{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3BXAMRBPUOX4YTUYTK4GOJFEL2","short_pith_number":"pith:3BXAMRBP","schema_version":"1.0","canonical_sha256":"d86e06442fa3afcc4e989ab86724a45e97db25f3ef064a44b757cd3129a5e140","source":{"kind":"arxiv","id":"2501.16551","version":1},"attestation_state":"computed","paper":{"title":"PackDiT: Joint Human Motion and Text Generation via Mutual Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Yen Yang, Hsiang-Wei Huang, Jenq-Neng Hwang, Wenhao Chai, Zhongyu Jiang, Zhuoran Zhou","submitted_at":"2025-01-27T22:51:45Z","abstract_excerpt":"Human motion generation has advanced markedly with the advent of diffusion models. Most recent studies have concentrated on generating motion sequences based on text prompts, commonly referred to as text-to-motion generation. However, the bidirectional generation of motion and text, enabling tasks such as motion-to-text alongside text-to-motion, has been largely unexplored. This capability is essential for aligning diverse modalities and supports unconditional generation. In this paper, we introduce PackDiT, the first diffusion-based generative model capable of performing various tasks simulta"},"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":"2501.16551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T22:51:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f1130f915972e3bad4cf36c2dd2b155cc063aba3a4811b5aa9a24327a859f2bc","abstract_canon_sha256":"efcd6d7f8acaa413b0de8039fff7a1b60509392b2813884db76c0e978c10e8c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:15.041940Z","signature_b64":"G6qGW6Rz3kGAPuSJTdx/rSgPNBST4wHTlWE3E0MKt82dRwx4TCBVm7Lxx6kJKx7PLodkUyxRA+PR7f0JZbtjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d86e06442fa3afcc4e989ab86724a45e97db25f3ef064a44b757cd3129a5e140","last_reissued_at":"2026-07-05T10:06:15.041427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:15.041427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PackDiT: Joint Human Motion and Text Generation via Mutual Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Yen Yang, Hsiang-Wei Huang, Jenq-Neng Hwang, Wenhao Chai, Zhongyu Jiang, Zhuoran Zhou","submitted_at":"2025-01-27T22:51:45Z","abstract_excerpt":"Human motion generation has advanced markedly with the advent of diffusion models. Most recent studies have concentrated on generating motion sequences based on text prompts, commonly referred to as text-to-motion generation. However, the bidirectional generation of motion and text, enabling tasks such as motion-to-text alongside text-to-motion, has been largely unexplored. This capability is essential for aligning diverse modalities and supports unconditional generation. In this paper, we introduce PackDiT, the first diffusion-based generative model capable of performing various tasks simulta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16551","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/2501.16551/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":"2501.16551","created_at":"2026-07-05T10:06:15.041485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16551v1","created_at":"2026-07-05T10:06:15.041485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16551","created_at":"2026-07-05T10:06:15.041485+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BXAMRBPUOX4","created_at":"2026-07-05T10:06:15.041485+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BXAMRBPUOX4YTUY","created_at":"2026-07-05T10:06:15.041485+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BXAMRBP","created_at":"2026-07-05T10:06:15.041485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03191","citing_title":"Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward","ref_index":221,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3BXAMRBPUOX4YTUYTK4GOJFEL2","json":"https://pith.science/pith/3BXAMRBPUOX4YTUYTK4GOJFEL2.json","graph_json":"https://pith.science/api/pith-number/3BXAMRBPUOX4YTUYTK4GOJFEL2/graph.json","events_json":"https://pith.science/api/pith-number/3BXAMRBPUOX4YTUYTK4GOJFEL2/events.json","paper":"https://pith.science/paper/3BXAMRBP"},"agent_actions":{"view_html":"https://pith.science/pith/3BXAMRBPUOX4YTUYTK4GOJFEL2","download_json":"https://pith.science/pith/3BXAMRBPUOX4YTUYTK4GOJFEL2.json","view_paper":"https://pith.science/paper/3BXAMRBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16551&json=true","fetch_graph":"https://pith.science/api/pith-number/3BXAMRBPUOX4YTUYTK4GOJFEL2/graph.json","fetch_events":"https://pith.science/api/pith-number/3BXAMRBPUOX4YTUYTK4GOJFEL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BXAMRBPUOX4YTUYTK4GOJFEL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BXAMRBPUOX4YTUYTK4GOJFEL2/action/storage_attestation","attest_author":"https://pith.science/pith/3BXAMRBPUOX4YTUYTK4GOJFEL2/action/author_attestation","sign_citation":"https://pith.science/pith/3BXAMRBPUOX4YTUYTK4GOJFEL2/action/citation_signature","submit_replication":"https://pith.science/pith/3BXAMRBPUOX4YTUYTK4GOJFEL2/action/replication_record"}},"created_at":"2026-07-05T10:06:15.041485+00:00","updated_at":"2026-07-05T10:06:15.041485+00:00"}