{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VFS5I4UDDFSWKQWEVNNVD6NJTE","short_pith_number":"pith:VFS5I4UD","schema_version":"1.0","canonical_sha256":"a965d4728319656542c4ab5b51f9a999354b52848a3c1b9157f71567443f7329","source":{"kind":"arxiv","id":"2410.07093","version":2},"attestation_state":"computed","paper":{"title":"LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Laurence T. Yang, Lingteng Qiu, Shenhao Zhu, Weichao Shen, Weihao Yuan, Xiaodong Gu, Yisheng He, Yuan Dong, Zhe Li, Zilong Dong","submitted_at":"2024-10-09T17:33:03Z","abstract_excerpt":"Language plays a vital role in the realm of human motion. Existing methods have largely depended on CLIP text embeddings for motion generation, yet they fall short in effectively aligning language and motion due to CLIP's pretraining on static image-text pairs. This work introduces LaMP, a novel Language-Motion Pretraining model, which transitions from a language-vision to a more suitable language-motion latent space. It addresses key limitations by generating motion-informative text embeddings, significantly enhancing the relevance and semantics of generated motion sequences. With LaMP, we ad"},"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":"2410.07093","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:33:03Z","cross_cats_sorted":[],"title_canon_sha256":"e6b97b20ee8e9f96e5d3c31f21fff458567d538f7f33397f94af5eb689ecce97","abstract_canon_sha256":"90b518edde04488a1543757a47004664ea452ab7d10b98c32cf8ec3dceb48bf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:40.641769Z","signature_b64":"Ug2vZerxceoNZoD7LMu3Hz4qb1WrqKApmNh7cL1vxtTaTuZ97rU6Zd1XT0wJg40ub4tBB3WNNL/4sS3mfSkuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a965d4728319656542c4ab5b51f9a999354b52848a3c1b9157f71567443f7329","last_reissued_at":"2026-07-05T10:26:40.640923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:40.640923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Laurence T. Yang, Lingteng Qiu, Shenhao Zhu, Weichao Shen, Weihao Yuan, Xiaodong Gu, Yisheng He, Yuan Dong, Zhe Li, Zilong Dong","submitted_at":"2024-10-09T17:33:03Z","abstract_excerpt":"Language plays a vital role in the realm of human motion. Existing methods have largely depended on CLIP text embeddings for motion generation, yet they fall short in effectively aligning language and motion due to CLIP's pretraining on static image-text pairs. This work introduces LaMP, a novel Language-Motion Pretraining model, which transitions from a language-vision to a more suitable language-motion latent space. It addresses key limitations by generating motion-informative text embeddings, significantly enhancing the relevance and semantics of generated motion sequences. With LaMP, we ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07093","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/2410.07093/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":"2410.07093","created_at":"2026-07-05T10:26:40.641030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07093v2","created_at":"2026-07-05T10:26:40.641030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07093","created_at":"2026-07-05T10:26:40.641030+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFS5I4UDDFSW","created_at":"2026-07-05T10:26:40.641030+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFS5I4UDDFSWKQWE","created_at":"2026-07-05T10:26:40.641030+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFS5I4UD","created_at":"2026-07-05T10:26:40.641030+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07907","citing_title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2602.12370","citing_title":"LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21668","citing_title":"Encoder-Free Human Motion Understanding via Structured Motion Descriptions","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VFS5I4UDDFSWKQWEVNNVD6NJTE","json":"https://pith.science/pith/VFS5I4UDDFSWKQWEVNNVD6NJTE.json","graph_json":"https://pith.science/api/pith-number/VFS5I4UDDFSWKQWEVNNVD6NJTE/graph.json","events_json":"https://pith.science/api/pith-number/VFS5I4UDDFSWKQWEVNNVD6NJTE/events.json","paper":"https://pith.science/paper/VFS5I4UD"},"agent_actions":{"view_html":"https://pith.science/pith/VFS5I4UDDFSWKQWEVNNVD6NJTE","download_json":"https://pith.science/pith/VFS5I4UDDFSWKQWEVNNVD6NJTE.json","view_paper":"https://pith.science/paper/VFS5I4UD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07093&json=true","fetch_graph":"https://pith.science/api/pith-number/VFS5I4UDDFSWKQWEVNNVD6NJTE/graph.json","fetch_events":"https://pith.science/api/pith-number/VFS5I4UDDFSWKQWEVNNVD6NJTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFS5I4UDDFSWKQWEVNNVD6NJTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFS5I4UDDFSWKQWEVNNVD6NJTE/action/storage_attestation","attest_author":"https://pith.science/pith/VFS5I4UDDFSWKQWEVNNVD6NJTE/action/author_attestation","sign_citation":"https://pith.science/pith/VFS5I4UDDFSWKQWEVNNVD6NJTE/action/citation_signature","submit_replication":"https://pith.science/pith/VFS5I4UDDFSWKQWEVNNVD6NJTE/action/replication_record"}},"created_at":"2026-07-05T10:26:40.641030+00:00","updated_at":"2026-07-05T10:26:40.641030+00:00"}