{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QUF24P4E3L4SH5D5I5AFXCBPSJ","short_pith_number":"pith:QUF24P4E","schema_version":"1.0","canonical_sha256":"850bae3f84daf923f47d47405b882f924d15a8ab0116483d6f2756d47755b88d","source":{"kind":"arxiv","id":"2307.03997","version":2},"attestation_state":"computed","paper":{"title":"Efficient Model-Free Exploration in Low-Rank MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Adam Block, Alexander Rakhlin, Dylan J. Foster, Zakaria Mhammedi","submitted_at":"2023-07-08T15:41:48Z","abstract_excerpt":"A major challenge in reinforcement learning is to develop practical, sample-efficient algorithms for exploration in high-dimensional domains where generalization and function approximation is required. Low-Rank Markov Decision Processes -- where transition probabilities admit a low-rank factorization based on an unknown feature embedding -- offer a simple, yet expressive framework for RL with function approximation, but existing algorithms are either (1) computationally intractable, or (2) reliant upon restrictive statistical assumptions such as latent variable structure, access to model-based"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.03997","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-08T15:41:48Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"bfb1cf28e8f7d8ebdfb6ad7d0be2d95db68584b3ca947ae6f42507bc2302a5e3","abstract_canon_sha256":"cc2543670aafa6a0446dd7cb34078f15921ba5a3a11e5d5fcff1e337b19819f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:38.385938Z","signature_b64":"ZQEfAB8W21qzcI995bA/tNYaQWaV+TIoG7N6zteCI82RA5Pz6A+pk6y/zpZQ/hrM7fJYRU07X2KZuqTSP+jBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"850bae3f84daf923f47d47405b882f924d15a8ab0116483d6f2756d47755b88d","last_reissued_at":"2026-07-05T07:50:38.385424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:38.385424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Model-Free Exploration in Low-Rank MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Adam Block, Alexander Rakhlin, Dylan J. Foster, Zakaria Mhammedi","submitted_at":"2023-07-08T15:41:48Z","abstract_excerpt":"A major challenge in reinforcement learning is to develop practical, sample-efficient algorithms for exploration in high-dimensional domains where generalization and function approximation is required. Low-Rank Markov Decision Processes -- where transition probabilities admit a low-rank factorization based on an unknown feature embedding -- offer a simple, yet expressive framework for RL with function approximation, but existing algorithms are either (1) computationally intractable, or (2) reliant upon restrictive statistical assumptions such as latent variable structure, access to model-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03997","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.03997/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.03997","created_at":"2026-07-05T07:50:38.385486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03997v2","created_at":"2026-07-05T07:50:38.385486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03997","created_at":"2026-07-05T07:50:38.385486+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUF24P4E3L4S","created_at":"2026-07-05T07:50:38.385486+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUF24P4E3L4SH5D5","created_at":"2026-07-05T07:50:38.385486+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUF24P4E","created_at":"2026-07-05T07:50:38.385486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUF24P4E3L4SH5D5I5AFXCBPSJ","json":"https://pith.science/pith/QUF24P4E3L4SH5D5I5AFXCBPSJ.json","graph_json":"https://pith.science/api/pith-number/QUF24P4E3L4SH5D5I5AFXCBPSJ/graph.json","events_json":"https://pith.science/api/pith-number/QUF24P4E3L4SH5D5I5AFXCBPSJ/events.json","paper":"https://pith.science/paper/QUF24P4E"},"agent_actions":{"view_html":"https://pith.science/pith/QUF24P4E3L4SH5D5I5AFXCBPSJ","download_json":"https://pith.science/pith/QUF24P4E3L4SH5D5I5AFXCBPSJ.json","view_paper":"https://pith.science/paper/QUF24P4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03997&json=true","fetch_graph":"https://pith.science/api/pith-number/QUF24P4E3L4SH5D5I5AFXCBPSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QUF24P4E3L4SH5D5I5AFXCBPSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUF24P4E3L4SH5D5I5AFXCBPSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUF24P4E3L4SH5D5I5AFXCBPSJ/action/storage_attestation","attest_author":"https://pith.science/pith/QUF24P4E3L4SH5D5I5AFXCBPSJ/action/author_attestation","sign_citation":"https://pith.science/pith/QUF24P4E3L4SH5D5I5AFXCBPSJ/action/citation_signature","submit_replication":"https://pith.science/pith/QUF24P4E3L4SH5D5I5AFXCBPSJ/action/replication_record"}},"created_at":"2026-07-05T07:50:38.385486+00:00","updated_at":"2026-07-05T07:50:38.385486+00:00"}