{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4VS4DXJPTKIVUCYBTCFACCFNNC","short_pith_number":"pith:4VS4DXJP","canonical_record":{"source":{"id":"2111.03788","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-06T03:09:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c47e841810982e2592de1eefeea9dfee3ae0007433c7469aa1d7a4615daa356","abstract_canon_sha256":"7f02491b091096adbab5254967860f5c470a09ec54382dfe1ed2a2f2bcd96683"},"schema_version":"1.0"},"canonical_sha256":"e565c1dd2f9a915a0b01988a0108ad68b040b22c99d14cc2467db3c9fa5196d8","source":{"kind":"arxiv","id":"2111.03788","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.03788","created_at":"2026-07-05T05:22:04Z"},{"alias_kind":"arxiv_version","alias_value":"2111.03788v2","created_at":"2026-07-05T05:22:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03788","created_at":"2026-07-05T05:22:04Z"},{"alias_kind":"pith_short_12","alias_value":"4VS4DXJPTKIV","created_at":"2026-07-05T05:22:04Z"},{"alias_kind":"pith_short_16","alias_value":"4VS4DXJPTKIVUCYB","created_at":"2026-07-05T05:22:04Z"},{"alias_kind":"pith_short_8","alias_value":"4VS4DXJP","created_at":"2026-07-05T05:22:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4VS4DXJPTKIVUCYBTCFACCFNNC","target":"record","payload":{"canonical_record":{"source":{"id":"2111.03788","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-06T03:09:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c47e841810982e2592de1eefeea9dfee3ae0007433c7469aa1d7a4615daa356","abstract_canon_sha256":"7f02491b091096adbab5254967860f5c470a09ec54382dfe1ed2a2f2bcd96683"},"schema_version":"1.0"},"canonical_sha256":"e565c1dd2f9a915a0b01988a0108ad68b040b22c99d14cc2467db3c9fa5196d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:04.850411Z","signature_b64":"1NPFbRySi9ed6SAv+QtTplEvyqoHKfBTQYf92z8DV4ua/hhf99wa8mooUQVNMNh53+i1BZywcs8nxRnehDzkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e565c1dd2f9a915a0b01988a0108ad68b040b22c99d14cc2467db3c9fa5196d8","last_reissued_at":"2026-07-05T05:22:04.849874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:04.849874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.03788","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":"2026-07-05T05:22:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S7dWmCO+UScUoHytTggKfSfLY/u/d/0wg+7sGMatQ5AU+S7XlCDQCWlcwFTVGFJcwEFWsSrHQ1GXTBSqTVLVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:46:49.582865Z"},"content_sha256":"d63c2f71dddf589695418164a355580f8ae96432f78324616fd863028877e84e","schema_version":"1.0","event_id":"sha256:d63c2f71dddf589695418164a355580f8ae96432f78324616fd863028877e84e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4VS4DXJPTKIVUCYBTCFACCFNNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"d3rlpy: An Offline Deep Reinforcement Learning Library","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Michita Imai, Takuma Seno","submitted_at":"2021-11-06T03:09:39Z","abstract_excerpt":"In this paper, we introduce d3rlpy, an open-sourced offline deep reinforcement learning (RL) library for Python. d3rlpy supports a set of offline deep RL algorithms as well as off-policy online algorithms via a fully documented plug-and-play API. To address a reproducibility issue, we conduct a large-scale benchmark with D4RL and Atari 2600 dataset to ensure implementation quality and provide experimental scripts and full tables of results. The d3rlpy source code can be found on GitHub: \\url{https://github.com/takuseno/d3rlpy}."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03788","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/2111.03788/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:22:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kF/VjD9BMBy+sst+N94ougvBrYAOdc/nYPLc8qkIQcEjrhPQBSdkAMOP4UEa1Qhrot73VEgBEqKCNX4GV29YAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:46:49.583371Z"},"content_sha256":"5f5ad426aaa5d9619aa008a29c747ab96047e213aec069a2076cd477c9130703","schema_version":"1.0","event_id":"sha256:5f5ad426aaa5d9619aa008a29c747ab96047e213aec069a2076cd477c9130703"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VS4DXJPTKIVUCYBTCFACCFNNC/bundle.json","state_url":"