{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CDTHA7PCHT2QYOJYXHAAULO6W2","short_pith_number":"pith:CDTHA7PC","canonical_record":{"source":{"id":"2210.15755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-27T20:19:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b10a881b71b1b3859e9597abc17524c82297995417774f01a11cb7ffac9e8bf1","abstract_canon_sha256":"d49361c5ef27602cff6298c94ce3169a54070c4000fcef59765746149f1d8c4c"},"schema_version":"1.0"},"canonical_sha256":"10e6707de23cf50c3938b9c00a2ddeb6abd65f904c8d5164f6e00d0b70865e31","source":{"kind":"arxiv","id":"2210.15755","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15755","created_at":"2026-07-05T05:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15755v1","created_at":"2026-07-05T05:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15755","created_at":"2026-07-05T05:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"CDTHA7PCHT2Q","created_at":"2026-07-05T05:11:10Z"},{"alias_kind":"pith_short_16","alias_value":"CDTHA7PCHT2QYOJY","created_at":"2026-07-05T05:11:10Z"},{"alias_kind":"pith_short_8","alias_value":"CDTHA7PC","created_at":"2026-07-05T05:11:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CDTHA7PCHT2QYOJYXHAAULO6W2","target":"record","payload":{"canonical_record":{"source":{"id":"2210.15755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-27T20:19:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b10a881b71b1b3859e9597abc17524c82297995417774f01a11cb7ffac9e8bf1","abstract_canon_sha256":"d49361c5ef27602cff6298c94ce3169a54070c4000fcef59765746149f1d8c4c"},"schema_version":"1.0"},"canonical_sha256":"10e6707de23cf50c3938b9c00a2ddeb6abd65f904c8d5164f6e00d0b70865e31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:10.526141Z","signature_b64":"+7Jwl+iCYXooX0A0u3dpUTCvYjx9Mxm1uxGk7chJXZmXYR8Y4fPo/x4hZuJwTwp98LUboWQmfxzAo8db7tDPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10e6707de23cf50c3938b9c00a2ddeb6abd65f904c8d5164f6e00d0b70865e31","last_reissued_at":"2026-07-05T05:11:10.525670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:10.525670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.15755","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":"2026-07-05T05:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wFeirqk6MybBCb5N6PBCMSTpIU6nQKyHOnQ6GCeIxJcpoC0+RPSk++e+3el14iNo1LfhuL2R1cNV5wgbFiR/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:55:27.116386Z"},"content_sha256":"9028f225ccd8846e807b578d49673dd4233efd2ce56a8fa0f25d416d8ebe836d","schema_version":"1.0","event_id":"sha256:9028f225ccd8846e807b578d49673dd4233efd2ce56a8fa0f25d416d8ebe836d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CDTHA7PCHT2QYOJYXHAAULO6W2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Confident Approximate Policy Iteration for Efficient Local Planning in $q^\\pi$-realizable MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Gy\\\"orgy, Csaba Szepesv\\'ari, Gell\\'ert Weisz, Tadashi Kozuno","submitted_at":"2022-10-27T20:19:31Z","abstract_excerpt":"We consider approximate dynamic programming in $\\gamma$-discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first contribution is a new variant of Approximate Policy Iteration (API), called Confident Approximate Policy Iteration (CAPI), which computes a deterministic stationary policy with an optimal error bound scaling linearly with the product of the effective horizon $H$ and the worst-case approximation error $\\epsilon$ of the action-value functions of stationary policies. This improvement over API (whose error scales with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15755","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/2210.15755/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":"2026-07-05T05:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1JbgwTWiqkiJU/npzUoe9VN2mVyILsMMBXX4XdP45PIOVeouofz2QVO4VEA8F47yvMiUL3RcdSBmBCYPgFNIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:55:27.116943Z"},"content_sha256":"ba15bb08930eb5bca38b0e6066ba471d861f7a96a5021b388188a7bf8bf425d7","schema_version":"1.0","event_id":"sha256:ba15bb08930eb5bca38b0e6066ba471d861f7a96a5021b388188a7bf8bf425d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/bundle.json","state_url":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/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":"2026-08-06T15:55:27Z","links":{"resolver":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2","bundle":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/bundle.json","state":"https://pith.science/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CDTHA7PCHT2QYOJYXHAAULO6W2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CDTHA7PCHT2QYOJYXHAAULO6W2","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":"d49361c5ef27602cff6298c94ce3169a54070c4000fcef59765746149f1d8c4c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-27T20:19:31Z","title_canon_sha256":"b10a881b71b1b3859e9597abc17524c82297995417774f01a11cb7ffac9e8bf1"},"schema_version":"1.0","source":{"id":"2210.15755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15755","created_at":"2026-07-05T05:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15755v1","created_at":"2026-07-05T05:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15755","created_at":"2026-07-05T05:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"CDTHA7PCHT2Q","created_at":"2026-07-05T05:11:10Z"},{"alias_kind":"pith_short_16","alias_value":"CDTHA7PCHT2QYOJY","created_at":"2026-07-05T05:11:10Z"},{"alias_kind":"pith_short_8","alias_value":"CDTHA7PC","created_at":"2026-07-05T05:11:10Z"}],"graph_snapshots":[{"event_id":"sha256:ba15bb08930eb5bca38b0e6066ba471d861f7a96a5021b388188a7bf8bf425d7","target":"graph","created_at":"2026-07-05T05:11:10Z","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/2210.15755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider approximate dynamic programming in $\\gamma$-discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first contribution is a new variant of Approximate Policy Iteration (API), called Confident Approximate Policy Iteration (CAPI), which computes a deterministic stationary policy with an optimal error bound scaling linearly with the product of the effective horizon $H$ and the worst-case approximation error $\\epsilon$ of the action-value functions of stationary policies. This improvement over API (whose error scales with ","authors_text":"Andr\\'as Gy\\\"orgy, Csaba Szepesv\\'ari, Gell\\'ert Weisz, Tadashi Kozuno","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-27T20:19:31Z","title":"Confident Approximate Policy Iteration for Efficient Local Planning in $q^\\pi$-realizable MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15755","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":"sha256:9028f225ccd8846e807b578d49673dd4233efd2ce56a8fa0f25d416d8ebe836d","target":"record","created_at":"2026-07-05T05:11:10Z","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":"d49361c5ef27602cff6298c94ce3169a54070c4000fcef59765746149f1d8c4c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-27T20:19:31Z","title_canon_sha256":"b10a881b71b1b3859e9597abc17524c82297995417774f01a11cb7ffac9e8bf1"},"schema_version":"1.0","source":{"id":"2210.15755","kind":"arxiv","version":1}},"canonical_sha256":"10e6707de23cf50c3938b9c00a2ddeb6abd65f904c8d5164f6e00d0b70865e31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10e6707de23cf50c3938b9c00a2ddeb6abd65f904c8d5164f6e00d0b70865e31","first_computed_at":"2026-07-05T05:11:10.525670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:10.525670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+7Jwl+iCYXooX0A0u3dpUTCvYjx9Mxm1uxGk7chJXZmXYR8Y4fPo/x4hZuJwTwp98LUboWQmfxzAo8db7tDPDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:10.526141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.15755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9028f225ccd8846e807b578d49673dd4233efd2ce56a8fa0f25d416d8ebe836d","sha256:ba15bb08930eb5bca38b0e6066ba471d861f7a96a5021b388188a7bf8bf425d7"],"state_sha256":"ddc2d53cee891ff24a7d17ccd81031c562919343ff3a72943ba38e05b6a17d0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FUp24RGTSg/KB+wyxVR6eAOKziyF1q7IURJVaQkCDo03nonLdwM2e0eW3mdc1zQ0DxaIAQc5+WdXhKDG1E+9Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:55:27.120778Z","bundle_sha256":"bb431a8ca09295f46bfbfb479162d2d090ad1013875225f42f835f8b0719cf60"}}