{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DU2QCFDGF6NFFRY5PUWEYQY4SF","short_pith_number":"pith:DU2QCFDG","canonical_record":{"source":{"id":"2211.01962","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T16:42:40Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"6d45c1b485725205d82aaaf9a1705b1c36b138331820dcd82df26ff4676ce590","abstract_canon_sha256":"0206224b9d068561adddc6fe7643b4b7b3a100f619c1ba836c5a56f11678ccb6"},"schema_version":"1.0"},"canonical_sha256":"1d350114662f9a52c71d7d2c4c431c914272e069de92a1a2a35144d14378da13","source":{"kind":"arxiv","id":"2211.01962","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.01962","created_at":"2026-07-05T06:26:16Z"},{"alias_kind":"arxiv_version","alias_value":"2211.01962v4","created_at":"2026-07-05T06:26:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01962","created_at":"2026-07-05T06:26:16Z"},{"alias_kind":"pith_short_12","alias_value":"DU2QCFDGF6NF","created_at":"2026-07-05T06:26:16Z"},{"alias_kind":"pith_short_16","alias_value":"DU2QCFDGF6NFFRY5","created_at":"2026-07-05T06:26:16Z"},{"alias_kind":"pith_short_8","alias_value":"DU2QCFDG","created_at":"2026-07-05T06:26:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DU2QCFDGF6NFFRY5PUWEYQY4SF","target":"record","payload":{"canonical_record":{"source":{"id":"2211.01962","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T16:42:40Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"6d45c1b485725205d82aaaf9a1705b1c36b138331820dcd82df26ff4676ce590","abstract_canon_sha256":"0206224b9d068561adddc6fe7643b4b7b3a100f619c1ba836c5a56f11678ccb6"},"schema_version":"1.0"},"canonical_sha256":"1d350114662f9a52c71d7d2c4c431c914272e069de92a1a2a35144d14378da13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:16.995980Z","signature_b64":"QnNhBy7yvDswN6Cx7Ch+BOU9gSBysSu54JjjufUmPkVth/PNuTExKU0YJGkYP5GPROdJPPtTR/GdJRzQ5XC6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d350114662f9a52c71d7d2c4c431c914272e069de92a1a2a35144d14378da13","last_reissued_at":"2026-07-05T06:26:16.995513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:16.995513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.01962","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:26:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFlXsfBNyuInOqsTeiOz5BIPSq1MZBYnnzi0xNj7OBANu8mF7Gg7ePWIbY/VaBcXyMBIsg76imFgzmv7zNY1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:55:02.891706Z"},"content_sha256":"179552fc60befe3795a880b89a6eefc4b3ff408ae55edca418b85f8a6750c45d","schema_version":"1.0","event_id":"sha256:179552fc60befe3795a880b89a6eefc4b3ff408ae55edca418b85f8a6750c45d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DU2QCFDGF6NFFRY5PUWEYQY4SF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GEC: A Unified Framework for Interactive Decision Making in MDP, POMDP, and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Zhong, Liwei Wang, Sirui Zheng, Tong Zhang, Wei Xiong, Zhaoran Wang, Zhuoran Yang","submitted_at":"2022-11-03T16:42:40Z","abstract_excerpt":"We study sample efficient reinforcement learning (RL) under the general framework of interactive decision making, which includes Markov decision process (MDP), partially observable Markov decision process (POMDP), and predictive state representation (PSR) as special cases. Toward finding the minimum assumption that empowers sample efficient learning, we propose a novel complexity measure, generalized eluder coefficient (GEC), which characterizes the fundamental tradeoff between exploration and exploitation in online interactive decision making. In specific, GEC captures the hardness of explora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01962","kind":"arxiv","version":4},"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/2211.01962/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":"2026-07-05T06:26:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hiRBmOdn9mJF3Hca+ro01/M2I5jwcJzkyMLy/D5ilhEws3qupU0/bXbqIqIR1fAuw4Y0+3iJ2+el2K1hryssDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:55:02.892774Z"},"content_sha256":"8cc49aaecc30d555d6a0bd7d9400f9069391d9a4a0e6af794669eceab95abc62","schema_version":"1.0","event_id":"sha256:8cc49aaecc30d555d6a0bd7d9400f9069391d9a4a0e6af794669eceab95abc62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DU2QCFDGF6NFFRY5PUWEYQY4SF/bundle.json","state_url":"https://pith.science