{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HMZ3GA2XGOALAXXCLBPB47DGYP","short_pith_number":"pith:HMZ3GA2X","schema_version":"1.0","canonical_sha256":"3b33b303573380b05ee2585e1e7c66c3c37bce7a397fa4c9aafb800c7b300472","source":{"kind":"arxiv","id":"2503.13684","version":2},"attestation_state":"computed","paper":{"title":"FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxi Xie, Lei Zhang, Mengyu Wang, Minghan Li, Yichen Wu","submitted_at":"2025-03-17T19:47:41Z","abstract_excerpt":"Numerous text-to-video (T2V) editing methods have emerged recently, but the lack of a standardized benchmark for fair evaluation has led to inconsistent claims and an inability to assess model sensitivity to hyperparameters. Fine-grained video editing is crucial for enabling precise, object-level modifications while maintaining context and temporal consistency. To address this, we introduce FiVE, a Fine-grained Video Editing Benchmark for evaluating emerging diffusion and rectified flow models. Our benchmark includes 74 real-world videos and 26 generated videos, featuring 6 fine-grained editin"},"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":"2503.13684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T19:47:41Z","cross_cats_sorted":[],"title_canon_sha256":"edc473227ea9f4f08b1506fbcefab623a7fda3b2051c9c903291444a73f80f74","abstract_canon_sha256":"612ba6892e83448a13e5bd0a45da6dbbd62d860a7f5f9f2e3cfb1ccf0f4092a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:53.549799Z","signature_b64":"hVsuVZfpAHse7KZ3bmlyG2tg/FIXQbxHfL9cCVQMDoyyau89GKEoz+5YTbFkw7eDaywaqcVhf8W+YPnbMJMDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b33b303573380b05ee2585e1e7c66c3c37bce7a397fa4c9aafb800c7b300472","last_reissued_at":"2026-07-05T11:40:53.549262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:53.549262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxi Xie, Lei Zhang, Mengyu Wang, Minghan Li, Yichen Wu","submitted_at":"2025-03-17T19:47:41Z","abstract_excerpt":"Numerous text-to-video (T2V) editing methods have emerged recently, but the lack of a standardized benchmark for fair evaluation has led to inconsistent claims and an inability to assess model sensitivity to hyperparameters. Fine-grained video editing is crucial for enabling precise, object-level modifications while maintaining context and temporal consistency. To address this, we introduce FiVE, a Fine-grained Video Editing Benchmark for evaluating emerging diffusion and rectified flow models. Our benchmark includes 74 real-world videos and 26 generated videos, featuring 6 fine-grained editin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13684","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/2503.13684/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":"2503.13684","created_at":"2026-07-05T11:40:53.549327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13684v2","created_at":"2026-07-05T11:40:53.549327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13684","created_at":"2026-07-05T11:40:53.549327+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMZ3GA2XGOAL","created_at":"2026-07-05T11:40:53.549327+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMZ3GA2XGOALAXXC","created_at":"2026-07-05T11:40:53.549327+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMZ3GA2X","created_at":"2026-07-05T11:40:53.549327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21466","citing_title":"StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21466","citing_title":"StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07469","citing_title":"VideoCoF: Unified Video Editing with Temporal Reasoner","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17445","citing_title":"LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21921","citing_title":"Context Unrolling in Omni Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16272","citing_title":"VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HMZ3GA2XGOALAXXCLBPB47DGYP","json":"https://pith.science/pith/HMZ3GA2XGOALAXXCLBPB47DGYP.json","graph_json":"https://pith.science/api/pith-number/HMZ3GA2XGOALAXXCLBPB47DGYP/graph.json","events_json":"https://pith.science/api/pith-number/HMZ3GA2XGOALAXXCLBPB47DGYP/events.json","paper":"https://pith.science/paper/HMZ3GA2X"},"agent_actions":{"view_html":"https://pith.science/pith/HMZ3GA2XGOALAXXCLBPB47DGYP","download_json":"https://pith.science/pith/HMZ3GA2XGOALAXXCLBPB47DGYP.json","view_paper":"https://pith.science/paper/HMZ3GA2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13684&json=true","fetch_graph":"https://pith.science/api/pith-number/HMZ3GA2XGOALAXXCLBPB47DGYP/graph.json","fetch_events":"https://pith.science/api/pith-number/HMZ3GA2XGOALAXXCLBPB47DGYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMZ3GA2XGOALAXXCLBPB47DGYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMZ3GA2XGOALAXXCLBPB47DGYP/action/storage_attestation","attest_author":"https://pith.science/pith/HMZ3GA2XGOALAXXCLBPB47DGYP/action/author_attestation","sign_citation":"https://pith.science/pith/HMZ3GA2XGOALAXXCLBPB47DGYP/action/citation_signature","submit_replication":"https://pith.science/pith/HMZ3GA2XGOALAXXCLBPB47DGYP/action/replication_record"}},"created_at":"2026-07-05T11:40:53.549327+00:00","updated_at":"2026-07-05T11:40:53.549327+00:00"}