{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NSA27YZLRX6J6YHGKTLPCIKY4B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"26c0a3adc0717a655de17c241ad89f439bfd79616fce4065e33e0c64c060805a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T01:59:38Z","title_canon_sha256":"10109dc2de4b668cc3c461a2d5ca9293036abb0d3b7acf78047edcc93bd84e61"},"schema_version":"1.0","source":{"id":"2507.23188","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23188","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23188v1","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23188","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"NSA27YZLRX6J","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"pith_short_16","alias_value":"NSA27YZLRX6J6YHG","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"pith_short_8","alias_value":"NSA27YZL","created_at":"2026-07-05T11:46:07Z"}],"graph_snapshots":[{"event_id":"sha256:a205b1c9c3d50eb7c8ab14df80401faf19dc075bc131527b0d4f16b7f51a30b0","target":"graph","created_at":"2026-07-05T11:46:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.23188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kangning Yin, Mingyuan Zhang, Shihao Zou, Shiyao Yu, Weixin Si, Zheng Tian, Zi-An Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T01:59:38Z","title":"Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23188","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5f7269bec14d49c237dc3e1b37811e283cea7a4757d20a51beec48e72e26abf7","target":"record","created_at":"2026-07-05T11:46:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"26c0a3adc0717a655de17c241ad89f439bfd79616fce4065e33e0c64c060805a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T01:59:38Z","title_canon_sha256":"10109dc2de4b668cc3c461a2d5ca9293036abb0d3b7acf78047edcc93bd84e61"},"schema_version":"1.0","source":{"id":"2507.23188","kind":"arxiv","version":1}},"canonical_sha256":"6c81afe32b8dfc9f60e654d6f12158e062f54d7397fe8a36117eb7cf82fa73a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c81afe32b8dfc9f60e654d6f12158e062f54d7397fe8a36117eb7cf82fa73a2","first_computed_at":"2026-07-05T11:46:07.032947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:07.032947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zJBzv+2te1vY8dVtT05XT++MkB8qCH/fv/c5Q48ucmU64mavLUcbXV6IhYH48sMyp7zjNR9j6Ab9sV1UvNXEBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:07.033440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23188","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f7269bec14d49c237dc3e1b37811e283cea7a4757d20a51beec48e72e26abf7","sha256:a205b1c9c3d50eb7c8ab14df80401faf19dc075bc131527b0d4f16b7f51a30b0"],"state_sha256":"4a09ea04e7c75bccde3f42031cd560a3a0290a947efec1c19263e13e3a71bee5"}