{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XKURJX7WL7JLA3ML57CLZO3AAH","short_pith_number":"pith:XKURJX7W","schema_version":"1.0","canonical_sha256":"baa914dff65fd2b06d8befc4bcbb6001d9669ba678b04d2f6da71d4db6ca7640","source":{"kind":"arxiv","id":"2207.07150","version":2},"attestation_state":"computed","paper":{"title":"Making Linear MDPs Practical via Contrastive Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Dale Schuurmans, Joseph E. Gonzalez, Mengjiao Yang, Tianjun Zhang, Tongzheng Ren","submitted_at":"2022-07-14T18:18:02Z","abstract_excerpt":"It is common to address the curse of dimensionality in Markov decision processes (MDPs) by exploiting low-rank representations. This motivates much of the recent theoretical study on linear MDPs. However, most approaches require a given representation under unrealistic assumptions about the normalization of the decomposition or introduce unresolved computational challenges in practice. Instead, we consider an alternative definition of linear MDPs that automatically ensures normalization while allowing efficient representation learning via contrastive estimation. The framework also admits confi"},"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":"2207.07150","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-14T18:18:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4dda20741b583d7c6154ecde79171b124497b2c645320447b3528b8b7f701159","abstract_canon_sha256":"3f8049af054dea06b6f3467a6522f5f0fa88e33e0a9945a5cb40a859193afba4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:21.684297Z","signature_b64":"x2UuGYttOkefn0Wq9lWc2AdSFERSe+MWaxP/oM9r29UIr0INskeNXWKQfFV7C1GZVKbVd5zfVhy4kBYoGc8WCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baa914dff65fd2b06d8befc4bcbb6001d9669ba678b04d2f6da71d4db6ca7640","last_reissued_at":"2026-07-05T05:23:21.683909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:21.683909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Linear MDPs Practical via Contrastive Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Dale Schuurmans, Joseph E. Gonzalez, Mengjiao Yang, Tianjun Zhang, Tongzheng Ren","submitted_at":"2022-07-14T18:18:02Z","abstract_excerpt":"It is common to address the curse of dimensionality in Markov decision processes (MDPs) by exploiting low-rank representations. This motivates much of the recent theoretical study on linear MDPs. However, most approaches require a given representation under unrealistic assumptions about the normalization of the decomposition or introduce unresolved computational challenges in practice. Instead, we consider an alternative definition of linear MDPs that automatically ensures normalization while allowing efficient representation learning via contrastive estimation. The framework also admits confi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07150","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/2207.07150/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":"2207.07150","created_at":"2026-07-05T05:23:21.683965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.07150v2","created_at":"2026-07-05T05:23:21.683965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07150","created_at":"2026-07-05T05:23:21.683965+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKURJX7WL7JL","created_at":"2026-07-05T05:23:21.683965+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKURJX7WL7JLA3ML","created_at":"2026-07-05T05:23:21.683965+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKURJX7W","created_at":"2026-07-05T05:23:21.683965+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/XKURJX7WL7JLA3ML57CLZO3AAH","json":"https://pith.science/pith/XKURJX7WL7JLA3ML57CLZO3AAH.json","graph_json":"https://pith.science/api/pith-number/XKURJX7WL7JLA3ML57CLZO3AAH/graph.json","events_json":"https://pith.science/api/pith-number/XKURJX7WL7JLA3ML57CLZO3AAH/events.json","paper":"https://pith.science/paper/XKURJX7W"},"agent_actions":{"view_html":"https://pith.science/pith/XKURJX7WL7JLA3ML57CLZO3AAH","download_json":"https://pith.science/pith/XKURJX7WL7JLA3ML57CLZO3AAH.json","view_paper":"https://pith.science/paper/XKURJX7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.07150&json=true","fetch_graph":"https://pith.science/api/pith-number/XKURJX7WL7JLA3ML57CLZO3AAH/graph.json","fetch_events":"https://pith.science/api/pith-number/XKURJX7WL7JLA3ML57CLZO3AAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKURJX7WL7JLA3ML57CLZO3AAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKURJX7WL7JLA3ML57CLZO3AAH/action/storage_attestation","attest_author":"https://pith.science/pith/XKURJX7WL7JLA3ML57CLZO3AAH/action/author_attestation","sign_citation":"https://pith.science/pith/XKURJX7WL7JLA3ML57CLZO3AAH/action/citation_signature","submit_replication":"https://pith.science/pith/XKURJX7WL7JLA3ML57CLZO3AAH/action/replication_record"}},"created_at":"2026-07-05T05:23:21.683965+00:00","updated_at":"2026-07-05T05:23:21.683965+00:00"}