{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IMTTUJIS736UTG7EYSCCUQ7NUF","short_pith_number":"pith:IMTTUJIS","schema_version":"1.0","canonical_sha256":"43273a2512fefd499be4c4842a43eda166757b5c7aec2395b5aff5a9f2a8744d","source":{"kind":"arxiv","id":"2605.18979","version":1},"attestation_state":"computed","paper":{"title":"TabQL: In-Context Q-Learning with Tabular Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Balu, Ashutosh Kumar Nirala, Qisai Liu, Soumik Sarkar, Timilehin Ayanlade, Yang Li, Zhanhong Jiang","submitted_at":"2026-05-18T18:03:05Z","abstract_excerpt":"We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) with a tabular foundation model endowed with in-context learning capabilities. The key idea is to represent Q-values through a sequence-to-sequence foundation model operating over a tabularized representation of state-action-Q-value tuples, enabling rapid adaptation from limited online interaction by conditioning on recent experience. TabQL departs from classical DQN by leveraging (i) zero- or few-shot Q-value inference via in-context updates, a"},"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":"2605.18979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T18:03:05Z","cross_cats_sorted":[],"title_canon_sha256":"9b8261bef9dd94869f7f5fe0ea430bbec3a31fda57fb27c9e76ab6608e64c663","abstract_canon_sha256":"bec7dfdb0e754151b03e5c4e5a230e3567666476830f3cae47f57ebf09911102"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:40.854924Z","signature_b64":"gtj+6c0KhWau5KKDtWc3wjwNCvEZGOHqs/a2s9cnIrekybcPbmRvHwu9zbsjnbcpVgh4WjumVAdGi8uSzTx6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43273a2512fefd499be4c4842a43eda166757b5c7aec2395b5aff5a9f2a8744d","last_reissued_at":"2026-05-20T00:06:40.854084Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:40.854084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabQL: In-Context Q-Learning with Tabular Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Balu, Ashutosh Kumar Nirala, Qisai Liu, Soumik Sarkar, Timilehin Ayanlade, Yang Li, Zhanhong Jiang","submitted_at":"2026-05-18T18:03:05Z","abstract_excerpt":"We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) with a tabular foundation model endowed with in-context learning capabilities. The key idea is to represent Q-values through a sequence-to-sequence foundation model operating over a tabularized representation of state-action-Q-value tuples, enabling rapid adaptation from limited online interaction by conditioning on recent experience. TabQL departs from classical DQN by leveraging (i) zero- or few-shot Q-value inference via in-context updates, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18979","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/2605.18979/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":"2605.18979","created_at":"2026-05-20T00:06:40.854221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18979v1","created_at":"2026-05-20T00:06:40.854221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18979","created_at":"2026-05-20T00:06:40.854221+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMTTUJIS736U","created_at":"2026-05-20T00:06:40.854221+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMTTUJIS736UTG7E","created_at":"2026-05-20T00:06:40.854221+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMTTUJIS","created_at":"2026-05-20T00:06:40.854221+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/IMTTUJIS736UTG7EYSCCUQ7NUF","json":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF.json","graph_json":"https://pith.science/api/pith-number/IMTTUJIS736UTG7EYSCCUQ7NUF/graph.json","events_json":"https://pith.science/api/pith-number/IMTTUJIS736UTG7EYSCCUQ7NUF/events.json","paper":"https://pith.science/paper/IMTTUJIS"},"agent_actions":{"view_html":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF","download_json":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF.json","view_paper":"https://pith.science/paper/IMTTUJIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18979&json=true","fetch_graph":"https://pith.science/api/pith-number/IMTTUJIS736UTG7EYSCCUQ7NUF/graph.json","fetch_events":"https://pith.science/api/pith-number/IMTTUJIS736UTG7EYSCCUQ7NUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/action/storage_attestation","attest_author":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/action/author_attestation","sign_citation":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/action/citation_signature","submit_replication":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/action/replication_record"}},"created_at":"2026-05-20T00:06:40.854221+00:00","updated_at":"2026-05-20T00:06:40.854221+00:00"}