{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OBA4SKDRW2B2DVNRYRVS5MXZIT","short_pith_number":"pith:OBA4SKDR","canonical_record":{"source":{"id":"2507.12383","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T16:31:17Z","cross_cats_sorted":[],"title_canon_sha256":"800078567b61d73accc0fd4ce68882b5afaa2852aa0c2400b2b879618e706a29","abstract_canon_sha256":"33937186ee26b2fb776f2d51823c82b8501fdd01f82cb290ccd8ff3abe1f4f0b"},"schema_version":"1.0"},"canonical_sha256":"7041c92871b683a1d5b1c46b2eb2f944ece799c852e76f3b9b790df9ac2c5022","source":{"kind":"arxiv","id":"2507.12383","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12383","created_at":"2026-07-05T11:38:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12383v1","created_at":"2026-07-05T11:38:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12383","created_at":"2026-07-05T11:38:19Z"},{"alias_kind":"pith_short_12","alias_value":"OBA4SKDRW2B2","created_at":"2026-07-05T11:38:19Z"},{"alias_kind":"pith_short_16","alias_value":"OBA4SKDRW2B2DVNR","created_at":"2026-07-05T11:38:19Z"},{"alias_kind":"pith_short_8","alias_value":"OBA4SKDR","created_at":"2026-07-05T11:38:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OBA4SKDRW2B2DVNRYRVS5MXZIT","target":"record","payload":{"canonical_record":{"source":{"id":"2507.12383","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T16:31:17Z","cross_cats_sorted":[],"title_canon_sha256":"800078567b61d73accc0fd4ce68882b5afaa2852aa0c2400b2b879618e706a29","abstract_canon_sha256":"33937186ee26b2fb776f2d51823c82b8501fdd01f82cb290ccd8ff3abe1f4f0b"},"schema_version":"1.0"},"canonical_sha256":"7041c92871b683a1d5b1c46b2eb2f944ece799c852e76f3b9b790df9ac2c5022","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:19.395300Z","signature_b64":"jtMi8H19RcWBN2Cy9khPkJnqQGKiVWL9TWkPspSA6iIeUD3rF1dMaKylXh+bOAg0ZJf7UNxT8BXBoIk+PwFQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7041c92871b683a1d5b1c46b2eb2f944ece799c852e76f3b9b790df9ac2c5022","last_reissued_at":"2026-07-05T11:38:19.394821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:19.394821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.12383","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":"2026-07-05T11:38:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yqf3zG7b5KRq+qfAUWv4QjajzAvCBWODr8JWO11SJ/mb0YSF47v/w7xCa8FvYQ+V1KaiDM1EbjdYGa0nCQGXBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:56:42.959129Z"},"content_sha256":"5709f5ac07e01fcde46d882dfbc584c8059aa1b5e9fe7b593815df680c7c0808","schema_version":"1.0","event_id":"sha256:5709f5ac07e01fcde46d882dfbc584c8059aa1b5e9fe7b593815df680c7c0808"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OBA4SKDRW2B2DVNRYRVS5MXZIT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Reinforcement Learning Sample-Efficiency using Local Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arvind Easwaran, Mohit Prashant","submitted_at":"2025-07-16T16:31:17Z","abstract_excerpt":"In this study, we derive Probably Approximately Correct (PAC) bounds on the asymptotic sample-complexity for RL within the infinite-horizon Markov Decision Process (MDP) setting that are sharper than those in existing literature. The premise of our study is twofold: firstly, the further two states are from each other, transition-wise, the less relevant the value of the first state is when learning the $\\epsilon$-optimal value of the second; secondly, the amount of 'effort', sample-complexity-wise, expended in learning the $\\epsilon$-optimal value of a state is independent of the number of samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12383","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/2507.12383/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":"2026-07-05T11:38:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PAR/no7RJ8U4QjbR4jFwYHmCE1BC/FZ3RbHB0tdmyXiqyxJXMKdnpUtLplUxAU43J/EMFi+ezE66ud4QQYUKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:56:42.959748Z"},"content_sha256":"cbb4319f236b5c3140b4edb6ace58946c2db4c240e8b7147ad9ec85910a89fc9","schema_version":"1.0","event_id":"sha256:cbb4319f236b5c3140b4edb6ace58946c2db4c240e8b7147ad9ec85910a89fc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/bundle.json","state_url":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/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":"2026-08-08T20:56:42Z","links":{"resolver":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT","bundle":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/bundle.json","state":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OBA4SKDRW2B2DVNRYRVS5MXZIT","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":"33937186ee26b2fb776f2d51823c82b8501fdd01f82cb290ccd8ff3abe1f4f0b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T16:31:17Z","title_canon_sha256":"800078567b61d73accc0fd4ce68882b5afaa2852aa0c2400b2b879618e706a29"},"schema_version":"1.0","source":{"id":"2507.12383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12383","created_at":"2026-07-05T11:38:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12383v1","created_at":"2026-07-05T11:38:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12383","created_at":"2026-07-05T11:38:19Z"},{"alias_kind":"pith_short_12","alias_value":"OBA4SKDRW2B2","created_at":"2026-07-05T11:38:19Z"},{"alias_kind":"pith_short_16","alias_value":"OBA4SKDRW2B2DVNR","created_at":"2026-07-05T11:38:19Z"},{"alias_kind":"pith_short_8","alias_value":"OBA4SKDR","created_at":"2026-07-05T11:38:19Z"}],"graph_snapshots":[{"event_id":"sha256:cbb4319f236b5c3140b4edb6ace58946c2db4c240e8b7147ad9ec85910a89fc9","target":"graph","created_at":"2026-07-05T11:38:19Z","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/2507.12383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we derive Probably Approximately Correct (PAC) bounds on the asymptotic sample-complexity for RL within the infinite-horizon Markov Decision Process (MDP) setting that are sharper than those in existing literature. The premise of our study is twofold: firstly, the further two states are from each other, transition-wise, the less relevant the value of the first state is when learning the $\\epsilon$-optimal value of the second; secondly, the amount of 'effort', sample-complexity-wise, expended in learning the $\\epsilon$-optimal value of a state is independent of the number of samp","authors_text":"Arvind Easwaran, Mohit Prashant","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T16:31:17Z","title":"Improving Reinforcement Learning Sample-Efficiency using Local Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12383","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":"sha256:5709f5ac07e01fcde46d882dfbc584c8059aa1b5e9fe7b593815df680c7c0808","target":"record","created_at":"2026-07-05T11:38:19Z","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":"33937186ee26b2fb776f2d51823c82b8501fdd01f82cb290ccd8ff3abe1f4f0b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T16:31:17Z","title_canon_sha256":"800078567b61d73accc0fd4ce68882b5afaa2852aa0c2400b2b879618e706a29"},"schema_version":"1.0","source":{"id":"2507.12383","kind":"arxiv","version":1}},"canonical_sha256":"7041c92871b683a1d5b1c46b2eb2f944ece799c852e76f3b9b790df9ac2c5022","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7041c92871b683a1d5b1c46b2eb2f944ece799c852e76f3b9b790df9ac2c5022","first_computed_at":"2026-07-05T11:38:19.394821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:19.394821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jtMi8H19RcWBN2Cy9khPkJnqQGKiVWL9TWkPspSA6iIeUD3rF1dMaKylXh+bOAg0ZJf7UNxT8BXBoIk+PwFQCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:19.395300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5709f5ac07e01fcde46d882dfbc584c8059aa1b5e9fe7b593815df680c7c0808","sha256:cbb4319f236b5c3140b4edb6ace58946c2db4c240e8b7147ad9ec85910a89fc9"],"state_sha256":"e64bb12bbb638cb1eec5f12d915bbbfce4ef35c2d0c96fc8a0790b7a6d6f0939"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jex1zXh3C1lbhCbAUwMqAXmZX7vVQLhN2ell2PTCmlYfRNYfWIWhM5wTWMv9IeTe/DhZM9yIxYyuY41GMv9dCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:56:42.965176Z","bundle_sha256":"0b82ad13d43f8fa6b6a7e9013245b9cde28ec2fe9d5e9b430fd53d6bcb3c6dd5"}}