{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:ICBHFYGXWX4KD7PKMVG6DWQZ2O","short_pith_number":"pith:ICBHFYGX","canonical_record":{"source":{"id":"1206.3231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-13T12:32:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"505e94c03c359ca5c3b55e6dce79712c9e2a1b5c62495e1df1b4feb73152b0b8","abstract_canon_sha256":"cb7752f0ca01b39e665e90806f9e68228873d2e571e7343de070e2b1bfb65c0e"},"schema_version":"1.0"},"canonical_sha256":"408272e0d7b5f8a1fdea654de1da19d398d793b94da979bcdecf125f29b9a326","source":{"kind":"arxiv","id":"1206.3231","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.3231","created_at":"2026-05-18T03:53:31Z"},{"alias_kind":"arxiv_version","alias_value":"1206.3231v1","created_at":"2026-05-18T03:53:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.3231","created_at":"2026-05-18T03:53:31Z"},{"alias_kind":"pith_short_12","alias_value":"ICBHFYGXWX4K","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"ICBHFYGXWX4KD7PK","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"ICBHFYGX","created_at":"2026-05-18T12:27:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:ICBHFYGXWX4KD7PKMVG6DWQZ2O","target":"record","payload":{"canonical_record":{"source":{"id":"1206.3231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-13T12:32:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"505e94c03c359ca5c3b55e6dce79712c9e2a1b5c62495e1df1b4feb73152b0b8","abstract_canon_sha256":"cb7752f0ca01b39e665e90806f9e68228873d2e571e7343de070e2b1bfb65c0e"},"schema_version":"1.0"},"canonical_sha256":"408272e0d7b5f8a1fdea654de1da19d398d793b94da979bcdecf125f29b9a326","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:53:31.182008Z","signature_b64":"vMQgGS5hT05ciEXvsk2KDVWU3jWMCINPwN4zzz8Ccb4chIPMA7oCwTzm21NkNiJ0toa/QelJlply6dopCTs6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"408272e0d7b5f8a1fdea654de1da19d398d793b94da979bcdecf125f29b9a326","last_reissued_at":"2026-05-18T03:53:31.181328Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:53:31.181328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1206.3231","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":"2026-05-18T03:53:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QIYcahFTrstiONfQ7/nupLLMTBcTev4wO6qosbWx8XEkzIEOGbYa50zTHWz6CGsY2nqKyYQZZfqhasb4t6l8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T20:03:03.010698Z"},"content_sha256":"d6c035572826da83d72ef83d1ab8406621df571ad0a0400bb49d6ea9786dfbb6","schema_version":"1.0","event_id":"sha256:d6c035572826da83d72ef83d1ab8406621df571ad0a0400bb49d6ea9786dfbb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:ICBHFYGXWX4KD7PKMVG6DWQZ2O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CORL: A Continuous-state Offset-dynamics Reinforcement Learner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bethany Leffler, Emma Brunskill, Lihong Li, Michael L. Littman, Nicholas Roy","submitted_at":"2012-06-13T12:32:13Z","abstract_excerpt":"Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinforcementlearning algorithm for learning in these domains and prove for certain environments the algorithm is probably approximately correct with a sample complexity that scales polynomially with the state-space dimension. Unfortunately, no optimal planning techniques exist in general for such problems; instead we use fitted value iteration to solve the learned MDP, and include the error due to approximate planning in ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.3231","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":"2026-05-18T03:53:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qZjtuBO4DQs6tkx97L8kp48culFDLRNGM2B2P4zf0xh2nFpzx8PERLvqRjOi4ngpx2CqPBASPkpHVfQJHxVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T20:03:03.011050Z"},"content_sha256":"302381b689e1961050e181820f3a9c5de5f243020fcae0f51dd3424bed0536b5","schema_version":"1.0","event_id":"sha256:302381b689e1961050e181820f3a9c5de5f243020fcae0f51dd3424bed0536b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICBHFYGXWX4KD7PKMVG6DWQZ2O/bundle.json","state_url":"https://