{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6U2RO6G6HQNTZD2JNG5VZ5BYHY","short_pith_number":"pith:6U2RO6G6","canonical_record":{"source":{"id":"2306.05905","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T14:01:26Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"14b4d353cd98a977fa8bea958cc86fea20cde5d0bc7508136dd06fc9196aa060","abstract_canon_sha256":"0d5ad5383016b574ef875b25418326cabfbf9a74abd126a5cec2ad905ad5e7fa"},"schema_version":"1.0"},"canonical_sha256":"f5351778de3c1b3c8f4969bb5cf4383e3fff5ced2b3476312458aa64f8d0e66a","source":{"kind":"arxiv","id":"2306.05905","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05905","created_at":"2026-05-22T01:03:13Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05905v2","created_at":"2026-05-22T01:03:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05905","created_at":"2026-05-22T01:03:13Z"},{"alias_kind":"pith_short_12","alias_value":"6U2RO6G6HQNT","created_at":"2026-05-22T01:03:13Z"},{"alias_kind":"pith_short_16","alias_value":"6U2RO6G6HQNTZD2J","created_at":"2026-05-22T01:03:13Z"},{"alias_kind":"pith_short_8","alias_value":"6U2RO6G6","created_at":"2026-05-22T01:03:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6U2RO6G6HQNTZD2JNG5VZ5BYHY","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05905","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T14:01:26Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"14b4d353cd98a977fa8bea958cc86fea20cde5d0bc7508136dd06fc9196aa060","abstract_canon_sha256":"0d5ad5383016b574ef875b25418326cabfbf9a74abd126a5cec2ad905ad5e7fa"},"schema_version":"1.0"},"canonical_sha256":"f5351778de3c1b3c8f4969bb5cf4383e3fff5ced2b3476312458aa64f8d0e66a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:13.479376Z","signature_b64":"SVFW/avTljVBOj095GYyWrBYBZnvMrtzWgt604BHhTO5z3mBg3TyEye/m4SQImfn/Hyc++qDgSYF7ahuddIWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5351778de3c1b3c8f4969bb5cf4383e3fff5ced2b3476312458aa64f8d0e66a","last_reissued_at":"2026-05-22T01:03:13.478660Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:13.478660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05905","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":"2026-05-22T01:03:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ecTQr5Rh1KiEHY346nGwy7kpZbDUPoyj6T/rVqdTfZDtzyT79QPkwwm4aEYX5vIFMM4CgJo2Y1TJaXQD76sPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:47:32.925444Z"},"content_sha256":"3e1d1d3bf05974df03cca0d2e48eb579f93756ad8c19e44d5ff83372586bac4d","schema_version":"1.0","event_id":"sha256:3e1d1d3bf05974df03cca0d2e48eb579f93756ad8c19e44d5ff83372586bac4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6U2RO6G6HQNTZD2JNG5VZ5BYHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TreeDQN: Sample-Efficient Off-Policy Reinforcement Learning for Combinatorial Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"A. Kostin, A.V. Savchenko, D. Sorokin, G. Gusev, L. Savchenko","submitted_at":"2023-06-09T14:01:26Z","abstract_excerpt":"A convenient approach to optimally solving combinatorial optimization tasks is the Branch-and-Bound method. Its branching heuristic can be learned to solve a large set of similar tasks. The promising results here are achieved by the recently appeared on-policy reinforcement learning method based on the tree Markov Decision Process. To overcome its main disadvantages, namely, very large training time and unstable training, we propose TreeDQN (Tree Deep Q-Network), a sample-efficient off-policy RL method trained by optimizing the geometric mean of expected return. To theoretically support the tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05905","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/2306.05905/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":"2026-05-22T01:03:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eSaKHOtXbt33ioLq6CMOeDibAnmS9/z/NB3Ou76OSkrMnOAKBl0AI6s3Nv7fs/vlmXDo11gnq+pG3RFHTxhtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:47:32.926296Z"},"content_sha256":"6eb62574d4a7a8634d16b47c9a49c15f83e1b2b061beef3d6b269a8ce449041c","schema_version":"1.0","event_id":"sha256:6eb62574d4a7a8634d16b47c9a49c15f83e1b2b061beef3d6b269a8ce449041c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6U2RO6G6HQNTZD2JNG5VZ5BYHY/bundle.json","state_url":"https://pith.science