{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S5L3RLLXC6SFGHFIDI3I75RCML","short_pith_number":"pith:S5L3RLLX","schema_version":"1.0","canonical_sha256":"9757b8ad7717a4531ca81a368ff62262d15280fdd18f6c1270b82dd29bcd7054","source":{"kind":"arxiv","id":"2310.10556","version":2},"attestation_state":"computed","paper":{"title":"Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mengdi Wang, Minshuo Chen, Xiang Ji, Zihao Li","submitted_at":"2023-10-16T16:27:06Z","abstract_excerpt":"A recently popular approach to solving reinforcement learning is with data from human preferences. In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, which involve evaluating an intermediate policy over a reward learned from human preference data with distribution shift, known as off-policy evaluation (OPE). Such algorithm includes (i) learning reward function from human preference dataset, and (ii) learning expected cumulative reward of a target policy. Despite the huge empirical success, existing OPE methods with preferenc"},"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":"2310.10556","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T16:27:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a99d9258115a812d617d771dc2836232bc48de1e31e9751a789cc6f14586e530","abstract_canon_sha256":"e7802cf0cef729b5333d6093cd22d7613820442c3a65ce7431cc25352df1681d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:34.125618Z","signature_b64":"Ku0Gm+yx8JDtw0XrShseGs0HPiAxuLTefKdsMsPzXBRsST6U1sXKNXscGha4I/Ky0fo5dqmHXw/LJFQ1G6tlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9757b8ad7717a4531ca81a368ff62262d15280fdd18f6c1270b82dd29bcd7054","last_reissued_at":"2026-07-05T07:49:34.125134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:34.125134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mengdi Wang, Minshuo Chen, Xiang Ji, Zihao Li","submitted_at":"2023-10-16T16:27:06Z","abstract_excerpt":"A recently popular approach to solving reinforcement learning is with data from human preferences. In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, which involve evaluating an intermediate policy over a reward learned from human preference data with distribution shift, known as off-policy evaluation (OPE). Such algorithm includes (i) learning reward function from human preference dataset, and (ii) learning expected cumulative reward of a target policy. Despite the huge empirical success, existing OPE methods with preferenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10556","kind":"arxiv","version":2},"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/2310.10556/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":"2310.10556","created_at":"2026-07-05T07:49:34.125190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10556v2","created_at":"2026-07-05T07:49:34.125190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10556","created_at":"2026-07-05T07:49:34.125190+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5L3RLLXC6SF","created_at":"2026-07-05T07:49:34.125190+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5L3RLLXC6SFGHFI","created_at":"2026-07-05T07:49:34.125190+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5L3RLLX","created_at":"2026-07-05T07:49:34.125190+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/S5L3RLLXC6SFGHFIDI3I75RCML","json":"https://pith.science/pith/S5L3RLLXC6SFGHFIDI3I75RCML.json","graph_json":"https://pith.science/api/pith-number/S5L3RLLXC6SFGHFIDI3I75RCML/graph.json","events_json":"https://pith.science/api/pith-number/S5L3RLLXC6SFGHFIDI3I75RCML/events.json","paper":"https://pith.science/paper/S5L3RLLX"},"agent_actions":{"view_html":"https://pith.science/pith/S5L3RLLXC6SFGHFIDI3I75RCML","download_json":"https://pith.science/pith/S5L3RLLXC6SFGHFIDI3I75RCML.json","view_paper":"https://pith.science/paper/S5L3RLLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10556&json=true","fetch_graph":"https://pith.science/api/pith-number/S5L3RLLXC6SFGHFIDI3I75RCML/graph.json","fetch_events":"https://pith.science/api/pith-number/S5L3RLLXC6SFGHFIDI3I75RCML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5L3RLLXC6SFGHFIDI3I75RCML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5L3RLLXC6SFGHFIDI3I75RCML/action/storage_attestation","attest_author":"https://pith.science/pith/S5L3RLLXC6SFGHFIDI3I75RCML/action/author_attestation","sign_citation":"https://pith.science/pith/S5L3RLLXC6SFGHFIDI3I75RCML/action/citation_signature","submit_replication":"https://pith.science/pith/S5L3RLLXC6SFGHFIDI3I75RCML/action/replication_record"}},"created_at":"2026-07-05T07:49:34.125190+00:00","updated_at":"2026-07-05T07:49:34.125190+00:00"}