pith.science/pith/ICBHFYGXWX4KD7PKMVG6DWQZ2O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICBHFYGXWX4KD7PKMVG6DWQZ2O/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":"2026-06-10T20:03:03Z","links":{"resolver":"https://pith.science/pith/ICBHFYGXWX4KD7PKMVG6DWQZ2O","bundle":"https://pith.science/pith/ICBHFYGXWX4KD7PKMVG6DWQZ2O/bundle.json","state":"https://pith.science/pith/ICBHFYGXWX4KD7PKMVG6DWQZ2O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICBHFYGXWX4KD7PKMVG6DWQZ2O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:ICBHFYGXWX4KD7PKMVG6DWQZ2O","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":"cb7752f0ca01b39e665e90806f9e68228873d2e571e7343de070e2b1bfb65c0e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-13T12:32:13Z","title_canon_sha256":"505e94c03c359ca5c3b55e6dce79712c9e2a1b5c62495e1df1b4feb73152b0b8"},"schema_version":"1.0","source":{"id":"1206.3231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.3231","created_at":"2026-05-18T03:53:31Z"},{"alias_kind":"arxiv_version","alias_value":"1206.3231v1","created_at":"2026-05-18T03:53:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.3231","created_at":"2026-05-18T03:53:31Z"},{"alias_kind":"pith_short_12","alias_value":"ICBHFYGXWX4K","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"ICBHFYGXWX4KD7PK","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"ICBHFYGX","created_at":"2026-05-18T12:27:09Z"}],"graph_snapshots":[{"event_id":"sha256:302381b689e1961050e181820f3a9c5de5f243020fcae0f51dd3424bed0536b5","target":"graph","created_at":"2026-05-18T03:53:31Z","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":"Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinforcementlearning algorithm for learning in these domains and prove for certain environments the algorithm is probably approximately correct with a sample complexity that scales polynomially with the state-space dimension. Unfortunately, no optimal planning techniques exist in general for such problems; instead we use fitted value iteration to solve the learned MDP, and include the error due to approximate planning in ou","authors_text":"Bethany Leffler, Emma Brunskill, Lihong Li, Michael L. Littman, Nicholas Roy","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-13T12:32:13Z","title":"CORL: A Continuous-state Offset-dynamics Reinforcement Learner"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.3231","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:d6c035572826da83d72ef83d1ab8406621df571ad0a0400bb49d6ea9786dfbb6","target":"record","created_at":"2026-05-18T03:53:31Z","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":"cb7752f0ca01b39e665e90806f9e68228873d2e571e7343de070e2b1bfb65c0e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-13T12:32:13Z","title_canon_sha256":"505e94c03c359ca5c3b55e6dce79712c9e2a1b5c62495e1df1b4feb73152b0b8"},"schema_version":"1.0","source":{"id":"1206.3231","kind":"arxiv","version":1}},"canonical_sha256":"408272e0d7b5f8a1fdea654de1da19d398d793b94da979bcdecf125f29b9a326","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"408272e0d7b5f8a1fdea654de1da19d398d793b94da979bcdecf125f29b9a326","first_computed_at":"2026-05-18T03:53:31.181328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:53:31.181328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vMQgGS5hT05ciEXvsk2KDVWU3jWMCINPwN4zzz8Ccb4chIPMA7oCwTzm21NkNiJ0toa/QelJlply6dopCTs6Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:53:31.182008Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.3231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6c035572826da83d72ef83d1ab8406621df571ad0a0400bb49d6ea9786dfbb6","sha256:302381b689e1961050e181820f3a9c5de5f243020fcae0f51dd3424bed0536b5"],"state_sha256":"f851dc01053d2c2d37324e84706d1ba0e329630175c68fe3c64f9105835709d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVL6J8mhgScn68/fair45738WClq/EBPDdqFCfF4fGqrna6cqWk8HVgBfzINrKs5o155xMPywJsPumZfwpHcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T20:03:03.012994Z","bundle_sha256":"a67f1e6b4dac51b5291fa95911a44f9321c8861cc8989f24e9b7ae90f3ef64a3"}}