/pith/6U2RO6G6HQNTZD2JNG5VZ5BYHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6U2RO6G6HQNTZD2JNG5VZ5BYHY/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":"2026-05-31T18:47:32Z","links":{"resolver":"https://pith.science/pith/6U2RO6G6HQNTZD2JNG5VZ5BYHY","bundle":"https://pith.science/pith/6U2RO6G6HQNTZD2JNG5VZ5BYHY/bundle.json","state":"https://pith.science/pith/6U2RO6G6HQNTZD2JNG5VZ5BYHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6U2RO6G6HQNTZD2JNG5VZ5BYHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6U2RO6G6HQNTZD2JNG5VZ5BYHY","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":"0d5ad5383016b574ef875b25418326cabfbf9a74abd126a5cec2ad905ad5e7fa","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T14:01:26Z","title_canon_sha256":"14b4d353cd98a977fa8bea958cc86fea20cde5d0bc7508136dd06fc9196aa060"},"schema_version":"1.0","source":{"id":"2306.05905","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05905","created_at":"2026-05-22T01:03:13Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05905v2","created_at":"2026-05-22T01:03:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05905","created_at":"2026-05-22T01:03:13Z"},{"alias_kind":"pith_short_12","alias_value":"6U2RO6G6HQNT","created_at":"2026-05-22T01:03:13Z"},{"alias_kind":"pith_short_16","alias_value":"6U2RO6G6HQNTZD2J","created_at":"2026-05-22T01:03:13Z"},{"alias_kind":"pith_short_8","alias_value":"6U2RO6G6","created_at":"2026-05-22T01:03:13Z"}],"graph_snapshots":[{"event_id":"sha256:6eb62574d4a7a8634d16b47c9a49c15f83e1b2b061beef3d6b269a8ce449041c","target":"graph","created_at":"2026-05-22T01:03:13Z","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/2306.05905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A convenient approach to optimally solving combinatorial optimization tasks is the Branch-and-Bound method. Its branching heuristic can be learned to solve a large set of similar tasks. The promising results here are achieved by the recently appeared on-policy reinforcement learning method based on the tree Markov Decision Process. To overcome its main disadvantages, namely, very large training time and unstable training, we propose TreeDQN (Tree Deep Q-Network), a sample-efficient off-policy RL method trained by optimizing the geometric mean of expected return. To theoretically support the tr","authors_text":"A. Kostin, A.V. Savchenko, D. Sorokin, G. Gusev, L. Savchenko","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T14:01:26Z","title":"TreeDQN: Sample-Efficient Off-Policy Reinforcement Learning for Combinatorial Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05905","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":"sha256:3e1d1d3bf05974df03cca0d2e48eb579f93756ad8c19e44d5ff83372586bac4d","target":"record","created_at":"2026-05-22T01:03:13Z","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":"0d5ad5383016b574ef875b25418326cabfbf9a74abd126a5cec2ad905ad5e7fa","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T14:01:26Z","title_canon_sha256":"14b4d353cd98a977fa8bea958cc86fea20cde5d0bc7508136dd06fc9196aa060"},"schema_version":"1.0","source":{"id":"2306.05905","kind":"arxiv","version":2}},"canonical_sha256":"f5351778de3c1b3c8f4969bb5cf4383e3fff5ced2b3476312458aa64f8d0e66a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5351778de3c1b3c8f4969bb5cf4383e3fff5ced2b3476312458aa64f8d0e66a","first_computed_at":"2026-05-22T01:03:13.478660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:13.478660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SVFW/avTljVBOj095GYyWrBYBZnvMrtzWgt604BHhTO5z3mBg3TyEye/m4SQImfn/Hyc++qDgSYF7ahuddIWCQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:13.479376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05905","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e1d1d3bf05974df03cca0d2e48eb579f93756ad8c19e44d5ff83372586bac4d","sha256:6eb62574d4a7a8634d16b47c9a49c15f83e1b2b061beef3d6b269a8ce449041c"],"state_sha256":"8b14bdc0b48875f82f7290d92d4cb788875dedfda367af7334ce7a2243d8eaea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pEAgLr4X0f1HSvl8f9+4Ik7w6ssrsIs6GBn2T5NSqknt5SQoCueBqgKnhMVMTBwJkvJHVrD5nqhjNS2NUw2oCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:47:32.930491Z","bundle_sha256":"7e6e6f293ecacc5226c57d7c44f421f116b0b474166e4cfd449675d8657f1ca3"}}