{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PXSFFQ4RBGGVXSMGD3PBKB7O44","short_pith_number":"pith:PXSFFQ4R","canonical_record":{"source":{"id":"2112.08451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2021-12-15T19:51:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7db37c43595e6f6b550f420e32696bb1670deba98e6961d3c6f5481ccd0c6535","abstract_canon_sha256":"18e27f76cd2d28308219f3643a0904733c36844079bea4c470590bbf98d2cc5e"},"schema_version":"1.0"},"canonical_sha256":"7de452c391098d5bc9861ede1507eee734da79c0cbcf9e4c1fe69d99251aeaee","source":{"kind":"arxiv","id":"2112.08451","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08451","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08451v1","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08451","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"PXSFFQ4RBGGV","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"PXSFFQ4RBGGVXSMG","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"PXSFFQ4R","created_at":"2026-07-05T03:42:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PXSFFQ4RBGGVXSMGD3PBKB7O44","target":"record","payload":{"canonical_record":{"source":{"id":"2112.08451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2021-12-15T19:51:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7db37c43595e6f6b550f420e32696bb1670deba98e6961d3c6f5481ccd0c6535","abstract_canon_sha256":"18e27f76cd2d28308219f3643a0904733c36844079bea4c470590bbf98d2cc5e"},"schema_version":"1.0"},"canonical_sha256":"7de452c391098d5bc9861ede1507eee734da79c0cbcf9e4c1fe69d99251aeaee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:42:06.728881Z","signature_b64":"8StC5/Ycw9wq+c8fSuHihlr5fzrDkWj8c5nknf27MGc8I3wb/4d8U0HCtyN83rSwRAAYTsuGguRgsiOX27JEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7de452c391098d5bc9861ede1507eee734da79c0cbcf9e4c1fe69d99251aeaee","last_reissued_at":"2026-07-05T03:42:06.728389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:42:06.728389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.08451","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":"2026-07-05T03:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xQ89ziDnPQYMDrkKxtoUK+vdoJqZRKUPuCy2upCiCFea02qe2byb5TXLXvQbpZ4Pdvj+Gu79z+s94gG8yY4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:32:20.463915Z"},"content_sha256":"ca83973b3d9d850fcb67b3d8cbf41e18d769d15ae5c2cf2af5db78762fc233d2","schema_version":"1.0","event_id":"sha256:ca83973b3d9d850fcb67b3d8cbf41e18d769d15ae5c2cf2af5db78762fc233d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PXSFFQ4RBGGVXSMGD3PBKB7O44","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantum Algorithms for Reinforcement Learning with a Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Aarthi Sundaram, Ashish Kapoor, Daochen Wang, Martin Roetteler, Robin Kothari","submitted_at":"2021-12-15T19:51:49Z","abstract_excerpt":"Reinforcement learning studies how an agent should interact with an environment to maximize its cumulative reward. A standard way to study this question abstractly is to ask how many samples an agent needs from the environment to learn an optimal policy for a $\\gamma$-discounted Markov decision process (MDP). For such an MDP, we design quantum algorithms that approximate an optimal policy ($\\pi^*$), the optimal value function ($v^*$), and the optimal $Q$-function ($q^*$), assuming the algorithms can access samples from the environment in quantum superposition. This assumption is justified when"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08451","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/2112.08451/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":"2026-07-05T03:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1VXfkhLmkGSgzV4VJDUaP+panlcRLHADfFjV4VPwGFCh5X0zqhA0l4hZDSwMgK5KG6VjyaD6m0plGqV0YMMFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:32:20.464448Z"},"content_sha256":"b5ea79ba8e39d3a235e652d14442a68bcd9a0e8d1f98da2ea3fe527ef40a0841","schema_version":"1.0","event_id":"sha256:b5ea79ba8e39d3a235e652d14442a68bcd9a0e8d1f98da2ea3fe527ef40a0841"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/bundle.json","state_url":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/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":"2026-08-16T06:32:20Z","links":{"resolver":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44","bundle":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/bundle.json","state":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PXSFFQ4RBGGVXSMGD3PBKB7O44","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":"18e27f76cd2d28308219f3643a0904733c36844079bea4c470590bbf98d2cc5e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2021-12-15T19:51:49Z","title_canon_sha256":"7db37c43595e6f6b550f420e32696bb1670deba98e6961d3c6f5481ccd0c6535"},"schema_version":"1.0","source":{"id":"2112.08451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08451","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08451v1","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08451","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"PXSFFQ4RBGGV","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"PXSFFQ4RBGGVXSMG","created_at":"2026-07-05T03:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"PXSFFQ4R","created_at":"2026-07-05T03:42:06Z"}],"graph_snapshots":[{"event_id":"sha256:b5ea79ba8e39d3a235e652d14442a68bcd9a0e8d1f98da2ea3fe527ef40a0841","target":"graph","created_at":"2026-07-05T03:42:06Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.08451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning studies how an agent should interact with an environment to maximize its cumulative reward. A standard way to study this question abstractly is to ask how many samples an agent needs from the environment to learn an optimal policy for a $\\gamma$-discounted Markov decision process (MDP). For such an MDP, we design quantum algorithms that approximate an optimal policy ($\\pi^*$), the optimal value function ($v^*$), and the optimal $Q$-function ($q^*$), assuming the algorithms can access samples from the environment in quantum superposition. This assumption is justified when","authors_text":"Aarthi Sundaram, Ashish Kapoor, Daochen Wang, Martin Roetteler, Robin Kothari","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2021-12-15T19:51:49Z","title":"Quantum Algorithms for Reinforcement Learning with a Generative Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08451","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:ca83973b3d9d850fcb67b3d8cbf41e18d769d15ae5c2cf2af5db78762fc233d2","target":"record","created_at":"2026-07-05T03:42:06Z","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":"18e27f76cd2d28308219f3643a0904733c36844079bea4c470590bbf98d2cc5e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2021-12-15T19:51:49Z","title_canon_sha256":"7db37c43595e6f6b550f420e32696bb1670deba98e6961d3c6f5481ccd0c6535"},"schema_version":"1.0","source":{"id":"2112.08451","kind":"arxiv","version":1}},"canonical_sha256":"7de452c391098d5bc9861ede1507eee734da79c0cbcf9e4c1fe69d99251aeaee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7de452c391098d5bc9861ede1507eee734da79c0cbcf9e4c1fe69d99251aeaee","first_computed_at":"2026-07-05T03:42:06.728389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:42:06.728389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8StC5/Ycw9wq+c8fSuHihlr5fzrDkWj8c5nknf27MGc8I3wb/4d8U0HCtyN83rSwRAAYTsuGguRgsiOX27JEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:42:06.728881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca83973b3d9d850fcb67b3d8cbf41e18d769d15ae5c2cf2af5db78762fc233d2","sha256:b5ea79ba8e39d3a235e652d14442a68bcd9a0e8d1f98da2ea3fe527ef40a0841"],"state_sha256":"3fa1bee786d53f5b54923911a685a31c4f3cde9df52440d6d72606091d6dc311"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pzu9jvYiKXZoU/Z3286r/wf1F1lGM6O9xzUZNwLfmirusUCKLI4bDYak6qmKu0haqW7LfXSWlJElU41pgfofDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T06:32:20.468148Z","bundle_sha256":"6c3bdb8ba5de200ad3e3d741b1f65c7ccc35e0e0b937bfc66d6cc3afa975413d"}}