{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:5RWWQMW6PW6SEY6WD4H5BWJ5B4","short_pith_number":"pith:5RWWQMW6","canonical_record":{"source":{"id":"1510.08906","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-10-29T21:14:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0cdbd9e98377d125a6dec853373839e2dd6777caab7a76f0691bd8211ba0c2ef","abstract_canon_sha256":"1331402d8840a03b9fb14642a9607faeb144f70020c06f7b796e3b8d100b5f28"},"schema_version":"1.0"},"canonical_sha256":"ec6d6832de7dbd2263d61f0fd0d93d0f3e9d3024f92404f7f70b74359651524f","source":{"kind":"arxiv","id":"1510.08906","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.08906","created_at":"2026-05-18T01:15:06Z"},{"alias_kind":"arxiv_version","alias_value":"1510.08906v3","created_at":"2026-05-18T01:15:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.08906","created_at":"2026-05-18T01:15:06Z"},{"alias_kind":"pith_short_12","alias_value":"5RWWQMW6PW6S","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"5RWWQMW6PW6SEY6W","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"5RWWQMW6","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:5RWWQMW6PW6SEY6WD4H5BWJ5B4","target":"record","payload":{"canonical_record":{"source":{"id":"1510.08906","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-10-29T21:14:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0cdbd9e98377d125a6dec853373839e2dd6777caab7a76f0691bd8211ba0c2ef","abstract_canon_sha256":"1331402d8840a03b9fb14642a9607faeb144f70020c06f7b796e3b8d100b5f28"},"schema_version":"1.0"},"canonical_sha256":"ec6d6832de7dbd2263d61f0fd0d93d0f3e9d3024f92404f7f70b74359651524f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:06.590803Z","signature_b64":"VOftSVtJXMx9VG8pEtDNp65tqaQWjhl2w6APtcOVv6OgcLDN3bD4YedJTHx17wb2jWsDOc7HWCqdVF4Mh0brBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec6d6832de7dbd2263d61f0fd0d93d0f3e9d3024f92404f7f70b74359651524f","last_reissued_at":"2026-05-18T01:15:06.590292Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:06.590292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1510.08906","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:15:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ncugfeSUZlFii3+NbXn5elQZk23zWXbyCOYL4fmsNfhP/S3jMpCHKqdRgSNIjOetSnXi6wL+/XmbETCGs6vRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T18:18:47.767951Z"},"content_sha256":"8f19d73177e3b15e3a148075fec8f7cf5d5f051017348c31ac9003e15a541e85","schema_version":"1.0","event_id":"sha256:8f19d73177e3b15e3a148075fec8f7cf5d5f051017348c31ac9003e15a541e85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:5RWWQMW6PW6SEY6WD4H5BWJ5B4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Christoph Dann, Emma Brunskill","submitted_at":"2015-10-29T21:14:42Z","abstract_excerpt":"Recently, there has been significant progress in understanding reinforcement learning in discounted infinite-horizon Markov decision processes (MDPs) by deriving tight sample complexity bounds. However, in many real-world applications, an interactive learning agent operates for a fixed or bounded period of time, for example tutoring students for exams or handling customer service requests. Such scenarios can often be better treated as episodic fixed-horizon MDPs, for which only looser bounds on the sample complexity exist. A natural notion of sample complexity in this setting is the number of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.08906","kind":"arxiv","version":3},"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":"2026-05-18T01:15:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HGxvMN2TMNT6BvXOScBQ/nDzyYzuhwK3QAY+G+TeeRbZSwZ6tmnEwYObhCC/DPlA8XiiCwzi/yi/K/va4baCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T18:18:47.768301Z"},"content_sha256":"5d965313b1c59cf5e8b01fc8600ad13f0d16a7bf8e54ed552a1e9ea4f9be7fbb","schema_version":"1.0","event_id":"sha256:5d965313b1c59cf5e8b01fc8600ad13f0d16a7bf8e54ed552a1e9ea4f9be7fbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5RWWQMW6PW6SEY6WD4H5BWJ5B4/bundle.json","state_url":"https://pith.science/pith/5RWWQMW6PW6SEY6WD4H5BWJ5B4