{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QC3QNDPXUC2LDSFYSZ7V3YS3US","short_pith_number":"pith:QC3QNDPX","canonical_record":{"source":{"id":"1906.09114","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-20T06:32:36Z","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"title_canon_sha256":"ef7daea42c2be913150a0755e8577878c5b103a0faff2cd287295212e7c729dd","abstract_canon_sha256":"789f281accb678d5f8fe93e1d1782989999d6651116b89714ad5615c247beda1"},"schema_version":"1.0"},"canonical_sha256":"80b7068df7a0b4b1c8b8967f5de25ba4a673dcb428ab83d9284c230fe753bc78","source":{"kind":"arxiv","id":"1906.09114","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09114","created_at":"2026-05-17T23:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09114v2","created_at":"2026-05-17T23:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09114","created_at":"2026-05-17T23:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"QC3QNDPXUC2L","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QC3QNDPXUC2LDSFY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QC3QNDPX","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QC3QNDPXUC2LDSFYSZ7V3YS3US","target":"record","payload":{"canonical_record":{"source":{"id":"1906.09114","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-20T06:32:36Z","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"title_canon_sha256":"ef7daea42c2be913150a0755e8577878c5b103a0faff2cd287295212e7c729dd","abstract_canon_sha256":"789f281accb678d5f8fe93e1d1782989999d6651116b89714ad5615c247beda1"},"schema_version":"1.0"},"canonical_sha256":"80b7068df7a0b4b1c8b8967f5de25ba4a673dcb428ab83d9284c230fe753bc78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:02.131359Z","signature_b64":"FnF366IpFvAsUIFBfkyXBT6UnlEKA6GfCCarB6GbfrWWhk8EtuT2oEZ6EaL7qaYSZARP25jY+MbbNngfXQudCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80b7068df7a0b4b1c8b8967f5de25ba4a673dcb428ab83d9284c230fe753bc78","last_reissued_at":"2026-05-17T23:41:02.130724Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:02.130724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.09114","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p4BLq2kKr0w3+7sIIJK415dBVuFa/6nZi+0eZPGV81OYz/bYoRrNBBZW6LmXhaVyMogQjBOLWOu25KUP+h1mBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:53:05.308674Z"},"content_sha256":"fbfd94fb71407f74e012e78b953a4ea6c54023bb929a34f2dac32c7d7a1aae6c","schema_version":"1.0","event_id":"sha256:fbfd94fb71407f74e012e78b953a4ea6c54023bb929a34f2dac32c7d7a1aae6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QC3QNDPXUC2LDSFYSZ7V3YS3US","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near-optimal Bayesian Solution For Unknown Discrete Markov Decision Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aristide Tossou, Christos Dimitrakakis, Debabrota Basu","submitted_at":"2019-06-20T06:32:36Z","abstract_excerpt":"We tackle the problem of acting in an unknown finite and discrete Markov Decision Process (MDP) for which the expected shortest path from any state to any other state is bounded by a finite number $D$. An MDP consists of $S$ states and $A$ possible actions per state. Upon choosing an action $a_t$ at state $s_t$, one receives a real value reward $r_t$, then one transits to a next state $s_{t+1}$. The reward $r_t$ is generated from a fixed reward distribution depending only on $(s_t, a_t)$ and similarly, the next state $s_{t+1}$ is generated from a fixed transition distribution depending only on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09114","kind":"arxiv","version":2},"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":"2026-05-17T23:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xSk8grh2k0iyfWIUe74dodVxfdY8PnrtyGgcPzQaqt6qi5663P29rg1CbGJriZCV3jAIfvpPQu+1wU5uVPYcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:53:05.309328Z"},"content_sha256":"cd835f10fe89f46e2097eca4b1b2ab674f7a7f9448518ea1931169a94a24c607","schema_version":"1.0","event_id":"sha256:cd835f10fe89f46e2097eca4b1b2ab674f7a7f9448518ea1931169a94a24c607"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QC3QNDPXUC2LDSFYSZ7V3YS3US/bundle.json","state_url":"https://pith.science/pith/QC3QNDPXUC2LDSFYSZ7V3YS3US/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QC3QNDPXUC2LDSFYSZ7V3YS3US/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":"2026-05-26T08:53:05Z","links":{"resolver":"https://pith.science/pith/QC3QNDPXUC2LDSFYSZ7V3YS3US","bundle":"https://pith.science/pith/QC3QNDPXUC2LDSFYSZ7V3YS3US/bundle.json","state":"https://pith.science/pith/QC3QNDPXUC2LDSFYSZ7V3YS3US/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QC3QNDPXUC2LDSFYSZ7V3YS3US/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QC3QNDPXUC2LDSFYSZ7V3YS3US","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":"789f281accb678d5f8fe93e1d1782989999d6651116b89714ad5615c247beda1","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-20T06:32:36Z","title_canon_sha256":"ef7daea42c2be913150a0755e8577878c5b103a0faff2cd287295212e7c729dd"},"schema_version":"1.0","source":{"id":"1906.09114","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09114","created_at":"2026-05-17T23:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09114v2","created_at":"2026-05-17T23:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09114","created_at":"2026-05-17T23:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"QC3QNDPXUC2L","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QC3QNDPXUC2LDSFY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QC3QNDPX","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:cd835f10fe89f46e2097eca4b1b2ab674f7a7f9448518ea1931169a94a24c607","target":"graph","created_at":"2026-05-17T23:41:02Z","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 tackle the problem of acting in an unknown finite and discrete Markov Decision Process (MDP) for which the expected shortest path from any state to any other state is bounded by a finite number $D$. An MDP consists of $S$ states and $A$ possible actions per state. Upon choosing an action $a_t$ at state $s_t$, one receives a real value reward $r_t$, then one transits to a next state $s_{t+1}$. The reward $r_t$ is generated from a fixed reward distribution depending only on $(s_t, a_t)$ and similarly, the next state $s_{t+1}$ is generated from a fixed transition distribution depending only on","authors_text":"Aristide Tossou, Christos Dimitrakakis, Debabrota Basu","cross_cats":["cs.AI","cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-20T06:32:36Z","title":"Near-optimal Bayesian Solution For Unknown Discrete Markov Decision Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09114","kind":"arxiv","version":2},"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:fbfd94fb71407f74e012e78b953a4ea6c54023bb929a34f2dac32c7d7a1aae6c","target":"record","created_at":"2026-05-17T23:41:02Z","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":"789f281accb678d5f8fe93e1d1782989999d6651116b89714ad5615c247beda1","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-20T06:32:36Z","title_canon_sha256":"ef7daea42c2be913150a0755e8577878c5b103a0faff2cd287295212e7c729dd"},"schema_version":"1.0","source":{"id":"1906.09114","kind":"arxiv","version":2}},"canonical_sha256":"80b7068df7a0b4b1c8b8967f5de25ba4a673dcb428ab83d9284c230fe753bc78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80b7068df7a0b4b1c8b8967f5de25ba4a673dcb428ab83d9284c230fe753bc78","first_computed_at":"2026-05-17T23:41:02.130724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:02.130724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FnF366IpFvAsUIFBfkyXBT6UnlEKA6GfCCarB6GbfrWWhk8EtuT2oEZ6EaL7qaYSZARP25jY+MbbNngfXQudCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:02.131359Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.09114","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbfd94fb71407f74e012e78b953a4ea6c54023bb929a34f2dac32c7d7a1aae6c","sha256:cd835f10fe89f46e2097eca4b1b2ab674f7a7f9448518ea1931169a94a24c607"],"state_sha256":"37f15333ade2b3259acaaad9a0f20542bc2be7491eb0d6fd214ecef7cce5d6a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P827nPUiEl5Pqw55DHNwTE4iSDCq7hRQ7VI687/4WRuFk0w2r20UzYacWnWlorS3P8IUGjowTEn6mUUpkxQPBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:53:05.312622Z","bundle_sha256":"ad2022bfed99a893a13c08c89c20472da3516e573b01eabe846142defd127865"}}