{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NSA27YZLRX6J6YHGKTLPCIKY4B","short_pith_number":"pith:NSA27YZL","schema_version":"1.0","canonical_sha256":"6c81afe32b8dfc9f60e654d6f12158e062f54d7397fe8a36117eb7cf82fa73a2","source":{"kind":"arxiv","id":"2507.23188","version":1},"attestation_state":"computed","paper":{"title":"Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kangning Yin, Mingyuan Zhang, Shihao Zou, Shiyao Yu, Weixin Si, Zheng Tian, Zi-An Wang","submitted_at":"2025-07-31T01:59:38Z","abstract_excerpt":"Motion retrieval is crucial for motion acquisition, offering superior precision, realism, controllability, and editability compared to motion generation. Existing approaches leverage contrastive learning to construct a unified embedding space for motion retrieval from text or visual modality. However, these methods lack a more intuitive and user-friendly interaction mode and often overlook the sequential representation of most modalities for improved retrieval performance. To address these limitations, we propose a framework that aligns four modalities -- text, audio, video, and motion -- with"},"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":"2507.23188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T01:59:38Z","cross_cats_sorted":[],"title_canon_sha256":"10109dc2de4b668cc3c461a2d5ca9293036abb0d3b7acf78047edcc93bd84e61","abstract_canon_sha256":"26c0a3adc0717a655de17c241ad89f439bfd79616fce4065e33e0c64c060805a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:07.033440Z","signature_b64":"zJBzv+2te1vY8dVtT05XT++MkB8qCH/fv/c5Q48ucmU64mavLUcbXV6IhYH48sMyp7zjNR9j6Ab9sV1UvNXEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c81afe32b8dfc9f60e654d6f12158e062f54d7397fe8a36117eb7cf82fa73a2","last_reissued_at":"2026-07-05T11:46:07.032947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:07.032947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kangning Yin, Mingyuan Zhang, Shihao Zou, Shiyao Yu, Weixin Si, Zheng Tian, Zi-An Wang","submitted_at":"2025-07-31T01:59:38Z","abstract_excerpt":"Motion retrieval is crucial for motion acquisition, offering superior precision, realism, controllability, and editability compared to motion generation. Existing approaches leverage contrastive learning to construct a unified embedding space for motion retrieval from text or visual modality. However, these methods lack a more intuitive and user-friendly interaction mode and often overlook the sequential representation of most modalities for improved retrieval performance. To address these limitations, we propose a framework that aligns four modalities -- text, audio, video, and motion -- with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23188","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/2507.23188/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":"2507.23188","created_at":"2026-07-05T11:46:07.033009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23188v1","created_at":"2026-07-05T11:46:07.033009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23188","created_at":"2026-07-05T11:46:07.033009+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSA27YZLRX6J","created_at":"2026-07-05T11:46:07.033009+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSA27YZLRX6J6YHG","created_at":"2026-07-05T11:46:07.033009+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSA27YZL","created_at":"2026-07-05T11:46:07.033009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NSA27YZLRX6J6YHGKTLPCIKY4B","json":"https://pith.science/pith/NSA27YZLRX6J6YHGKTLPCIKY4B.json","graph_json":"https://pith.science/api/pith-number/NSA27YZLRX6J6YHGKTLPCIKY4B/graph.json","events_json":"https://pith.science/api/pith-number/NSA27YZLRX6J6YHGKTLPCIKY4B/events.json","paper":"https://pith.science/paper/NSA27YZL"},"agent_actions":{"view_html":"https://pith.science/pith/NSA27YZLRX6J6YHGKTLPCIKY4B","download_json":"https://pith.science/pith/NSA27YZLRX6J6YHGKTLPCIKY4B.json","view_paper":"https://pith.science/paper/NSA27YZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23188&json=true","fetch_graph":"https://pith.science/api/pith-number/NSA27YZLRX6J6YHGKTLPCIKY4B/graph.json","fetch_events":"https://pith.science/api/pith-number/NSA27YZLRX6J6YHGKTLPCIKY4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSA27YZLRX6J6YHGKTLPCIKY4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSA27YZLRX6J6YHGKTLPCIKY4B/action/storage_attestation","attest_author":"https://pith.science/pith/NSA27YZLRX6J6YHGKTLPCIKY4B/action/author_attestation","sign_citation":"https://pith.science/pith/NSA27YZLRX6J6YHGKTLPCIKY4B/action/citation_signature","submit_replication":"https://pith.science/pith/NSA27YZLRX6J6YHGKTLPCIKY4B/action/replication_record"}},"created_at":"2026-07-05T11:46:07.033009+00:00","updated_at":"2026-07-05T11:46:07.033009+00:00"}