{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IMTTUJIS736UTG7EYSCCUQ7NUF","short_pith_number":"pith:IMTTUJIS","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"},"canonical_sha256":"43273a2512fefd499be4c4842a43eda166757b5c7aec2395b5aff5a9f2a8744d","source":{"kind":"arxiv","id":"2605.18979","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18979","created_at":"2026-05-20T00:06:40Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18979v1","created_at":"2026-05-20T00:06:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18979","created_at":"2026-05-20T00:06:40Z"},{"alias_kind":"pith_short_12","alias_value":"IMTTUJIS736U","created_at":"2026-05-20T00:06:40Z"},{"alias_kind":"pith_short_16","alias_value":"IMTTUJIS736UTG7E","created_at":"2026-05-20T00:06:40Z"},{"alias_kind":"pith_short_8","alias_value":"IMTTUJIS","created_at":"2026-05-20T00:06:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IMTTUJIS736UTG7EYSCCUQ7NUF","target":"record","payload":{"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"},"canonical_sha256":"43273a2512fefd499be4c4842a43eda166757b5c7aec2395b5aff5a9f2a8744d","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"},"source_kind":"arxiv","source_id":"2605.18979","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":"2026-05-20T00:06:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H94qBhRBM0v092TJyuZ0tbhIWT23yBisip1eCuEj3oJppsIqOhSNNO4Q6POO1w2dgB5Ox6IBHRi48z39YS7IBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T03:49:10.712333Z"},"content_sha256":"12722595c94be260d9abac596c4822e676cc81ef4a3835a4ebc2fe60c1d2c548","schema_version":"1.0","event_id":"sha256:12722595c94be260d9abac596c4822e676cc81ef4a3835a4ebc2fe60c1d2c548"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IMTTUJIS736UTG7EYSCCUQ7NUF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sMac1Z4VX3ON5ssazxVb8Gwa5rX+nC1RIx8yizyvkkfe8vkLYavh1tk0jewntnqT5EybNUS9+uO72OE0xXsMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T03:49:10.713071Z"},"content_sha256":"af11085e13325d980fa45bbe54f7ea7e0ca2445f3e9af73312154f0179f8d9c5","schema_version":"1.0","event_id":"sha256:af11085e13325d980fa45bbe54f7ea7e0ca2445f3e9af73312154f0179f8d9c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/bundle.json","state_url":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/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":"2026-05-25T03:49:10Z","links":{"resolver":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF","bundle":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/bundle.json","state":"https://pith.science/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMTTUJIS736UTG7EYSCCUQ7NUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IMTTUJIS736UTG7EYSCCUQ7NUF","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":"bec7dfdb0e754151b03e5c4e5a230e3567666476830f3cae47f57ebf09911102","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T18:03:05Z","title_canon_sha256":"9b8261bef9dd94869f7f5fe0ea430bbec3a31fda57fb27c9e76ab6608e64c663"},"schema_version":"1.0","source":{"id":"2605.18979","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18979","created_at":"2026-05-20T00:06:40Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18979v1","created_at":"2026-05-20T00:06:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18979","created_at":"2026-05-20T00:06:40Z"},{"alias_kind":"pith_short_12","alias_value":"IMTTUJIS736U","created_at":"2026-05-20T00:06:40Z"},{"alias_kind":"pith_short_16","alias_value":"IMTTUJIS736UTG7E","created_at":"2026-05-20T00:06:40Z"},{"alias_kind":"pith_short_8","alias_value":"IMTTUJIS","created_at":"2026-05-20T00:06:40Z"}],"graph_snapshots":[{"event_id":"sha256:af11085e13325d980fa45bbe54f7ea7e0ca2445f3e9af73312154f0179f8d9c5","target":"graph","created_at":"2026-05-20T00:06:40Z","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/2605.18979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aditya Balu, Ashutosh Kumar Nirala, Qisai Liu, Soumik Sarkar, Timilehin Ayanlade, Yang Li, Zhanhong Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T18:03:05Z","title":"TabQL: In-Context Q-Learning with Tabular Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18979","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":"sha256:12722595c94be260d9abac596c4822e676cc81ef4a3835a4ebc2fe60c1d2c548","target":"record","created_at":"2026-05-20T00:06:40Z","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":"bec7dfdb0e754151b03e5c4e5a230e3567666476830f3cae47f57ebf09911102","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T18:03:05Z","title_canon_sha256":"9b8261bef9dd94869f7f5fe0ea430bbec3a31fda57fb27c9e76ab6608e64c663"},"schema_version":"1.0","source":{"id":"2605.18979","kind":"arxiv","version":1}},"canonical_sha256":"43273a2512fefd499be4c4842a43eda166757b5c7aec2395b5aff5a9f2a8744d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43273a2512fefd499be4c4842a43eda166757b5c7aec2395b5aff5a9f2a8744d","first_computed_at":"2026-05-20T00:06:40.854084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:40.854084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gtj+6c0KhWau5KKDtWc3wjwNCvEZGOHqs/a2s9cnIrekybcPbmRvHwu9zbsjnbcpVgh4WjumVAdGi8uSzTx6Cg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:40.854924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18979","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12722595c94be260d9abac596c4822e676cc81ef4a3835a4ebc2fe60c1d2c548","sha256:af11085e13325d980fa45bbe54f7ea7e0ca2445f3e9af73312154f0179f8d9c5"],"state_sha256":"e465668bbd42749406d33595c39a88c03a803846756f665661916b2ceded0f62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YGKSOqAFHIopuUzsAC9Qkbpn4M/Hy3AGbgGBEp7xfGUgXewesqNBmWTaRSI+Le+AxqM9feG/2sitt/L94L0ZBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T03:49:10.716603Z","bundle_sha256":"5610f2dd892c0a235319e69ad44093507dfd84ed342af692058f33f1b48ed502"}}