{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H3WZO5NXVTTN2OGAVN2JTFKFOL","short_pith_number":"pith:H3WZO5NX","schema_version":"1.0","canonical_sha256":"3eed9775b7ace6dd38c0ab7499954572f59b372c826a03d87644afecb4e1faec","source":{"kind":"arxiv","id":"2505.20781","version":1},"attestation_state":"computed","paper":{"title":"STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Florian Shkurti, Haruki Nishimura, Hossein Goli, Masha Itkina, Michael Gimelfarb, Nathan Samuel de Lara","submitted_at":"2025-05-27T06:39:26Z","abstract_excerpt":"Off-policy evaluation (OPE) estimates the performance of a target policy using offline data collected from a behavior policy, and is crucial in domains such as robotics or healthcare where direct interaction with the environment is costly or unsafe. Existing OPE methods are ineffective for high-dimensional, long-horizon problems, due to exponential blow-ups in variance from importance weighting or compounding errors from learned dynamics models. To address these challenges, we propose STITCH-OPE, a model-based generative framework that leverages denoising diffusion for long-horizon OPE in high"},"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":"2505.20781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-27T06:39:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f1066ebd75015297860a45504f0e24805fb29f50918c9a94020a22169b9f7498","abstract_canon_sha256":"5d71b17362490f9675388885f63e44aa4f7e5b6a8984e6f9ca5b2ea17cd7bd52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:18.794775Z","signature_b64":"zSYsikkpnKXOz/gnV7APPfMMSN+saEHOv8Wiap0lJILTkMT41mj6VCZOHQBijqvpfVYU1wWQpujreanrplj+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eed9775b7ace6dd38c0ab7499954572f59b372c826a03d87644afecb4e1faec","last_reissued_at":"2026-07-05T11:10:18.794273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:18.794273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Florian Shkurti, Haruki Nishimura, Hossein Goli, Masha Itkina, Michael Gimelfarb, Nathan Samuel de Lara","submitted_at":"2025-05-27T06:39:26Z","abstract_excerpt":"Off-policy evaluation (OPE) estimates the performance of a target policy using offline data collected from a behavior policy, and is crucial in domains such as robotics or healthcare where direct interaction with the environment is costly or unsafe. Existing OPE methods are ineffective for high-dimensional, long-horizon problems, due to exponential blow-ups in variance from importance weighting or compounding errors from learned dynamics models. To address these challenges, we propose STITCH-OPE, a model-based generative framework that leverages denoising diffusion for long-horizon OPE in high"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20781","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/2505.20781/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":"2505.20781","created_at":"2026-07-05T11:10:18.794339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20781v1","created_at":"2026-07-05T11:10:18.794339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20781","created_at":"2026-07-05T11:10:18.794339+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3WZO5NXVTTN","created_at":"2026-07-05T11:10:18.794339+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3WZO5NXVTTN2OGA","created_at":"2026-07-05T11:10:18.794339+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3WZO5NX","created_at":"2026-07-05T11:10:18.794339+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/H3WZO5NXVTTN2OGAVN2JTFKFOL","json":"https://pith.science/pith/H3WZO5NXVTTN2OGAVN2JTFKFOL.json","graph_json":"https://pith.science/api/pith-number/H3WZO5NXVTTN2OGAVN2JTFKFOL/graph.json","events_json":"https://pith.science/api/pith-number/H3WZO5NXVTTN2OGAVN2JTFKFOL/events.json","paper":"https://pith.science/paper/H3WZO5NX"},"agent_actions":{"view_html":"https://pith.science/pith/H3WZO5NXVTTN2OGAVN2JTFKFOL","download_json":"https://pith.science/pith/H3WZO5NXVTTN2OGAVN2JTFKFOL.json","view_paper":"https://pith.science/paper/H3WZO5NX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20781&json=true","fetch_graph":"https://pith.science/api/pith-number/H3WZO5NXVTTN2OGAVN2JTFKFOL/graph.json","fetch_events":"https://pith.science/api/pith-number/H3WZO5NXVTTN2OGAVN2JTFKFOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3WZO5NXVTTN2OGAVN2JTFKFOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3WZO5NXVTTN2OGAVN2JTFKFOL/action/storage_attestation","attest_author":"https://pith.science/pith/H3WZO5NXVTTN2OGAVN2JTFKFOL/action/author_attestation","sign_citation":"https://pith.science/pith/H3WZO5NXVTTN2OGAVN2JTFKFOL/action/citation_signature","submit_replication":"https://pith.science/pith/H3WZO5NXVTTN2OGAVN2JTFKFOL/action/replication_record"}},"created_at":"2026-07-05T11:10:18.794339+00:00","updated_at":"2026-07-05T11:10:18.794339+00:00"}