{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TMJ4R5UWX4Z5N2VFSTDYDDP3O6","short_pith_number":"pith:TMJ4R5UW","schema_version":"1.0","canonical_sha256":"9b13c8f696bf33d6eaa594c7818dfb7798cd4fc57e0a5070c9cd1d31989f15d2","source":{"kind":"arxiv","id":"2509.11259","version":1},"attestation_state":"computed","paper":{"title":"Gradient Free Deep Reinforcement Learning With TabPFN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Schiff, Ofir Lindenbaum, Yonathan Efroni","submitted_at":"2025-09-14T13:09:58Z","abstract_excerpt":"Gradient based optimization is fundamental to most modern deep reinforcement learning algorithms, however, it introduces significant sensitivity to hyperparameters, unstable training dynamics, and high computational costs. We propose TabPFN RL, a novel gradient free deep RL framework that repurposes the meta trained transformer TabPFN as a Q function approximator. Originally developed for tabular classification, TabPFN is a transformer pre trained on millions of synthetic datasets to perform inference on new unseen datasets via in context learning. Given an in context dataset of sample label p"},"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":"2509.11259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-14T13:09:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"361e80a039a99b15511dfd35d4d4c953b194a42a8a66d836ecddc4d889bf35b0","abstract_canon_sha256":"635705379bf9996277dc646f31351f5dbff01b443d307570aaa729a076c2be94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:36.275985Z","signature_b64":"YtbJV792E7v7EW0ueAoAXcFqVlQPho2yxFRlf44ickgkPHyeX3enokkmaf/eSpgu1mL9zixY6OEOHBV9slv0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b13c8f696bf33d6eaa594c7818dfb7798cd4fc57e0a5070c9cd1d31989f15d2","last_reissued_at":"2026-07-05T12:11:36.275466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:36.275466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Free Deep Reinforcement Learning With TabPFN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Schiff, Ofir Lindenbaum, Yonathan Efroni","submitted_at":"2025-09-14T13:09:58Z","abstract_excerpt":"Gradient based optimization is fundamental to most modern deep reinforcement learning algorithms, however, it introduces significant sensitivity to hyperparameters, unstable training dynamics, and high computational costs. We propose TabPFN RL, a novel gradient free deep RL framework that repurposes the meta trained transformer TabPFN as a Q function approximator. Originally developed for tabular classification, TabPFN is a transformer pre trained on millions of synthetic datasets to perform inference on new unseen datasets via in context learning. Given an in context dataset of sample label p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.11259","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/2509.11259/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":"2509.11259","created_at":"2026-07-05T12:11:36.275527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.11259v1","created_at":"2026-07-05T12:11:36.275527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.11259","created_at":"2026-07-05T12:11:36.275527+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMJ4R5UWX4Z5","created_at":"2026-07-05T12:11:36.275527+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMJ4R5UWX4Z5N2VF","created_at":"2026-07-05T12:11:36.275527+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMJ4R5UW","created_at":"2026-07-05T12:11:36.275527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2606.18812","citing_title":"Reinforcement Learning Foundation Models Should Already Be A Thing","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30336","citing_title":"FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13986","citing_title":"TabPFN-3: Technical Report","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30336","citing_title":"FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30410","citing_title":"Beyond IID: How General Are Tabular Foundation Models, Really?","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18979","citing_title":"TabQL: In-Context Q-Learning with Tabular Foundation Models","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13986","citing_title":"TabPFN-3: Technical Report","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2511.08667","citing_title":"TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMJ4R5UWX4Z5N2VFSTDYDDP3O6","json":"https://pith.science/pith/TMJ4R5UWX4Z5N2VFSTDYDDP3O6.json","graph_json":"https://pith.science/api/pith-number/TMJ4R5UWX4Z5N2VFSTDYDDP3O6/graph.json","events_json":"https://pith.science/api/pith-number/TMJ4R5UWX4Z5N2VFSTDYDDP3O6/events.json","paper":"https://pith.science/paper/TMJ4R5UW"},"agent_actions":{"view_html":"https://pith.science/pith/TMJ4R5UWX4Z5N2VFSTDYDDP3O6","download_json":"https://pith.science/pith/TMJ4R5UWX4Z5N2VFSTDYDDP3O6.json","view_paper":"https://pith.science/paper/TMJ4R5UW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.11259&json=true","fetch_graph":"https://pith.science/api/pith-number/TMJ4R5UWX4Z5N2VFSTDYDDP3O6/graph.json","fetch_events":"https://pith.science/api/pith-number/TMJ4R5UWX4Z5N2VFSTDYDDP3O6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMJ4R5UWX4Z5N2VFSTDYDDP3O6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMJ4R5UWX4Z5N2VFSTDYDDP3O6/action/storage_attestation","attest_author":"https://pith.science/pith/TMJ4R5UWX4Z5N2VFSTDYDDP3O6/action/author_attestation","sign_citation":"https://pith.science/pith/TMJ4R5UWX4Z5N2VFSTDYDDP3O6/action/citation_signature","submit_replication":"https://pith.science/pith/TMJ4R5UWX4Z5N2VFSTDYDDP3O6/action/replication_record"}},"created_at":"2026-07-05T12:11:36.275527+00:00","updated_at":"2026-07-05T12:11:36.275527+00:00"}