{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EHHV4BHTQH7FVFT26IGAA3WSVB","short_pith_number":"pith:EHHV4BHT","schema_version":"1.0","canonical_sha256":"21cf5e04f381fe5a967af20c006ed2a87e346af9ac060aa65958ca5a28a2a513","source":{"kind":"arxiv","id":"2411.16805","version":4},"attestation_state":"computed","paper":{"title":"Human Motion Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Feng Zhou, Jenq-Neng Hwang, Jianhao Wang, Ju Dai, Lei Li, Sen Jia, Tianfang Zhang, Zhongyu Jiang, Zongkai Wu","submitted_at":"2024-11-25T14:38:43Z","abstract_excerpt":"This paper presents LLaMo (Large Language and Human Motion Assistant), a multimodal framework for human motion instruction tuning. In contrast to conventional instruction-tuning approaches that convert non-linguistic inputs, such as video or motion sequences, into language tokens, LLaMo retains motion in its native form for instruction tuning. This method preserves motion-specific details that are often diminished in tokenization, thereby improving the model's ability to interpret complex human behaviors. By processing both video and motion data alongside textual inputs, LLaMo enables a flexib"},"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":"2411.16805","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-25T14:38:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8bd6818ef29770faa29480949f36915a7da242778b815bdc65311b803374d0e9","abstract_canon_sha256":"61f680b2c5e260afd2ec5b738770dfe49a7ab8a37b1656910f49534ce063ac4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:23.223869Z","signature_b64":"G/6faeVNztLYaGiWnhD5kKZckWoR/2UmiIOXuqePnyhPP2DppmF/gTrK6BpPnBW2bEVCrCxLtazRjDyAh2XrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21cf5e04f381fe5a967af20c006ed2a87e346af9ac060aa65958ca5a28a2a513","last_reissued_at":"2026-07-05T10:39:23.223384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:23.223384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human Motion Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Feng Zhou, Jenq-Neng Hwang, Jianhao Wang, Ju Dai, Lei Li, Sen Jia, Tianfang Zhang, Zhongyu Jiang, Zongkai Wu","submitted_at":"2024-11-25T14:38:43Z","abstract_excerpt":"This paper presents LLaMo (Large Language and Human Motion Assistant), a multimodal framework for human motion instruction tuning. In contrast to conventional instruction-tuning approaches that convert non-linguistic inputs, such as video or motion sequences, into language tokens, LLaMo retains motion in its native form for instruction tuning. This method preserves motion-specific details that are often diminished in tokenization, thereby improving the model's ability to interpret complex human behaviors. By processing both video and motion data alongside textual inputs, LLaMo enables a flexib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16805","kind":"arxiv","version":4},"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/2411.16805/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":"2411.16805","created_at":"2026-07-05T10:39:23.223443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16805v4","created_at":"2026-07-05T10:39:23.223443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16805","created_at":"2026-07-05T10:39:23.223443+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHHV4BHTQH7F","created_at":"2026-07-05T10:39:23.223443+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHHV4BHTQH7FVFT2","created_at":"2026-07-05T10:39:23.223443+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHHV4BHT","created_at":"2026-07-05T10:39:23.223443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22862","citing_title":"Chains That See, Answers That Don't: A Multi-Aspect Evaluation Recipe for Forced Chain-of-Thought on Video-MME","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHHV4BHTQH7FVFT26IGAA3WSVB","json":"https://pith.science/pith/EHHV4BHTQH7FVFT26IGAA3WSVB.json","graph_json":"https://pith.science/api/pith-number/EHHV4BHTQH7FVFT26IGAA3WSVB/graph.json","events_json":"https://pith.science/api/pith-number/EHHV4BHTQH7FVFT26IGAA3WSVB/events.json","paper":"https://pith.science/paper/EHHV4BHT"},"agent_actions":{"view_html":"https://pith.science/pith/EHHV4BHTQH7FVFT26IGAA3WSVB","download_json":"https://pith.science/pith/EHHV4BHTQH7FVFT26IGAA3WSVB.json","view_paper":"https://pith.science/paper/EHHV4BHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16805&json=true","fetch_graph":"https://pith.science/api/pith-number/EHHV4BHTQH7FVFT26IGAA3WSVB/graph.json","fetch_events":"https://pith.science/api/pith-number/EHHV4BHTQH7FVFT26IGAA3WSVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHHV4BHTQH7FVFT26IGAA3WSVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHHV4BHTQH7FVFT26IGAA3WSVB/action/storage_attestation","attest_author":"https://pith.science/pith/EHHV4BHTQH7FVFT26IGAA3WSVB/action/author_attestation","sign_citation":"https://pith.science/pith/EHHV4BHTQH7FVFT26IGAA3WSVB/action/citation_signature","submit_replication":"https://pith.science/pith/EHHV4BHTQH7FVFT26IGAA3WSVB/action/replication_record"}},"created_at":"2026-07-05T10:39:23.223443+00:00","updated_at":"2026-07-05T10:39:23.223443+00:00"}