{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E6CZWARP4WSTVYVEUW3WWLBF2H","short_pith_number":"pith:E6CZWARP","schema_version":"1.0","canonical_sha256":"27859b022fe5a53ae2a4a5b76b2c25d1fe9bbe8402bcffbf740732eb8d9a8257","source":{"kind":"arxiv","id":"2403.13900","version":2},"attestation_state":"computed","paper":{"title":"CoMo: Controllable Motion Generation through Language Guided Pose Code Editing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chris Callison-Burch, Lingjie Liu, Mark Yatskar, Weilin Wan, Yiming Huang, Yue Yang","submitted_at":"2024-03-20T18:11:10Z","abstract_excerpt":"Text-to-motion models excel at efficient human motion generation, but existing approaches lack fine-grained controllability over the generation process. Consequently, modifying subtle postures within a motion or inserting new actions at specific moments remains a challenge, limiting the applicability of these methods in diverse scenarios. In light of these challenges, we introduce CoMo, a Controllable Motion generation model, adept at accurately generating and editing motions by leveraging the knowledge priors of large language models (LLMs). Specifically, CoMo decomposes motions into discrete"},"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":"2403.13900","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T18:11:10Z","cross_cats_sorted":[],"title_canon_sha256":"9fe7e01bd949f3f3128cac7abdfed9958d52bada7edc956fc1e47688bc1af366","abstract_canon_sha256":"1e0d6852366cd676ab570b58a85cf86aabdffb7652e034b2f2fe481ce2894172"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:03.516848Z","signature_b64":"rP/6oJ2kPg7uGgXfYXObnLPQOXKNllYcDvvy1y1pjovs0TL5aztcoXrjXN4AnPptq1/8YduJgCV9QJ5sdamWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27859b022fe5a53ae2a4a5b76b2c25d1fe9bbe8402bcffbf740732eb8d9a8257","last_reissued_at":"2026-07-05T09:09:03.516357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:03.516357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoMo: Controllable Motion Generation through Language Guided Pose Code Editing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chris Callison-Burch, Lingjie Liu, Mark Yatskar, Weilin Wan, Yiming Huang, Yue Yang","submitted_at":"2024-03-20T18:11:10Z","abstract_excerpt":"Text-to-motion models excel at efficient human motion generation, but existing approaches lack fine-grained controllability over the generation process. Consequently, modifying subtle postures within a motion or inserting new actions at specific moments remains a challenge, limiting the applicability of these methods in diverse scenarios. In light of these challenges, we introduce CoMo, a Controllable Motion generation model, adept at accurately generating and editing motions by leveraging the knowledge priors of large language models (LLMs). Specifically, CoMo decomposes motions into discrete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13900","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/2403.13900/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":"2403.13900","created_at":"2026-07-05T09:09:03.516424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13900v2","created_at":"2026-07-05T09:09:03.516424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13900","created_at":"2026-07-05T09:09:03.516424+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6CZWARP4WST","created_at":"2026-07-05T09:09:03.516424+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6CZWARP4WSTVYVE","created_at":"2026-07-05T09:09:03.516424+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6CZWARP","created_at":"2026-07-05T09:09:03.516424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06590","citing_title":"MOST: Motion Diffusion Model for Rare Text via Temporal Clip Banzhaf Interaction","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6CZWARP4WSTVYVEUW3WWLBF2H","json":"https://pith.science/pith/E6CZWARP4WSTVYVEUW3WWLBF2H.json","graph_json":"https://pith.science/api/pith-number/E6CZWARP4WSTVYVEUW3WWLBF2H/graph.json","events_json":"https://pith.science/api/pith-number/E6CZWARP4WSTVYVEUW3WWLBF2H/events.json","paper":"https://pith.science/paper/E6CZWARP"},"agent_actions":{"view_html":"https://pith.science/pith/E6CZWARP4WSTVYVEUW3WWLBF2H","download_json":"https://pith.science/pith/E6CZWARP4WSTVYVEUW3WWLBF2H.json","view_paper":"https://pith.science/paper/E6CZWARP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13900&json=true","fetch_graph":"https://pith.science/api/pith-number/E6CZWARP4WSTVYVEUW3WWLBF2H/graph.json","fetch_events":"https://pith.science/api/pith-number/E6CZWARP4WSTVYVEUW3WWLBF2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6CZWARP4WSTVYVEUW3WWLBF2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6CZWARP4WSTVYVEUW3WWLBF2H/action/storage_attestation","attest_author":"https://pith.science/pith/E6CZWARP4WSTVYVEUW3WWLBF2H/action/author_attestation","sign_citation":"https://pith.science/pith/E6CZWARP4WSTVYVEUW3WWLBF2H/action/citation_signature","submit_replication":"https://pith.science/pith/E6CZWARP4WSTVYVEUW3WWLBF2H/action/replication_record"}},"created_at":"2026-07-05T09:09:03.516424+00:00","updated_at":"2026-07-05T09:09:03.516424+00:00"}