{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:XSMH6XH2MKEBQZSOCPK74BWFZK","short_pith_number":"pith:XSMH6XH2","canonical_record":{"source":{"id":"1207.4114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-07-11T14:43:04Z","cross_cats_sorted":[],"title_canon_sha256":"17151a3de3688cc2af74d4c27f7dccf5bfd3e6e57ccff4f0069db77630f1cccd","abstract_canon_sha256":"649583ad31fbafa578d07eccec532eb218105adc6301b1c34cff82b7b9c41d39"},"schema_version":"1.0"},"canonical_sha256":"bc987f5cfa628818664e13d5fe06c5cabd96d9f4efdd70ed6001ff81906f012b","source":{"kind":"arxiv","id":"1207.4114","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.4114","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"1207.4114v1","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4114","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"XSMH6XH2MKEB","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"XSMH6XH2MKEBQZSO","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"XSMH6XH2","created_at":"2026-05-18T12:27:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:XSMH6XH2MKEBQZSOCPK74BWFZK","target":"record","payload":{"canonical_record":{"source":{"id":"1207.4114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-07-11T14:43:04Z","cross_cats_sorted":[],"title_canon_sha256":"17151a3de3688cc2af74d4c27f7dccf5bfd3e6e57ccff4f0069db77630f1cccd","abstract_canon_sha256":"649583ad31fbafa578d07eccec532eb218105adc6301b1c34cff82b7b9c41d39"},"schema_version":"1.0"},"canonical_sha256":"bc987f5cfa628818664e13d5fe06c5cabd96d9f4efdd70ed6001ff81906f012b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:50:47.950455Z","signature_b64":"30DFp4x68nllKCcVUjei7pcpg1VHkM+5UTwIpQcYYRB0izbB03GZUVTXZWj0CW/+Z+qCuO184ZyS2uz6xfMBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc987f5cfa628818664e13d5fe06c5cabd96d9f4efdd70ed6001ff81906f012b","last_reissued_at":"2026-05-18T03:50:47.949830Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:50:47.949830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1207.4114","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":"2026-05-18T03:50:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oFS3VQy6GUF5xZixz9qe9ynD8AK5sj/T8Pq34cpeCL+tdKYuUTQkxx6GKhb92qcy5MgR8JLhaTOEraN8iuGSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:34:47.490193Z"},"content_sha256":"5c6b704f3d70e42aacaae3db1775c9e47e3f526b47d2959e1b6da6982888458c","schema_version":"1.0","event_id":"sha256:5c6b704f3d70e42aacaae3db1775c9e47e3f526b47d2959e1b6da6982888458c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:XSMH6XH2MKEBQZSOCPK74BWFZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Metrics for Finite Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Doina Precup, Norman Ferns, Prakash Panangaden","submitted_at":"2012-07-11T14:43:04Z","abstract_excerpt":"We present metrics for measuring the similarity of states in a finite Markov decision process (MDP). The formulation of our metrics is based on the notion of bisimulation for MDPs, with an aim towards solving discounted infinite horizon reinforcement learning tasks. Such metrics can be used to aggregate states, as well as to better structure other value function approximators (e.g., memory-based or nearest-neighbor approximators). We provide bounds that relate our metric distances to the optimal values of states in the given MDP."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.4114","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":""},"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":"2026-05-18T03:50:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hrsXEZZRHpelMeUNcHqJRSfCLt2knROJbpk/fQP1mmDSpQWP3Z9pp4yfIHyZmAs/knwv7C8GOdV0gbFGnPZaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:34:47.490899Z"},"content_sha256":"2cb2dc286793e497b022d16b3dddadeabe526c1bef0d68753f4d17f0295bb0fc","schema_version":"1.0","event_id":"sha256:2cb2dc286793e497b022d16b3dddadeabe526c1bef0d68753f4d17f0295bb0fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/bundle.json","state_url":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/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":"2026-05-27T04:34:47Z","links":{"resolver":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK","bundle":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/bundle.json","state":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:XSMH6XH2MKEBQZSOCPK74BWFZK","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":"649583ad31fbafa578d07eccec532eb218105adc6301b1c34cff82b7b9c41d39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-07-11T14:43:04Z","title_canon_sha256":"17151a3de3688cc2af74d4c27f7dccf5bfd3e6e57ccff4f0069db77630f1cccd"},"schema_version":"1.0","source":{"id":"1207.4114","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.4114","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"1207.4114v1","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4114","created_at":"2026-05-18T03:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"XSMH6XH2MKEB","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"XSMH6XH2MKEBQZSO","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"XSMH6XH2","created_at":"2026-05-18T12:27:27Z"}],"graph_snapshots":[{"event_id":"sha256:2cb2dc286793e497b022d16b3dddadeabe526c1bef0d68753f4d17f0295bb0fc","target":"graph","created_at":"2026-05-18T03:50:47Z","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"},"paper":{"abstract_excerpt":"We present metrics for measuring the similarity of states in a finite Markov decision process (MDP). The formulation of our metrics is based on the notion of bisimulation for MDPs, with an aim towards solving discounted infinite horizon reinforcement learning tasks. Such metrics can be used to aggregate states, as well as to better structure other value function approximators (e.g., memory-based or nearest-neighbor approximators). We provide bounds that relate our metric distances to the optimal values of states in the given MDP.","authors_text":"Doina Precup, Norman Ferns, Prakash Panangaden","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-07-11T14:43:04Z","title":"Metrics for Finite Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.4114","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":"sha256:5c6b704f3d70e42aacaae3db1775c9e47e3f526b47d2959e1b6da6982888458c","target":"record","created_at":"2026-05-18T03:50:47Z","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":"649583ad31fbafa578d07eccec532eb218105adc6301b1c34cff82b7b9c41d39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-07-11T14:43:04Z","title_canon_sha256":"17151a3de3688cc2af74d4c27f7dccf5bfd3e6e57ccff4f0069db77630f1cccd"},"schema_version":"1.0","source":{"id":"1207.4114","kind":"arxiv","version":1}},"canonical_sha256":"bc987f5cfa628818664e13d5fe06c5cabd96d9f4efdd70ed6001ff81906f012b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc987f5cfa628818664e13d5fe06c5cabd96d9f4efdd70ed6001ff81906f012b","first_computed_at":"2026-05-18T03:50:47.949830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:50:47.949830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"30DFp4x68nllKCcVUjei7pcpg1VHkM+5UTwIpQcYYRB0izbB03GZUVTXZWj0CW/+Z+qCuO184ZyS2uz6xfMBDg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:50:47.950455Z","signed_message":"canonical_sha256_bytes"},"source_id":"1207.4114","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c6b704f3d70e42aacaae3db1775c9e47e3f526b47d2959e1b6da6982888458c","sha256:2cb2dc286793e497b022d16b3dddadeabe526c1bef0d68753f4d17f0295bb0fc"],"state_sha256":"0c72f176b4cadeabe1f90dd2c0321ca387fa6ef4718730f11d7435b58dfd2524"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WG9XErOY5bVMWFXh4XuR78k2oTZMopHsMK5ga4H5aYdTtGIVyh+Li7wF0C5ZibBVwV78nGl9aK4uCoro6Ac8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T04:34:47.494327Z","bundle_sha256":"1056deeb441be65cfe32b3d5aa4e1280e0d5c75b9fbbf9eac83f3e991ca462e3"}}