{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6R7ARDSSLKFDWALSSOZRWGE3VX","short_pith_number":"pith:6R7ARDSS","schema_version":"1.0","canonical_sha256":"f47e088e525a8a3b017293b31b189badfd5c9899bca190108b5ac3173a5ce292","source":{"kind":"arxiv","id":"2503.14919","version":2},"attestation_state":"computed","paper":{"title":"GenM$^3$: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinni Zhou, Junyu Shi, Lijiang Liu, Qiang Nie, Yong Sun, Zhiyuan Zhang","submitted_at":"2025-03-19T05:56:52Z","abstract_excerpt":"Scaling up motion datasets is crucial to enhance motion generation capabilities. However, training on large-scale multi-source datasets introduces data heterogeneity challenges due to variations in motion content. To address this, we propose Generative Pretrained Multi-path Motion Model (GenM\\(^3\\)), a comprehensive framework designed to learn unified motion representations. GenM\\(^3\\) comprises two components: 1) a Multi-Expert VQ-VAE (MEVQ-VAE) that adapts to different dataset distributions to learn a unified discrete motion representation, and 2) a Multi-path Motion Transformer (MMT) that i"},"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":"2503.14919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T05:56:52Z","cross_cats_sorted":[],"title_canon_sha256":"a69d30d7061b2bb1685bfcc6f281570d99d23d9d5d899d8a91a643905f896fa4","abstract_canon_sha256":"8a060fc7dddcd15f35a61d78241ee671946d81ab58be8e7c302f84fec91c08ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:02.871179Z","signature_b64":"QVQTxrxiMjyXEx+v43/tEkuzUsv1lYmqkbn5W87dd+17Lr1mbvJyU1WEutyGefzP25iBmlTCr9oCAFQvYBpXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f47e088e525a8a3b017293b31b189badfd5c9899bca190108b5ac3173a5ce292","last_reissued_at":"2026-07-05T11:44:02.870724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:02.870724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenM$^3$: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinni Zhou, Junyu Shi, Lijiang Liu, Qiang Nie, Yong Sun, Zhiyuan Zhang","submitted_at":"2025-03-19T05:56:52Z","abstract_excerpt":"Scaling up motion datasets is crucial to enhance motion generation capabilities. However, training on large-scale multi-source datasets introduces data heterogeneity challenges due to variations in motion content. To address this, we propose Generative Pretrained Multi-path Motion Model (GenM\\(^3\\)), a comprehensive framework designed to learn unified motion representations. GenM\\(^3\\) comprises two components: 1) a Multi-Expert VQ-VAE (MEVQ-VAE) that adapts to different dataset distributions to learn a unified discrete motion representation, and 2) a Multi-path Motion Transformer (MMT) that i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14919","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/2503.14919/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":"2503.14919","created_at":"2026-07-05T11:44:02.870785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14919v2","created_at":"2026-07-05T11:44:02.870785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14919","created_at":"2026-07-05T11:44:02.870785+00:00"},{"alias_kind":"pith_short_12","alias_value":"6R7ARDSSLKFD","created_at":"2026-07-05T11:44:02.870785+00:00"},{"alias_kind":"pith_short_16","alias_value":"6R7ARDSSLKFDWALS","created_at":"2026-07-05T11:44:02.870785+00:00"},{"alias_kind":"pith_short_8","alias_value":"6R7ARDSS","created_at":"2026-07-05T11:44:02.870785+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21926","citing_title":"Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6R7ARDSSLKFDWALSSOZRWGE3VX","json":"https://pith.science/pith/6R7ARDSSLKFDWALSSOZRWGE3VX.json","graph_json":"https://pith.science/api/pith-number/6R7ARDSSLKFDWALSSOZRWGE3VX/graph.json","events_json":"https://pith.science/api/pith-number/6R7ARDSSLKFDWALSSOZRWGE3VX/events.json","paper":"https://pith.science/paper/6R7ARDSS"},"agent_actions":{"view_html":"https://pith.science/pith/6R7ARDSSLKFDWALSSOZRWGE3VX","download_json":"https://pith.science/pith/6R7ARDSSLKFDWALSSOZRWGE3VX.json","view_paper":"https://pith.science/paper/6R7ARDSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14919&json=true","fetch_graph":"https://pith.science/api/pith-number/6R7ARDSSLKFDWALSSOZRWGE3VX/graph.json","fetch_events":"https://pith.science/api/pith-number/6R7ARDSSLKFDWALSSOZRWGE3VX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6R7ARDSSLKFDWALSSOZRWGE3VX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6R7ARDSSLKFDWALSSOZRWGE3VX/action/storage_attestation","attest_author":"https://pith.science/pith/6R7ARDSSLKFDWALSSOZRWGE3VX/action/author_attestation","sign_citation":"https://pith.science/pith/6R7ARDSSLKFDWALSSOZRWGE3VX/action/citation_signature","submit_replication":"https://pith.science/pith/6R7ARDSSLKFDWALSSOZRWGE3VX/action/replication_record"}},"created_at":"2026-07-05T11:44:02.870785+00:00","updated_at":"2026-07-05T11:44:02.870785+00:00"}