{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MCQMVIWLO3R76TD7O5TOYH3OSU","short_pith_number":"pith:MCQMVIWL","canonical_record":{"source":{"id":"1907.00456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T20:53:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"edb9f11dda92f2c090f26a59390efb333c67c887e01c84879fc1797f4815041d","abstract_canon_sha256":"05b5d99512a3744648aac17c70914a96cdc29a1128bfa051a1171409f9148b82"},"schema_version":"1.0"},"canonical_sha256":"60a0caa2cb76e3ff4c7f7766ec1f6e951b49bd8dd6e1cb19ab5873bcd043b8fe","source":{"kind":"arxiv","id":"1907.00456","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00456","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00456v2","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00456","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"pith_short_12","alias_value":"MCQMVIWLO3R7","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MCQMVIWLO3R76TD7","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MCQMVIWL","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MCQMVIWLO3R76TD7O5TOYH3OSU","target":"record","payload":{"canonical_record":{"source":{"id":"1907.00456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T20:53:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"edb9f11dda92f2c090f26a59390efb333c67c887e01c84879fc1797f4815041d","abstract_canon_sha256":"05b5d99512a3744648aac17c70914a96cdc29a1128bfa051a1171409f9148b82"},"schema_version":"1.0"},"canonical_sha256":"60a0caa2cb76e3ff4c7f7766ec1f6e951b49bd8dd6e1cb19ab5873bcd043b8fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:17.029737Z","signature_b64":"M+fya589XvJpMgzL+pfQC5+FaVM0I9tNe2I+Hs8DaNRHaoU3U55DlFDMYVxg+aA0Lgan78scTcx01BYRohtCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60a0caa2cb76e3ff4c7f7766ec1f6e951b49bd8dd6e1cb19ab5873bcd043b8fe","last_reissued_at":"2026-05-17T23:41:17.029130Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:17.029130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.00456","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cDdt01T/5gPJJ7sTmHAcWZgG0T4SdvsEXnoaVOmqqJwjNC8O0UZHoP/K58MpSAkmmtHjq2c3ZnmH3KE/KGrPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:29:44.196142Z"},"content_sha256":"140dc2fd08117fe7db80292b4f124f5ac84f517ed6246658f442e4881a3be5b0","schema_version":"1.0","event_id":"sha256:140dc2fd08117fe7db80292b4f124f5ac84f517ed6246658f442e4881a3be5b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MCQMVIWLO3R76TD7O5TOYH3OSU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Agata Lapedriza, Asma Ghandeharioun, Craig Ferguson, Judy Hanwen Shen, Natasha Jaques, Noah Jones, Rosalind Picard, Shixiang Gu","submitted_at":"2019-06-30T20:53:19Z","abstract_excerpt":"Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where collecting data is expensive, and models must be tested offline before being deployed to interact with the environment -- e.g. systems that learn from human interaction. Thus, we develop a novel class of off-policy batch RL algorithms, which are able to effectively learn offline, without exploring, from a fixed batch of human interaction data. We leverage mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00456","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JHSuYyAzKXNB7IzFiwRuMx6SuFMg0gWCwRiZotgX2W/cCgjnBzXImkWGl39xcsyW++RlbFqda7BFEYgfjVFfBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:29:44.196757Z"},"content_sha256":"00b766760d9bff727f16f610ae96bc27d9b5eba89bee6864e1e37214d4f33377","schema_version":"1.0","event_id":"sha256:00b766760d9bff727f16f610ae96bc27d9b5eba89bee6864e1e37214d4f33377"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCQMVIWLO3R76TD7O5TOYH3OSU/bundle.json","state_url":"https://pith.science/pith/MCQMVIWLO3R76TD7O5TOYH3OSU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCQMVIWLO3R76TD7O5TOYH3OSU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-29T19:29:44Z","links":{"resolver":"https://pith.science/pith/MCQMVIWLO3R76TD7O5TOYH3OSU","bundle":"https://pith.science/pith/MCQMVIWLO3R76TD7O5TOYH3OSU/bundle.json","state":"https://pith.science/pith/MCQMVIWLO3R76TD7O5TOYH3OSU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCQMVIWLO3R76TD7O5TOYH3OSU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MCQMVIWLO3R76TD7O5TOYH3OSU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"05b5d99512a3744648aac17c70914a96cdc29a1128bfa051a1171409f9148b82","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T20:53:19Z","title_canon_sha256":"edb9f11dda92f2c090f26a59390efb333c67c887e01c84879fc1797f4815041d"},"schema_version":"1.0","source":{"id":"1907.00456","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00456","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00456v2","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00456","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"pith_short_12","alias_value":"MCQMVIWLO3R7","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MCQMVIWLO3R76TD7","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MCQMVIWL","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:00b766760d9bff727f16f610ae96bc27d9b5eba89bee6864e1e37214d4f33377","target":"graph","created_at":"2026-05-17T23:41:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where collecting data is expensive, and models must be tested offline before being deployed to interact with the environment -- e.g. systems that learn from human interaction. Thus, we develop a novel class of off-policy batch RL algorithms, which are able to effectively learn offline, without exploring, from a fixed batch of human interaction data. We leverage mo","authors_text":"Agata Lapedriza, Asma Ghandeharioun, Craig Ferguson, Judy Hanwen Shen, Natasha Jaques, Noah Jones, Rosalind Picard, Shixiang Gu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T20:53:19Z","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00456","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:140dc2fd08117fe7db80292b4f124f5ac84f517ed6246658f442e4881a3be5b0","target":"record","created_at":"2026-05-17T23:41:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"05b5d99512a3744648aac17c70914a96cdc29a1128bfa051a1171409f9148b82","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T20:53:19Z","title_canon_sha256":"edb9f11dda92f2c090f26a59390efb333c67c887e01c84879fc1797f4815041d"},"schema_version":"1.0","source":{"id":"1907.00456","kind":"arxiv","version":2}},"canonical_sha256":"60a0caa2cb76e3ff4c7f7766ec1f6e951b49bd8dd6e1cb19ab5873bcd043b8fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60a0caa2cb76e3ff4c7f7766ec1f6e951b49bd8dd6e1cb19ab5873bcd043b8fe","first_computed_at":"2026-05-17T23:41:17.029130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:17.029130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M+fya589XvJpMgzL+pfQC5+FaVM0I9tNe2I+Hs8DaNRHaoU3U55DlFDMYVxg+aA0Lgan78scTcx01BYRohtCCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:17.029737Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.00456","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:140dc2fd08117fe7db80292b4f124f5ac84f517ed6246658f442e4881a3be5b0","sha256:00b766760d9bff727f16f610ae96bc27d9b5eba89bee6864e1e37214d4f33377"],"state_sha256":"2aba145b8602ae38d10e224c18a99be8591a7bf0bc9e63e5bd382a53d80d6554"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"76TS1owLy45vyxugIFPIptQ5nkdTSThBF/QddSB4UrICZu83mgEXVTAh/oEFqW6fcR/QwLaVXD8TCfwBhtZdAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T19:29:44.199245Z","bundle_sha256":"fa73cc75ccf96d9293f3232aec7ac51a8e4c09db70bac6ea4c7a35d423f5bb6a"}}