{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HB35ZG56M25SEOUWE232OSJO66","short_pith_number":"pith:HB35ZG56","schema_version":"1.0","canonical_sha256":"3877dc9bbe66bb223a9626b7a7492ef78ec65a57d354719961c99e2fc2b19c85","source":{"kind":"arxiv","id":"2504.02478","version":1},"attestation_state":"computed","paper":{"title":"MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bizhu Wu, Jianfeng Ren, Jinheng Xie, Keming Shen, Linlin Shen, Rong Qu, Ruibin Bai, Zhe Kong","submitted_at":"2025-04-03T10:53:41Z","abstract_excerpt":"Recent motion-aware large language models have demonstrated promising potential in unifying motion comprehension and generation. However, existing approaches primarily focus on coarse-grained motion-text modeling, where text describes the overall semantics of an entire motion sequence in just a few words. This limits their ability to handle fine-grained motion-relevant tasks, such as understanding and controlling the movements of specific body parts. To overcome this limitation, we pioneer MG-MotionLLM, a unified motion-language model for multi-granular motion comprehension and generation. We "},"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":"2504.02478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T10:53:41Z","cross_cats_sorted":[],"title_canon_sha256":"a55ab1bcdf093b8163374d9dbf85309b301f456d0368d91c9c22e52b84f20872","abstract_canon_sha256":"ae8286a4e51fd415ae4b254afe28c6b4603d01c4d0ec81c6411ebacd02a145cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:57.759533Z","signature_b64":"+N2uh8Q/GrPL+IBa1uwuDsR4a0hJj/MQrJ6RPxfgr7bDPuwIYuTFULeL4IjoQh0bdsy4YMy3o5VTBQSYVz0mBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3877dc9bbe66bb223a9626b7a7492ef78ec65a57d354719961c99e2fc2b19c85","last_reissued_at":"2026-07-05T10:43:57.759031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:57.759031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bizhu Wu, Jianfeng Ren, Jinheng Xie, Keming Shen, Linlin Shen, Rong Qu, Ruibin Bai, Zhe Kong","submitted_at":"2025-04-03T10:53:41Z","abstract_excerpt":"Recent motion-aware large language models have demonstrated promising potential in unifying motion comprehension and generation. However, existing approaches primarily focus on coarse-grained motion-text modeling, where text describes the overall semantics of an entire motion sequence in just a few words. This limits their ability to handle fine-grained motion-relevant tasks, such as understanding and controlling the movements of specific body parts. To overcome this limitation, we pioneer MG-MotionLLM, a unified motion-language model for multi-granular motion comprehension and generation. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02478","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/2504.02478/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":"2504.02478","created_at":"2026-07-05T10:43:57.759089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02478v1","created_at":"2026-07-05T10:43:57.759089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02478","created_at":"2026-07-05T10:43:57.759089+00:00"},{"alias_kind":"pith_short_12","alias_value":"HB35ZG56M25S","created_at":"2026-07-05T10:43:57.759089+00:00"},{"alias_kind":"pith_short_16","alias_value":"HB35ZG56M25SEOUW","created_at":"2026-07-05T10:43:57.759089+00:00"},{"alias_kind":"pith_short_8","alias_value":"HB35ZG56","created_at":"2026-07-05T10:43:57.759089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04773","citing_title":"NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02908","citing_title":"SentiAvatar: Towards Expressive and Interactive Digital Humans","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HB35ZG56M25SEOUWE232OSJO66","json":"https://pith.science/pith/HB35ZG56M25SEOUWE232OSJO66.json","graph_json":"https://pith.science/api/pith-number/HB35ZG56M25SEOUWE232OSJO66/graph.json","events_json":"https://pith.science/api/pith-number/HB35ZG56M25SEOUWE232OSJO66/events.json","paper":"https://pith.science/paper/HB35ZG56"},"agent_actions":{"view_html":"https://pith.science/pith/HB35ZG56M25SEOUWE232OSJO66","download_json":"https://pith.science/pith/HB35ZG56M25SEOUWE232OSJO66.json","view_paper":"https://pith.science/paper/HB35ZG56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02478&json=true","fetch_graph":"https://pith.science/api/pith-number/HB35ZG56M25SEOUWE232OSJO66/graph.json","fetch_events":"https://pith.science/api/pith-number/HB35ZG56M25SEOUWE232OSJO66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HB35ZG56M25SEOUWE232OSJO66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HB35ZG56M25SEOUWE232OSJO66/action/storage_attestation","attest_author":"https://pith.science/pith/HB35ZG56M25SEOUWE232OSJO66/action/author_attestation","sign_citation":"https://pith.science/pith/HB35ZG56M25SEOUWE232OSJO66/action/citation_signature","submit_replication":"https://pith.science/pith/HB35ZG56M25SEOUWE232OSJO66/action/replication_record"}},"created_at":"2026-07-05T10:43:57.759089+00:00","updated_at":"2026-07-05T10:43:57.759089+00:00"}