{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NBSLF4B4K5TH6EL6SX5R2HID3O","short_pith_number":"pith:NBSLF4B4","canonical_record":{"source":{"id":"2402.11835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T04:58:39Z","cross_cats_sorted":["cs.GT","cs.MA"],"title_canon_sha256":"49252d4c8f2297de00a3a6eba0799987f16c462c391f2a14b13d9bce14dafe34","abstract_canon_sha256":"b391c556757ba168a045ff5c50f22df2ab3d6d529e8598e6fddcc1fed3414bb0"},"schema_version":"1.0"},"canonical_sha256":"6864b2f03c57667f117e95fb1d1d03dba78344d8b7d011abbd29ba2faf56063b","source":{"kind":"arxiv","id":"2402.11835","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11835","created_at":"2026-07-05T07:46:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11835v1","created_at":"2026-07-05T07:46:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11835","created_at":"2026-07-05T07:46:45Z"},{"alias_kind":"pith_short_12","alias_value":"NBSLF4B4K5TH","created_at":"2026-07-05T07:46:45Z"},{"alias_kind":"pith_short_16","alias_value":"NBSLF4B4K5TH6EL6","created_at":"2026-07-05T07:46:45Z"},{"alias_kind":"pith_short_8","alias_value":"NBSLF4B4","created_at":"2026-07-05T07:46:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NBSLF4B4K5TH6EL6SX5R2HID3O","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T04:58:39Z","cross_cats_sorted":["cs.GT","cs.MA"],"title_canon_sha256":"49252d4c8f2297de00a3a6eba0799987f16c462c391f2a14b13d9bce14dafe34","abstract_canon_sha256":"b391c556757ba168a045ff5c50f22df2ab3d6d529e8598e6fddcc1fed3414bb0"},"schema_version":"1.0"},"canonical_sha256":"6864b2f03c57667f117e95fb1d1d03dba78344d8b7d011abbd29ba2faf56063b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:45.066136Z","signature_b64":"u2pzEQyBYJp0cSdQ1i2dSTO1ZxU/1z1SyM7frcIm1ZpUafef6VB47aqqeBvW3nsHaMrWBhhTBu4NxbTwGGtRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6864b2f03c57667f117e95fb1d1d03dba78344d8b7d011abbd29ba2faf56063b","last_reissued_at":"2026-07-05T07:46:45.065793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:45.065793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11835","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":"2026-07-05T07:46:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"72/EhnHpNzxVZZEAsI7/eF2a4DMI2Ut0xFkkZyYIEfojihBZCAvEwP+jsAI1ZIJJNBdi/mt+PIFBVbp5cYqmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:45:55.740205Z"},"content_sha256":"a45f09eef1063cddcead5c9f494c008436ca3d6280308f18e2756917869fae0c","schema_version":"1.0","event_id":"sha256:a45f09eef1063cddcead5c9f494c008436ca3d6280308f18e2756917869fae0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NBSLF4B4K5TH6EL6SX5R2HID3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"David C. Parkes, Hugh Zhang, Luca D'Amico-Wong, Marc Lanctot","submitted_at":"2024-02-19T04:58:39Z","abstract_excerpt":"We propose ABCs (Adaptive Branching through Child stationarity), a best-of-both-worlds algorithm combining Boltzmann Q-learning (BQL), a classic reinforcement learning algorithm for single-agent domains, and counterfactual regret minimization (CFR), a central algorithm for learning in multi-agent domains. ABCs adaptively chooses what fraction of the environment to explore each iteration by measuring the stationarity of the environment's reward and transition dynamics. In Markov decision processes, ABCs converges to the optimal policy with at most an O(A) factor slowdown compared to BQL, where "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11835","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/2402.11835/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":"2026-07-05T07:46:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kbjcJ8r+2rsdPlND03g/DHTPBYzKmoenFMtghNlo2NQO1aRXmjOgedbMxCGttV79JJQgqU3XN2E0fhYnIY6mDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:45:55.740721Z"},"content_sha256":"c02a4ccba30111229950e1d1f139f6aa73311ba886871a2f24bb476f3efe96c9","schema_version":"1.0","event_id":"sha256:c02a4ccba30111229950e1d1f139f6aa73311ba886871a2f24bb476f3efe96c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/bundle.json","state_url":