_sha256":"f4e2627ae58872576d11799a4f36d869f450e7174649a5165396ff702aaae585","abstract_canon_sha256":"9f61809704de314c20eb06ad2f46d3a330f57e84820ec193dfa997204dcc0e3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:34.134682Z","signature_b64":"+g7qUxMRqG3Al0T2m4nXV/2JMp8oOVT7WVhu0CNbaDT9AGXbBi4EtioH2OgpT+bTrIGfoGYXTGPSoH6dWSnHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ba7cf95a8fa3c01b859e14ba394ef35c644ab7bf2a992a237dd58c43adbbca0","last_reissued_at":"2026-07-05T11:35:34.134233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:34.134233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxi Xie, Lei Zhang, Liyi Chen, Ruibin Li, Shihao Wang, Yuhui Wu","submitted_at":"2025-03-26T07:30:58Z","abstract_excerpt":"Instruction-based video editing allows effective and interactive editing of videos using only instructions without extra inputs such as masks or attributes. However, collecting high-quality training triplets (source video, edited video, instruction) is a challenging task. Existing datasets mostly consist of low-resolution, short duration, and limited amount of source videos with unsatisfactory editing quality, limiting the performance of trained editing models. In this work, we present a high-quality Instruction-based Video Editing dataset with 1M triplets, namely InsViE-1M. We first curate hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20287","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/2503.20287/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":"2503.20287","created_at":"2026-07-05T11:35:34.134285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20287v2","created_at":"2026-07-05T11:35:34.134285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20287","created_at":"2026-07-05T11:35:34.134285+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOT47FNI7I6A","created_at":"2026-07-05T11:35:34.134285+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOT47FNI7I6ADOCZ","created_at":"2026-07-05T11:35:34.134285+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOT47FNI","created_at":"2026-07-05T11:35:34.134285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23192","citing_title":"Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17019","citing_title":"StreamingEffect: Real-Time Human-Centric Video Effect Generation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08646","citing_title":"InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOT47FNI7I6ADOCZ4FF2HFHPGX","json":"https://pith.science/pith/TOT47FNI7I6ADOCZ4FF2HFHPGX.json","graph_json":"https://pith.science/api/pith-number/TOT47FNI7I6ADOCZ4FF2HFHPGX/graph.json","events_json":"https://pith.science/api/pith-number/TOT47FNI7I6ADOCZ4FF2HFHPGX/events.json","paper":"https://pith.science/paper/TOT47FNI"},"agent_actions":{"view_html":"https://pith.science/pith/TOT47FNI7I6ADOCZ4FF2HFHPGX","download_json":"https://pith.science/pith/TOT47FNI7I6ADOCZ4FF2HFHPGX.json","view_paper":"https://pith.science/paper/TOT47FNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20287&json=true","fetch_graph":"https://pith.science/api/pith-number/TOT47FNI7I6ADOCZ4FF2HFHPGX/graph.json","fetch_events":"https://pith.science/api/pith-number/TOT47FNI7I6ADOCZ4FF2HFHPGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOT47FNI7I6ADOCZ4FF2HFHPGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOT47FNI7I6ADOCZ4FF2HFHPGX/action/storage_attestation","attest_author":"https://pith.science/pith/TOT47FNI7I6ADOCZ4FF2HFHPGX/action/author_attestation","sign_citation":"https://pith.science/pith/TOT47FNI7I6ADOCZ4FF2HFHPGX/action/citation_signature","submit_replication":"https://pith.science/pith/TOT47FNI7I6ADOCZ4FF2HFHPGX/action/replication_record"}},"created_at":"2026-07-05T11:35:34.134285+00:00","updated_at":"2026-07-05T11:35:34.134285+00:00"}