{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7DC5AS6F5A4JAKTRH4LTD6CYDN","short_pith_number":"pith:7DC5AS6F","schema_version":"1.0","canonical_sha256":"f8c5d04bc5e838902a713f1731f8581b570221bae5ade82e758625fc549d7fbc","source":{"kind":"arxiv","id":"2402.16075","version":4},"attestation_state":"computed","paper":{"title":"Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Eugene Lim, Harold Soh, Kaiqi Chen, Kelvin Lin, Yiyang Chen","submitted_at":"2024-02-25T12:19:21Z","abstract_excerpt":"Imitation learning empowers artificial agents to mimic behavior by learning from demonstrations. Recently, diffusion models, which have the ability to model high-dimensional and multimodal distributions, have shown impressive performance on imitation learning tasks. These models learn to shape a policy by diffusing actions (or states) from standard Gaussian noise. However, the target policy to be learned is often significantly different from Gaussian and this mismatch can result in poor performance when using a small number of diffusion steps (to improve inference speed) and under limited data"},"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":"2402.16075","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-25T12:19:21Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"f718369ef216d8761cf0a6a06ba539d84b8a45f851951f761142b12f925dacaa","abstract_canon_sha256":"b02d936bb3f52bb6031e0bebbf8da6b919939230ff68bd12382bcf62bebb01ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:33.333923Z","signature_b64":"k/FbwRkNHrWvvxO9TfZdE4SjYpQElGTCRGnc9Ut8d+61ysd65xAbw9pdl5PF74KkSPD8Vm4H1R/mWHZ7WLR2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8c5d04bc5e838902a713f1731f8581b570221bae5ade82e758625fc549d7fbc","last_reissued_at":"2026-07-05T08:42:33.333446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:33.333446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Eugene Lim, Harold Soh, Kaiqi Chen, Kelvin Lin, Yiyang Chen","submitted_at":"2024-02-25T12:19:21Z","abstract_excerpt":"Imitation learning empowers artificial agents to mimic behavior by learning from demonstrations. Recently, diffusion models, which have the ability to model high-dimensional and multimodal distributions, have shown impressive performance on imitation learning tasks. These models learn to shape a policy by diffusing actions (or states) from standard Gaussian noise. However, the target policy to be learned is often significantly different from Gaussian and this mismatch can result in poor performance when using a small number of diffusion steps (to improve inference speed) and under limited data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16075","kind":"arxiv","version":4},"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/2402.16075/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":"2402.16075","created_at":"2026-07-05T08:42:33.333506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16075v4","created_at":"2026-07-05T08:42:33.333506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16075","created_at":"2026-07-05T08:42:33.333506+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DC5AS6F5A4J","created_at":"2026-07-05T08:42:33.333506+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DC5AS6F5A4JAKTR","created_at":"2026-07-05T08:42:33.333506+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DC5AS6F","created_at":"2026-07-05T08:42:33.333506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13959","citing_title":"WarmPrior: Straightening Flow-Matching Policies with Temporal Priors","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DC5AS6F5A4JAKTRH4LTD6CYDN","json":"https://pith.science/pith/7DC5AS6F5A4JAKTRH4LTD6CYDN.json","graph_json":"https://pith.science/api/pith-number/7DC5AS6F5A4JAKTRH4LTD6CYDN/graph.json","events_json":"https://pith.science/api/pith-number/7DC5AS6F5A4JAKTRH4LTD6CYDN/events.json","paper":"https://pith.science/paper/7DC5AS6F"},"agent_actions":{"view_html":"https://pith.science/pith/7DC5AS6F5A4JAKTRH4LTD6CYDN","download_json":"https://pith.science/pith/7DC5AS6F5A4JAKTRH4LTD6CYDN.json","view_paper":"https://pith.science/paper/7DC5AS6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16075&json=true","fetch_graph":"https://pith.science/api/pith-number/7DC5AS6F5A4JAKTRH4LTD6CYDN/graph.json","fetch_events":"https://pith.science/api/pith-number/7DC5AS6F5A4JAKTRH4LTD6CYDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DC5AS6F5A4JAKTRH4LTD6CYDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DC5AS6F5A4JAKTRH4LTD6CYDN/action/storage_attestation","attest_author":"https://pith.science/pith/7DC5AS6F5A4JAKTRH4LTD6CYDN/action/author_attestation","sign_citation":"https://pith.science/pith/7DC5AS6F5A4JAKTRH4LTD6CYDN/action/citation_signature","submit_replication":"https://pith.science/pith/7DC5AS6F5A4JAKTRH4LTD6CYDN/action/replication_record"}},"created_at":"2026-07-05T08:42:33.333506+00:00","updated_at":"2026-07-05T08:42:33.333506+00:00"}