{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HTBI2JNVF22H2LHRGSRS7KUDYH","short_pith_number":"pith:HTBI2JNV","schema_version":"1.0","canonical_sha256":"3cc28d25b52eb47d2cf134a32faa83c1e49e9e2464283b0c08b7f424f1642b91","source":{"kind":"arxiv","id":"2211.15603","version":3},"attestation_state":"computed","paper":{"title":"Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Ravi Kiran Sarvadevabhatla, Sai Shashank Kalakonda, Shubh Maheshwari","submitted_at":"2022-11-28T17:57:48Z","abstract_excerpt":"We introduce Action-GPT, a plug-and-play framework for incorporating Large Language Models (LLMs) into text-based action generation models. Action phrases in current motion capture datasets contain minimal and to-the-point information. By carefully crafting prompts for LLMs, we generate richer and fine-grained descriptions of the action. We show that utilizing these detailed descriptions instead of the original action phrases leads to better alignment of text and motion spaces. We introduce a generic approach compatible with stochastic (e.g. VAE-based) and deterministic (e.g. MotionCLIP) text-"},"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":"2211.15603","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T17:57:48Z","cross_cats_sorted":["cs.GR","cs.MM"],"title_canon_sha256":"b7cbbf3d6d4a479033ce6abebf346e729f23b8e533a50a5a0525ce68a707e210","abstract_canon_sha256":"9cc123b8b251ca10c1786c5071c94976e4c3cd825bb02b3efc66dd5de4498a75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:43.617162Z","signature_b64":"Ay1wd/J9LEv9V5tdxGG1ndw5WY3dYQQE/KkwO2x27a/ZpvAcaVZhV5cK0tTotObkjRMzCqioBnkNv6bY7fYYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cc28d25b52eb47d2cf134a32faa83c1e49e9e2464283b0c08b7f424f1642b91","last_reissued_at":"2026-07-05T05:48:43.616738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:43.616738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Ravi Kiran Sarvadevabhatla, Sai Shashank Kalakonda, Shubh Maheshwari","submitted_at":"2022-11-28T17:57:48Z","abstract_excerpt":"We introduce Action-GPT, a plug-and-play framework for incorporating Large Language Models (LLMs) into text-based action generation models. Action phrases in current motion capture datasets contain minimal and to-the-point information. By carefully crafting prompts for LLMs, we generate richer and fine-grained descriptions of the action. We show that utilizing these detailed descriptions instead of the original action phrases leads to better alignment of text and motion spaces. We introduce a generic approach compatible with stochastic (e.g. VAE-based) and deterministic (e.g. MotionCLIP) text-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15603","kind":"arxiv","version":3},"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/2211.15603/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":"2211.15603","created_at":"2026-07-05T05:48:43.616794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15603v3","created_at":"2026-07-05T05:48:43.616794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15603","created_at":"2026-07-05T05:48:43.616794+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTBI2JNVF22H","created_at":"2026-07-05T05:48:43.616794+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTBI2JNVF22H2LHR","created_at":"2026-07-05T05:48:43.616794+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTBI2JNV","created_at":"2026-07-05T05:48:43.616794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06843","citing_title":"Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01743","citing_title":"InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTBI2JNVF22H2LHRGSRS7KUDYH","json":"https://pith.science/pith/HTBI2JNVF22H2LHRGSRS7KUDYH.json","graph_json":"https://pith.science/api/pith-number/HTBI2JNVF22H2LHRGSRS7KUDYH/graph.json","events_json":"https://pith.science/api/pith-number/HTBI2JNVF22H2LHRGSRS7KUDYH/events.json","paper":"https://pith.science/paper/HTBI2JNV"},"agent_actions":{"view_html":"https://pith.science/pith/HTBI2JNVF22H2LHRGSRS7KUDYH","download_json":"https://pith.science/pith/HTBI2JNVF22H2LHRGSRS7KUDYH.json","view_paper":"https://pith.science/paper/HTBI2JNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15603&json=true","fetch_graph":"https://pith.science/api/pith-number/HTBI2JNVF22H2LHRGSRS7KUDYH/graph.json","fetch_events":"https://pith.science/api/pith-number/HTBI2JNVF22H2LHRGSRS7KUDYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTBI2JNVF22H2LHRGSRS7KUDYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTBI2JNVF22H2LHRGSRS7KUDYH/action/storage_attestation","attest_author":"https://pith.science/pith/HTBI2JNVF22H2LHRGSRS7KUDYH/action/author_attestation","sign_citation":"https://pith.science/pith/HTBI2JNVF22H2LHRGSRS7KUDYH/action/citation_signature","submit_replication":"https://pith.science/pith/HTBI2JNVF22H2LHRGSRS7KUDYH/action/replication_record"}},"created_at":"2026-07-05T05:48:43.616794+00:00","updated_at":"2026-07-05T05:48:43.616794+00:00"}