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/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":"2026-08-03T19:45:55Z","links":{"resolver":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O","bundle":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/bundle.json","state":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NBSLF4B4K5TH6EL6SX5R2HID3O","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":"b391c556757ba168a045ff5c50f22df2ab3d6d529e8598e6fddcc1fed3414bb0","cross_cats_sorted":["cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T04:58:39Z","title_canon_sha256":"49252d4c8f2297de00a3a6eba0799987f16c462c391f2a14b13d9bce14dafe34"},"schema_version":"1.0","source":{"id":"2402.11835","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11835","created_at":"2026-07-05T07:46:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11835v1","created_at":"2026-07-05T07:46:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11835","created_at":"2026-07-05T07:46:45Z"},{"alias_kind":"pith_short_12","alias_value":"NBSLF4B4K5TH","created_at":"2026-07-05T07:46:45Z"},{"alias_kind":"pith_short_16","alias_value":"NBSLF4B4K5TH6EL6","created_at":"2026-07-05T07:46:45Z"},{"alias_kind":"pith_short_8","alias_value":"NBSLF4B4","created_at":"2026-07-05T07:46:45Z"}],"graph_snapshots":[{"event_id":"sha256:c02a4ccba30111229950e1d1f139f6aa73311ba886871a2f24bb476f3efe96c9","target":"graph","created_at":"2026-07-05T07:46:45Z","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/2402.11835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose ABCs (Adaptive Branching through Child stationarity), a best-of-both-worlds algorithm combining Boltzmann Q-learning (BQL), a classic reinforcement learning algorithm for single-agent domains, and counterfactual regret minimization (CFR), a central algorithm for learning in multi-agent domains. ABCs adaptively chooses what fraction of the environment to explore each iteration by measuring the stationarity of the environment's reward and transition dynamics. In Markov decision processes, ABCs converges to the optimal policy with at most an O(A) factor slowdown compared to BQL, where ","authors_text":"David C. Parkes, Hugh Zhang, Luca D'Amico-Wong, Marc Lanctot","cross_cats":["cs.GT","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T04:58:39Z","title":"Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11835","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:a45f09eef1063cddcead5c9f494c008436ca3d6280308f18e2756917869fae0c","target":"record","created_at":"2026-07-05T07:46:45Z","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":"b391c556757ba168a045ff5c50f22df2ab3d6d529e8598e6fddcc1fed3414bb0","cross_cats_sorted":["cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T04:58:39Z","title_canon_sha256":"49252d4c8f2297de00a3a6eba0799987f16c462c391f2a14b13d9bce14dafe34"},"schema_version":"1.0","source":{"id":"2402.11835","kind":"arxiv","version":1}},"canonical_sha256":"6864b2f03c57667f117e95fb1d1d03dba78344d8b7d011abbd29ba2faf56063b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6864b2f03c57667f117e95fb1d1d03dba78344d8b7d011abbd29ba2faf56063b","first_computed_at":"2026-07-05T07:46:45.065793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:45.065793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u2pzEQyBYJp0cSdQ1i2dSTO1ZxU/1z1SyM7frcIm1ZpUafef6VB47aqqeBvW3nsHaMrWBhhTBu4NxbTwGGtRBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:45.066136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11835","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a45f09eef1063cddcead5c9f494c008436ca3d6280308f18e2756917869fae0c","sha256:c02a4ccba30111229950e1d1f139f6aa73311ba886871a2f24bb476f3efe96c9"],"state_sha256":"ff3bec704471194abdc7b013e125ee8108c05f714e3c7f8a6372cf06296f534f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1sGwa7oeVqw8nt75rTDK+Gji+ZQs1YRoBZnLft/2+Kvu3aARh82TEB8TfCI8sFuGDRyetLQadJDAwOrbK/UqDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:45:55.745631Z","bundle_sha256":"803ddca5bc5fc8a25aecd1107a66d4c1b9a5c7a0502b0aa895d1f97c3a0b94ed"}}