{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZFKGMMFUQ3MQ3PS2VQFIXXQND","short_pith_number":"pith:LZFKGMMF","schema_version":"1.0","canonical_sha256":"5e4aa33185a436c86df2d560545ef068c3aef873c195a048f77faea933310119","source":{"kind":"arxiv","id":"2405.03803","version":1},"attestation_state":"computed","paper":{"title":"MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabio Galasso, Giovanni Ficarra, Indro Spinelli, Luca Collorone, Massimiliano Pappa","submitted_at":"2024-05-06T19:19:20Z","abstract_excerpt":"Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability to generate various outputs from a single input, is key to their success. However, this diversity should not be unrestricted, as it may lead to unlikely generations. Instead, it should be confined within the boundaries of text-aligned and realistic generations. To address this issue, we propose MoDiPO (Motion Diffusion DPO), a novel methodology that leverages"},"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":"2405.03803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-06T19:19:20Z","cross_cats_sorted":[],"title_canon_sha256":"cd307fb50a4a4b3b02390f05334f2743633cd7a11564ba3698bd1ebb6efb2467","abstract_canon_sha256":"0d90956269fca568c74c9519dd5a9bec8bf5c14611fc10c24d2639e6b53a1e15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:10.969746Z","signature_b64":"yTvFcLxDCeWkjXzMCVQJNIdMs498y1eFZ+Q0iw0O327/XRe8CTN2qR39spifrl27B9dtamn0fro6s2lHkP2ZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4aa33185a436c86df2d560545ef068c3aef873c195a048f77faea933310119","last_reissued_at":"2026-07-05T08:16:10.969179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:10.969179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabio Galasso, Giovanni Ficarra, Indro Spinelli, Luca Collorone, Massimiliano Pappa","submitted_at":"2024-05-06T19:19:20Z","abstract_excerpt":"Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability to generate various outputs from a single input, is key to their success. However, this diversity should not be unrestricted, as it may lead to unlikely generations. Instead, it should be confined within the boundaries of text-aligned and realistic generations. To address this issue, we propose MoDiPO (Motion Diffusion DPO), a novel methodology that leverages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03803","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/2405.03803/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":"2405.03803","created_at":"2026-07-05T08:16:10.969230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03803v1","created_at":"2026-07-05T08:16:10.969230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03803","created_at":"2026-07-05T08:16:10.969230+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZFKGMMFUQ3M","created_at":"2026-07-05T08:16:10.969230+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZFKGMMFUQ3MQ3PS","created_at":"2026-07-05T08:16:10.969230+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZFKGMMF","created_at":"2026-07-05T08:16:10.969230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22894","citing_title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZFKGMMFUQ3MQ3PS2VQFIXXQND","json":"https://pith.science/pith/LZFKGMMFUQ3MQ3PS2VQFIXXQND.json","graph_json":"https://pith.science/api/pith-number/LZFKGMMFUQ3MQ3PS2VQFIXXQND/graph.json","events_json":"https://pith.science/api/pith-number/LZFKGMMFUQ3MQ3PS2VQFIXXQND/events.json","paper":"https://pith.science/paper/LZFKGMMF"},"agent_actions":{"view_html":"https://pith.science/pith/LZFKGMMFUQ3MQ3PS2VQFIXXQND","download_json":"https://pith.science/pith/LZFKGMMFUQ3MQ3PS2VQFIXXQND.json","view_paper":"https://pith.science/paper/LZFKGMMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03803&json=true","fetch_graph":"https://pith.science/api/pith-number/LZFKGMMFUQ3MQ3PS2VQFIXXQND/graph.json","fetch_events":"https://pith.science/api/pith-number/LZFKGMMFUQ3MQ3PS2VQFIXXQND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZFKGMMFUQ3MQ3PS2VQFIXXQND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZFKGMMFUQ3MQ3PS2VQFIXXQND/action/storage_attestation","attest_author":"https://pith.science/pith/LZFKGMMFUQ3MQ3PS2VQFIXXQND/action/author_attestation","sign_citation":"https://pith.science/pith/LZFKGMMFUQ3MQ3PS2VQFIXXQND/action/citation_signature","submit_replication":"https://pith.science/pith/LZFKGMMFUQ3MQ3PS2VQFIXXQND/action/replication_record"}},"created_at":"2026-07-05T08:16:10.969230+00:00","updated_at":"2026-07-05T08:16:10.969230+00:00"}