https://pith.science/pith/4VS4DXJPTKIVUCYBTCFACCFNNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VS4DXJPTKIVUCYBTCFACCFNNC/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":"2026-08-08T15:46:49Z","links":{"resolver":"https://pith.science/pith/4VS4DXJPTKIVUCYBTCFACCFNNC","bundle":"https://pith.science/pith/4VS4DXJPTKIVUCYBTCFACCFNNC/bundle.json","state":"https://pith.science/pith/4VS4DXJPTKIVUCYBTCFACCFNNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VS4DXJPTKIVUCYBTCFACCFNNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4VS4DXJPTKIVUCYBTCFACCFNNC","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":"7f02491b091096adbab5254967860f5c470a09ec54382dfe1ed2a2f2bcd96683","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-06T03:09:39Z","title_canon_sha256":"1c47e841810982e2592de1eefeea9dfee3ae0007433c7469aa1d7a4615daa356"},"schema_version":"1.0","source":{"id":"2111.03788","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.03788","created_at":"2026-07-05T05:22:04Z"},{"alias_kind":"arxiv_version","alias_value":"2111.03788v2","created_at":"2026-07-05T05:22:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03788","created_at":"2026-07-05T05:22:04Z"},{"alias_kind":"pith_short_12","alias_value":"4VS4DXJPTKIV","created_at":"2026-07-05T05:22:04Z"},{"alias_kind":"pith_short_16","alias_value":"4VS4DXJPTKIVUCYB","created_at":"2026-07-05T05:22:04Z"},{"alias_kind":"pith_short_8","alias_value":"4VS4DXJP","created_at":"2026-07-05T05:22:04Z"}],"graph_snapshots":[{"event_id":"sha256:5f5ad426aaa5d9619aa008a29c747ab96047e213aec069a2076cd477c9130703","target":"graph","created_at":"2026-07-05T05:22:04Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2111.03788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce d3rlpy, an open-sourced offline deep reinforcement learning (RL) library for Python. d3rlpy supports a set of offline deep RL algorithms as well as off-policy online algorithms via a fully documented plug-and-play API. To address a reproducibility issue, we conduct a large-scale benchmark with D4RL and Atari 2600 dataset to ensure implementation quality and provide experimental scripts and full tables of results. The d3rlpy source code can be found on GitHub: \\url{https://github.com/takuseno/d3rlpy}.","authors_text":"Michita Imai, Takuma Seno","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-06T03:09:39Z","title":"d3rlpy: An Offline Deep Reinforcement Learning Library"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03788","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:d63c2f71dddf589695418164a355580f8ae96432f78324616fd863028877e84e","target":"record","created_at":"2026-07-05T05:22:04Z","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":"7f02491b091096adbab5254967860f5c470a09ec54382dfe1ed2a2f2bcd96683","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-06T03:09:39Z","title_canon_sha256":"1c47e841810982e2592de1eefeea9dfee3ae0007433c7469aa1d7a4615daa356"},"schema_version":"1.0","source":{"id":"2111.03788","kind":"arxiv","version":2}},"canonical_sha256":"e565c1dd2f9a915a0b01988a0108ad68b040b22c99d14cc2467db3c9fa5196d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e565c1dd2f9a915a0b01988a0108ad68b040b22c99d14cc2467db3c9fa5196d8","first_computed_at":"2026-07-05T05:22:04.849874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:04.849874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1NPFbRySi9ed6SAv+QtTplEvyqoHKfBTQYf92z8DV4ua/hhf99wa8mooUQVNMNh53+i1BZywcs8nxRnehDzkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:04.850411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.03788","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d63c2f71dddf589695418164a355580f8ae96432f78324616fd863028877e84e","sha256:5f5ad426aaa5d9619aa008a29c747ab96047e213aec069a2076cd477c9130703"],"state_sha256":"547394952063852fa5509bd55324b33ec6dcf3f41b4cf9b65ac9c491de65ed4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"20LbgT/WPRaC16jx/jw28Qt9Z/KNhyZQB1zCWU9gQYrI4gQbNtvIGMrjFGcUR/qXEh4KNCQzBF/BeykGdVu8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:46:49.586952Z","bundle_sha256":"8d6c9076721f2060c137de8561d1c8b69bd96e4ac08a09e030b88f4edccbae27"}}