{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CLKZZB3NSK7BR6D7H7WTWD4A64","short_pith_number":"pith:CLKZZB3N","schema_version":"1.0","canonical_sha256":"12d59c876d92be18f87f3fed3b0f80f733c67b430eb7770230e8cc07f954028a","source":{"kind":"arxiv","id":"2312.08895","version":1},"attestation_state":"computed","paper":{"title":"Motion Flow Matching for Human Motion Synthesis and Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Basura Fernando, Bjorn Ommer, Cees G. M. Snoek, Efstratios Gavves, Pascal Mettes, Pingchuan Ma, Vincent Tao Hu, Wenzhe Yin, Yuki M Asano, Yunlu Chen","submitted_at":"2023-12-14T12:57:35Z","abstract_excerpt":"Human motion synthesis is a fundamental task in computer animation. Recent methods based on diffusion models or GPT structure demonstrate commendable performance but exhibit drawbacks in terms of slow sampling speeds and error accumulation. In this paper, we propose \\emph{Motion Flow Matching}, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications. Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-mo"},"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":"2312.08895","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T12:57:35Z","cross_cats_sorted":[],"title_canon_sha256":"28e434c9d2ace2b51011827cf4d26ee7acbf079143f203d003851f243e18fe90","abstract_canon_sha256":"1bb441a7c3fb4ed2d1ec04481473107ca22fab4eece79870ebf2a3c30fafd4df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:11.256921Z","signature_b64":"8v+WEXG4zPQE0TCo/2tblM3fSNKfQBKRcmeUAd5wtWolejumr8P3vIVSqrBPb5spVEjhrju/VANeoR6eXeMXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12d59c876d92be18f87f3fed3b0f80f733c67b430eb7770230e8cc07f954028a","last_reissued_at":"2026-07-05T07:24:11.256442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:11.256442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motion Flow Matching for Human Motion Synthesis and Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Basura Fernando, Bjorn Ommer, Cees G. M. Snoek, Efstratios Gavves, Pascal Mettes, Pingchuan Ma, Vincent Tao Hu, Wenzhe Yin, Yuki M Asano, Yunlu Chen","submitted_at":"2023-12-14T12:57:35Z","abstract_excerpt":"Human motion synthesis is a fundamental task in computer animation. Recent methods based on diffusion models or GPT structure demonstrate commendable performance but exhibit drawbacks in terms of slow sampling speeds and error accumulation. In this paper, we propose \\emph{Motion Flow Matching}, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications. Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08895","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/2312.08895/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":"2312.08895","created_at":"2026-07-05T07:24:11.256500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08895v1","created_at":"2026-07-05T07:24:11.256500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08895","created_at":"2026-07-05T07:24:11.256500+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLKZZB3NSK7B","created_at":"2026-07-05T07:24:11.256500+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLKZZB3NSK7BR6D7","created_at":"2026-07-05T07:24:11.256500+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLKZZB3N","created_at":"2026-07-05T07:24:11.256500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19209","citing_title":"FineCombo-TTS: Collaborative and Precise Controllable Speech Synthesis Using Text Descriptions and Reference Speech","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14417","citing_title":"Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14417","citing_title":"Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23264","citing_title":"MotionHiFlow: Text-to-motion via hierarchical flow matching","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLKZZB3NSK7BR6D7H7WTWD4A64","json":"https://pith.science/pith/CLKZZB3NSK7BR6D7H7WTWD4A64.json","graph_json":"https://pith.science/api/pith-number/CLKZZB3NSK7BR6D7H7WTWD4A64/graph.json","events_json":"https://pith.science/api/pith-number/CLKZZB3NSK7BR6D7H7WTWD4A64/events.json","paper":"https://pith.science/paper/CLKZZB3N"},"agent_actions":{"view_html":"https://pith.science/pith/CLKZZB3NSK7BR6D7H7WTWD4A64","download_json":"https://pith.science/pith/CLKZZB3NSK7BR6D7H7WTWD4A64.json","view_paper":"https://pith.science/paper/CLKZZB3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08895&json=true","fetch_graph":"https://pith.science/api/pith-number/CLKZZB3NSK7BR6D7H7WTWD4A64/graph.json","fetch_events":"https://pith.science/api/pith-number/CLKZZB3NSK7BR6D7H7WTWD4A64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLKZZB3NSK7BR6D7H7WTWD4A64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLKZZB3NSK7BR6D7H7WTWD4A64/action/storage_attestation","attest_author":"https://pith.science/pith/CLKZZB3NSK7BR6D7H7WTWD4A64/action/author_attestation","sign_citation":"https://pith.science/pith/CLKZZB3NSK7BR6D7H7WTWD4A64/action/citation_signature","submit_replication":"https://pith.science/pith/CLKZZB3NSK7BR6D7H7WTWD4A64/action/replication_record"}},"created_at":"2026-07-05T07:24:11.256500+00:00","updated_at":"2026-07-05T07:24:11.256500+00:00"}