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5RWWQMW6PW6SEY6WD4H5BWJ5B4/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":"2026-06-03T18:18:47Z","links":{"resolver":"https://pith.science/pith/5RWWQMW6PW6SEY6WD4H5BWJ5B4","bundle":"https://pith.science/pith/5RWWQMW6PW6SEY6WD4H5BWJ5B4/bundle.json","state":"https://pith.science/pith/5RWWQMW6PW6SEY6WD4H5BWJ5B4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5RWWQMW6PW6SEY6WD4H5BWJ5B4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:5RWWQMW6PW6SEY6WD4H5BWJ5B4","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":"1331402d8840a03b9fb14642a9607faeb144f70020c06f7b796e3b8d100b5f28","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-10-29T21:14:42Z","title_canon_sha256":"0cdbd9e98377d125a6dec853373839e2dd6777caab7a76f0691bd8211ba0c2ef"},"schema_version":"1.0","source":{"id":"1510.08906","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.08906","created_at":"2026-05-18T01:15:06Z"},{"alias_kind":"arxiv_version","alias_value":"1510.08906v3","created_at":"2026-05-18T01:15:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.08906","created_at":"2026-05-18T01:15:06Z"},{"alias_kind":"pith_short_12","alias_value":"5RWWQMW6PW6S","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"5RWWQMW6PW6SEY6W","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"5RWWQMW6","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:5d965313b1c59cf5e8b01fc8600ad13f0d16a7bf8e54ed552a1e9ea4f9be7fbb","target":"graph","created_at":"2026-05-18T01:15:06Z","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":"Recently, there has been significant progress in understanding reinforcement learning in discounted infinite-horizon Markov decision processes (MDPs) by deriving tight sample complexity bounds. However, in many real-world applications, an interactive learning agent operates for a fixed or bounded period of time, for example tutoring students for exams or handling customer service requests. Such scenarios can often be better treated as episodic fixed-horizon MDPs, for which only looser bounds on the sample complexity exist. A natural notion of sample complexity in this setting is the number of ","authors_text":"Christoph Dann, Emma Brunskill","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-10-29T21:14:42Z","title":"Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.08906","kind":"arxiv","version":3},"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":"sha256:8f19d73177e3b15e3a148075fec8f7cf5d5f051017348c31ac9003e15a541e85","target":"record","created_at":"2026-05-18T01:15:06Z","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":"1331402d8840a03b9fb14642a9607faeb144f70020c06f7b796e3b8d100b5f28","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-10-29T21:14:42Z","title_canon_sha256":"0cdbd9e98377d125a6dec853373839e2dd6777caab7a76f0691bd8211ba0c2ef"},"schema_version":"1.0","source":{"id":"1510.08906","kind":"arxiv","version":3}},"canonical_sha256":"ec6d6832de7dbd2263d61f0fd0d93d0f3e9d3024f92404f7f70b74359651524f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec6d6832de7dbd2263d61f0fd0d93d0f3e9d3024f92404f7f70b74359651524f","first_computed_at":"2026-05-18T01:15:06.590292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:15:06.590292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VOftSVtJXMx9VG8pEtDNp65tqaQWjhl2w6APtcOVv6OgcLDN3bD4YedJTHx17wb2jWsDOc7HWCqdVF4Mh0brBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:15:06.590803Z","signed_message":"canonical_sha256_bytes"},"source_id":"1510.08906","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f19d73177e3b15e3a148075fec8f7cf5d5f051017348c31ac9003e15a541e85","sha256:5d965313b1c59cf5e8b01fc8600ad13f0d16a7bf8e54ed552a1e9ea4f9be7fbb"],"state_sha256":"b38d5d497931ba77775e54bb7dbb9b98281d3e83c00c56db87b4f96492800535"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FdNjUFxxDOtW/kVMcJimOQ5qEQttVNKOakxdMisjagYIU2Udb9XddxQ9cEid0Ze6a3FfvAeuwPAeUukunkJPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T18:18:47.770264Z","bundle_sha256":"ef07076e5a31023a327cba6ac22164bd49416009f95ed31327dc0855eab098b5"}}