{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WPVBUYTSX4FE6K4DHM65DB5IUH","short_pith_number":"pith:WPVBUYTS","schema_version":"1.0","canonical_sha256":"b3ea1a6272bf0a4f2b833b3dd187a8a1d6a499bd2c9a2be128df17bdfb2f5e66","source":{"kind":"arxiv","id":"2607.24296","version":1},"attestation_state":"computed","paper":{"title":"PAC-DP: PAC-Bayesian Diffusion Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andrea Del Prete, Dian Yu, Majid Khadiv, Matteo Saveriano, Mohammad Hasan Yeganegi","submitted_at":"2026-07-27T11:43:49Z","abstract_excerpt":"Diffusion Policies (DPs) are able to perform complex manipulation tasks. However, DPs are typically trained by minimizing a denoising objective, which provides limited control over generalization in the finite-data regimes common in robotics. In this letter, we propose PAC-DP, an approach that increases the performance of DPs in robotic manipulation tasks. By modeling the DP as a Bayesian neural network, and defining a PAC-Bayes generalization bound, we derive a novel training objective that augments the standard denoising loss with a Kullback-Leibler divergence regularizer between the posteri"},"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":"2607.24296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-27T11:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"5dbc41b4e8c1d1c01058a804c1e49b47d76e664a5fa26fd29f10c9aa934f8837","abstract_canon_sha256":"2e3d6893364c494f163f036297ba63718cbf9e43df88a12c6c42517b66ba53a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:23:55.922666Z","signature_b64":"ADE1vfEzjjHFZ2dXAHdJk1iAHJvnRbs0cCUA9QSLDERMec1ogpyaDDVM5UQulMYWewx4Z62iGJ9G86F5oCD6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3ea1a6272bf0a4f2b833b3dd187a8a1d6a499bd2c9a2be128df17bdfb2f5e66","last_reissued_at":"2026-07-28T02:23:55.921850Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:23:55.921850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAC-DP: PAC-Bayesian Diffusion Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andrea Del Prete, Dian Yu, Majid Khadiv, Matteo Saveriano, Mohammad Hasan Yeganegi","submitted_at":"2026-07-27T11:43:49Z","abstract_excerpt":"Diffusion Policies (DPs) are able to perform complex manipulation tasks. However, DPs are typically trained by minimizing a denoising objective, which provides limited control over generalization in the finite-data regimes common in robotics. In this letter, we propose PAC-DP, an approach that increases the performance of DPs in robotic manipulation tasks. By modeling the DP as a Bayesian neural network, and defining a PAC-Bayes generalization bound, we derive a novel training objective that augments the standard denoising loss with a Kullback-Leibler divergence regularizer between the posteri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24296","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/2607.24296/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":"2607.24296","created_at":"2026-07-28T02:23:55.922262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24296v1","created_at":"2026-07-28T02:23:55.922262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24296","created_at":"2026-07-28T02:23:55.922262+00:00"},{"alias_kind":"pith_short_12","alias_value":"WPVBUYTSX4FE","created_at":"2026-07-28T02:23:55.922262+00:00"},{"alias_kind":"pith_short_16","alias_value":"WPVBUYTSX4FE6K4D","created_at":"2026-07-28T02:23:55.922262+00:00"},{"alias_kind":"pith_short_8","alias_value":"WPVBUYTS","created_at":"2026-07-28T02:23:55.922262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WPVBUYTSX4FE6K4DHM65DB5IUH","json":"https://pith.science/pith/WPVBUYTSX4FE6K4DHM65DB5IUH.json","graph_json":"https://pith.science/api/pith-number/WPVBUYTSX4FE6K4DHM65DB5IUH/graph.json","events_json":"https://pith.science/api/pith-number/WPVBUYTSX4FE6K4DHM65DB5IUH/events.json","paper":"https://pith.science/paper/WPVBUYTS"},"agent_actions":{"view_html":"https://pith.science/pith/WPVBUYTSX4FE6K4DHM65DB5IUH","download_json":"https://pith.science/pith/WPVBUYTSX4FE6K4DHM65DB5IUH.json","view_paper":"https://pith.science/paper/WPVBUYTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24296&json=true","fetch_graph":"https://pith.science/api/pith-number/WPVBUYTSX4FE6K4DHM65DB5IUH/graph.json","fetch_events":"https://pith.science/api/pith-number/WPVBUYTSX4FE6K4DHM65DB5IUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WPVBUYTSX4FE6K4DHM65DB5IUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WPVBUYTSX4FE6K4DHM65DB5IUH/action/storage_attestation","attest_author":"https://pith.science/pith/WPVBUYTSX4FE6K4DHM65DB5IUH/action/author_attestation","sign_citation":"https://pith.science/pith/WPVBUYTSX4FE6K4DHM65DB5IUH/action/citation_signature","submit_replication":"https://pith.science/pith/WPVBUYTSX4FE6K4DHM65DB5IUH/action/replication_record"}},"created_at":"2026-07-28T02:23:55.922262+00:00","updated_at":"2026-07-28T02:23:55.922262+00:00"}