/pith/DU2QCFDGF6NFFRY5PUWEYQY4SF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DU2QCFDGF6NFFRY5PUWEYQY4SF/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":"2026-08-08T02:55:02Z","links":{"resolver":"https://pith.science/pith/DU2QCFDGF6NFFRY5PUWEYQY4SF","bundle":"https://pith.science/pith/DU2QCFDGF6NFFRY5PUWEYQY4SF/bundle.json","state":"https://pith.science/pith/DU2QCFDGF6NFFRY5PUWEYQY4SF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DU2QCFDGF6NFFRY5PUWEYQY4SF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DU2QCFDGF6NFFRY5PUWEYQY4SF","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":"0206224b9d068561adddc6fe7643b4b7b3a100f619c1ba836c5a56f11678ccb6","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T16:42:40Z","title_canon_sha256":"6d45c1b485725205d82aaaf9a1705b1c36b138331820dcd82df26ff4676ce590"},"schema_version":"1.0","source":{"id":"2211.01962","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.01962","created_at":"2026-07-05T06:26:16Z"},{"alias_kind":"arxiv_version","alias_value":"2211.01962v4","created_at":"2026-07-05T06:26:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01962","created_at":"2026-07-05T06:26:16Z"},{"alias_kind":"pith_short_12","alias_value":"DU2QCFDGF6NF","created_at":"2026-07-05T06:26:16Z"},{"alias_kind":"pith_short_16","alias_value":"DU2QCFDGF6NFFRY5","created_at":"2026-07-05T06:26:16Z"},{"alias_kind":"pith_short_8","alias_value":"DU2QCFDG","created_at":"2026-07-05T06:26:16Z"}],"graph_snapshots":[{"event_id":"sha256:8cc49aaecc30d555d6a0bd7d9400f9069391d9a4a0e6af794669eceab95abc62","target":"graph","created_at":"2026-07-05T06:26:16Z","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/2211.01962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study sample efficient reinforcement learning (RL) under the general framework of interactive decision making, which includes Markov decision process (MDP), partially observable Markov decision process (POMDP), and predictive state representation (PSR) as special cases. Toward finding the minimum assumption that empowers sample efficient learning, we propose a novel complexity measure, generalized eluder coefficient (GEC), which characterizes the fundamental tradeoff between exploration and exploitation in online interactive decision making. In specific, GEC captures the hardness of explora","authors_text":"Han Zhong, Liwei Wang, Sirui Zheng, Tong Zhang, Wei Xiong, Zhaoran Wang, Zhuoran Yang","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T16:42:40Z","title":"GEC: A Unified Framework for Interactive Decision Making in MDP, POMDP, and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01962","kind":"arxiv","version":4},"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":"sha256:179552fc60befe3795a880b89a6eefc4b3ff408ae55edca418b85f8a6750c45d","target":"record","created_at":"2026-07-05T06:26:16Z","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":"0206224b9d068561adddc6fe7643b4b7b3a100f619c1ba836c5a56f11678ccb6","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T16:42:40Z","title_canon_sha256":"6d45c1b485725205d82aaaf9a1705b1c36b138331820dcd82df26ff4676ce590"},"schema_version":"1.0","source":{"id":"2211.01962","kind":"arxiv","version":4}},"canonical_sha256":"1d350114662f9a52c71d7d2c4c431c914272e069de92a1a2a35144d14378da13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d350114662f9a52c71d7d2c4c431c914272e069de92a1a2a35144d14378da13","first_computed_at":"2026-07-05T06:26:16.995513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:16.995513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QnNhBy7yvDswN6Cx7Ch+BOU9gSBysSu54JjjufUmPkVth/PNuTExKU0YJGkYP5GPROdJPPtTR/GdJRzQ5XC6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:16.995980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.01962","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:179552fc60befe3795a880b89a6eefc4b3ff408ae55edca418b85f8a6750c45d","sha256:8cc49aaecc30d555d6a0bd7d9400f9069391d9a4a0e6af794669eceab95abc62"],"state_sha256":"fd8354caaf833e9f4b319f396a2727f54623e5a9678b51ce13029fc5ad3310af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TV4i5t8amy/1sXur7V3z/yCbymmXX2y0IR7CnyjpNckXq4qk0NR0cZyvRYntQxMLAkmizb9Lo5fjbd7BfekiDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:55:02.898755Z","bundle_sha256":"f196f647d203eff8afcce2eeb2a74f03ac6d7820c590d375708ceb575f3ec5cb"}}