{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IRAVN6QUKXN6B46UNTENPSMWWT","short_pith_number":"pith:IRAVN6QU","canonical_record":{"source":{"id":"2212.01105","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-02T11:35:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"65b632ddaad8c06746e2f6ee129adacc28575fde6e57e3876577598577ed352d","abstract_canon_sha256":"8d28d5d19712ad5301a149adf653d8d0b754bfb3c3b327d3c5428a255e7a5b31"},"schema_version":"1.0"},"canonical_sha256":"444156fa1455dbe0f3d46cc8d7c996b4dfb409bc4acd82a9fd61cf82443d2909","source":{"kind":"arxiv","id":"2212.01105","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01105","created_at":"2026-07-05T05:21:49Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01105v1","created_at":"2026-07-05T05:21:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01105","created_at":"2026-07-05T05:21:49Z"},{"alias_kind":"pith_short_12","alias_value":"IRAVN6QUKXN6","created_at":"2026-07-05T05:21:49Z"},{"alias_kind":"pith_short_16","alias_value":"IRAVN6QUKXN6B46U","created_at":"2026-07-05T05:21:49Z"},{"alias_kind":"pith_short_8","alias_value":"IRAVN6QU","created_at":"2026-07-05T05:21:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IRAVN6QUKXN6B46UNTENPSMWWT","target":"record","payload":{"canonical_record":{"source":{"id":"2212.01105","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-02T11:35:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"65b632ddaad8c06746e2f6ee129adacc28575fde6e57e3876577598577ed352d","abstract_canon_sha256":"8d28d5d19712ad5301a149adf653d8d0b754bfb3c3b327d3c5428a255e7a5b31"},"schema_version":"1.0"},"canonical_sha256":"444156fa1455dbe0f3d46cc8d7c996b4dfb409bc4acd82a9fd61cf82443d2909","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:49.600206Z","signature_b64":"ez9daTEoD4YnAljzdxi0hOuJwadQCQjBuVNMJfnMmjbF+NJd6AiUNeTbMLHwLA8nCJdpaQ+TyJ0JvpLOXubjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"444156fa1455dbe0f3d46cc8d7c996b4dfb409bc4acd82a9fd61cf82443d2909","last_reissued_at":"2026-07-05T05:21:49.599846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:49.599846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.01105","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:21:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7nRQTqM9oaSbIsxnCnBF1KHSNWi58WAYXeKq+0f0JnKUOJNHzkKPVhtai1O2ktj27UKJHvj3BIE/kzsJQ8R3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:08:48.311883Z"},"content_sha256":"20ef8ee933608fdd4bc0aa5f9e501aa8bd87709f102f5733b9105f5bf8e40c67","schema_version":"1.0","event_id":"sha256:20ef8ee933608fdd4bc0aa5f9e501aa8bd87709f102f5733b9105f5bf8e40c67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IRAVN6QUKXN6B46UNTENPSMWWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Hao Hu, Jun Yang, Qianchuan Zhao, Siyuan Li, Wenzhe Li, Yiqin Yang","submitted_at":"2022-12-02T11:35:51Z","abstract_excerpt":"Offline reinforcement learning (RL) enables the agent to effectively learn from logged data, which significantly extends the applicability of RL algorithms in real-world scenarios where exploration can be expensive or unsafe. Previous works have shown that extracting primitive skills from the recurring and temporally extended structures in the logged data yields better learning. However, these methods suffer greatly when the primitives have limited representation ability to recover the original policy space, especially in offline settings. In this paper, we give a quantitative characterization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01105","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/2212.01105/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":"2026-07-05T05:21:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vqvn0+rrF0/9c/xL51beVTOuBgWhWojR4nuOq0LWIXxtNqXIsiO9zh2SFKFJtpHpIMJ5MdDuqWOFrKQeBPMQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:08:48.312258Z"},"content_sha256":"ec4ba2ac5daa35a7d32496e206c65c907b0a18487d2fd217dd02366fd386dd9f","schema_version":"1.0","event_id":"sha256:ec4ba2ac5daa35a7d32496e206c65c907b0a18487d2fd217dd02366fd386dd9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IRAVN6QUKXN6B46UNTENPSMWWT/bundle.json","state_url":"https://pith.science/pith/IRAVN6QUKXN6B46UNTENPSMWWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IRAVN6QUKXN6B46UNTENPSMWWT/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":"2026-07-07T05:08:48Z","links":{"resolver":"https://pith.science/pith/IRAVN6QUKXN6B46UNTENPSMWWT","bundle":"https://pith.science/pith/IRAVN6QUKXN6B46UNTENPSMWWT/bundle.json","state":"https://pith.science/pith/IRAVN6QUKXN6B46UNTENPSMWWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IRAVN6QUKXN6B46UNTENPSMWWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IRAVN6QUKXN6B46UNTENPSMWWT","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":"8d28d5d19712ad5301a149adf653d8d0b754bfb3c3b327d3c5428a255e7a5b31","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-02T11:35:51Z","title_canon_sha256":"65b632ddaad8c06746e2f6ee129adacc28575fde6e57e3876577598577ed352d"},"schema_version":"1.0","source":{"id":"2212.01105","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01105","created_at":"2026-07-05T05:21:49Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01105v1","created_at":"2026-07-05T05:21:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01105","created_at":"2026-07-05T05:21:49Z"},{"alias_kind":"pith_short_12","alias_value":"IRAVN6QUKXN6","created_at":"2026-07-05T05:21:49Z"},{"alias_kind":"pith_short_16","alias_value":"IRAVN6QUKXN6B46U","created_at":"2026-07-05T05:21:49Z"},{"alias_kind":"pith_short_8","alias_value":"IRAVN6QU","created_at":"2026-07-05T05:21:49Z"}],"graph_snapshots":[{"event_id":"sha256:ec4ba2ac5daa35a7d32496e206c65c907b0a18487d2fd217dd02366fd386dd9f","target":"graph","created_at":"2026-07-05T05:21:49Z","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/2212.01105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) enables the agent to effectively learn from logged data, which significantly extends the applicability of RL algorithms in real-world scenarios where exploration can be expensive or unsafe. Previous works have shown that extracting primitive skills from the recurring and temporally extended structures in the logged data yields better learning. However, these methods suffer greatly when the primitives have limited representation ability to recover the original policy space, especially in offline settings. In this paper, we give a quantitative characterization","authors_text":"Chongjie Zhang, Hao Hu, Jun Yang, Qianchuan Zhao, Siyuan Li, Wenzhe Li, Yiqin Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-02T11:35:51Z","title":"Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01105","kind":"arxiv","version":1},"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":"sha256:20ef8ee933608fdd4bc0aa5f9e501aa8bd87709f102f5733b9105f5bf8e40c67","target":"record","created_at":"2026-07-05T05:21:49Z","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":"8d28d5d19712ad5301a149adf653d8d0b754bfb3c3b327d3c5428a255e7a5b31","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-02T11:35:51Z","title_canon_sha256":"65b632ddaad8c06746e2f6ee129adacc28575fde6e57e3876577598577ed352d"},"schema_version":"1.0","source":{"id":"2212.01105","kind":"arxiv","version":1}},"canonical_sha256":"444156fa1455dbe0f3d46cc8d7c996b4dfb409bc4acd82a9fd61cf82443d2909","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"444156fa1455dbe0f3d46cc8d7c996b4dfb409bc4acd82a9fd61cf82443d2909","first_computed_at":"2026-07-05T05:21:49.599846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:49.599846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ez9daTEoD4YnAljzdxi0hOuJwadQCQjBuVNMJfnMmjbF+NJd6AiUNeTbMLHwLA8nCJdpaQ+TyJ0JvpLOXubjDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:49.600206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.01105","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20ef8ee933608fdd4bc0aa5f9e501aa8bd87709f102f5733b9105f5bf8e40c67","sha256:ec4ba2ac5daa35a7d32496e206c65c907b0a18487d2fd217dd02366fd386dd9f"],"state_sha256":"a18d1bf3f8dfb13db610d5cbd798bebc11eca0104254ee258302f281ded4bcbd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IieyHKrid1K0g6n7CS8wkU3WyMpjvtdM2UDwxuc7ZCezEn7F3nHH172i85cRlFPMiZH/DWdpOHRH19vGYn6hDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:08:48.315165Z","bundle_sha256":"32dfef5e37a9abf72fa365045887049b866b0389d3c1625c902280f47d34623b"}}