{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XJ5F3PDSIWFUJR4MR5JGAOLPE5","short_pith_number":"pith:XJ5F3PDS","schema_version":"1.0","canonical_sha256":"ba7a5dbc72458b44c78c8f5260396f274d2e88afb00a9a1c23663e578d1ba1a1","source":{"kind":"arxiv","id":"2606.28939","version":1},"attestation_state":"computed","paper":{"title":"ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Dileep Kalathil, P. R. Kumar, Srinivas Shakkottai, Tzu-Hsiang Lin","submitted_at":"2026-06-27T14:23:21Z","abstract_excerpt":"Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into task failure. Existing methods address this either by expanding the training distribution through expert corrections or synthetic augmentation, or by steering a frozen policy at test time with guidance from a learned model. The former can be expensive or assumption-dependent, while the latter discards the corrected trajectories after execution. We introduce ReGuide, a self-improving framework that treats guided rollouts as reusable on-policy re"},"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":"2606.28939","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T14:23:21Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"859ede53a61d7df1b374b8d5db79a7a41d70b471202ad6bce1aeab197469be53","abstract_canon_sha256":"4ed077a68bcafc3e808b88ffe2ca90270bd272d98b55f8f376572e2cd4c9d125"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:46.377311Z","signature_b64":"vUPCKq1YzqaR3YZHaGW7kyImuWGgh+D1b6GlZBkYlXhIEZJfFb23yhqwMmlLiCjfS4YP0R8VqK0PUgcvPUNbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba7a5dbc72458b44c78c8f5260396f274d2e88afb00a9a1c23663e578d1ba1a1","last_reissued_at":"2026-06-30T01:17:46.376825Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:46.376825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Dileep Kalathil, P. R. Kumar, Srinivas Shakkottai, Tzu-Hsiang Lin","submitted_at":"2026-06-27T14:23:21Z","abstract_excerpt":"Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into task failure. Existing methods address this either by expanding the training distribution through expert corrections or synthetic augmentation, or by steering a frozen policy at test time with guidance from a learned model. The former can be expensive or assumption-dependent, while the latter discards the corrected trajectories after execution. We introduce ReGuide, a self-improving framework that treats guided rollouts as reusable on-policy re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28939","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/2606.28939/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":"2606.28939","created_at":"2026-06-30T01:17:46.376901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28939v1","created_at":"2026-06-30T01:17:46.376901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28939","created_at":"2026-06-30T01:17:46.376901+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJ5F3PDSIWFU","created_at":"2026-06-30T01:17:46.376901+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJ5F3PDSIWFUJR4M","created_at":"2026-06-30T01:17:46.376901+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJ5F3PDS","created_at":"2026-06-30T01:17:46.376901+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/XJ5F3PDSIWFUJR4MR5JGAOLPE5","json":"https://pith.science/pith/XJ5F3PDSIWFUJR4MR5JGAOLPE5.json","graph_json":"https://pith.science/api/pith-number/XJ5F3PDSIWFUJR4MR5JGAOLPE5/graph.json","events_json":"https://pith.science/api/pith-number/XJ5F3PDSIWFUJR4MR5JGAOLPE5/events.json","paper":"https://pith.science/paper/XJ5F3PDS"},"agent_actions":{"view_html":"https://pith.science/pith/XJ5F3PDSIWFUJR4MR5JGAOLPE5","download_json":"https://pith.science/pith/XJ5F3PDSIWFUJR4MR5JGAOLPE5.json","view_paper":"https://pith.science/paper/XJ5F3PDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28939&json=true","fetch_graph":"https://pith.science/api/pith-number/XJ5F3PDSIWFUJR4MR5JGAOLPE5/graph.json","fetch_events":"https://pith.science/api/pith-number/XJ5F3PDSIWFUJR4MR5JGAOLPE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJ5F3PDSIWFUJR4MR5JGAOLPE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJ5F3PDSIWFUJR4MR5JGAOLPE5/action/storage_attestation","attest_author":"https://pith.science/pith/XJ5F3PDSIWFUJR4MR5JGAOLPE5/action/author_attestation","sign_citation":"https://pith.science/pith/XJ5F3PDSIWFUJR4MR5JGAOLPE5/action/citation_signature","submit_replication":"https://pith.science/pith/XJ5F3PDSIWFUJR4MR5JGAOLPE5/action/replication_record"}},"created_at":"2026-06-30T01:17:46.376901+00:00","updated_at":"2026-06-30T01:17:46.376901+00:00"}