{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TMJ4R5UWX4Z5N2VFSTDYDDP3O6","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":"635705379bf9996277dc646f31351f5dbff01b443d307570aaa729a076c2be94","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-14T13:09:58Z","title_canon_sha256":"361e80a039a99b15511dfd35d4d4c953b194a42a8a66d836ecddc4d889bf35b0"},"schema_version":"1.0","source":{"id":"2509.11259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.11259","created_at":"2026-07-05T12:11:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.11259v1","created_at":"2026-07-05T12:11:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.11259","created_at":"2026-07-05T12:11:36Z"},{"alias_kind":"pith_short_12","alias_value":"TMJ4R5UWX4Z5","created_at":"2026-07-05T12:11:36Z"},{"alias_kind":"pith_short_16","alias_value":"TMJ4R5UWX4Z5N2VF","created_at":"2026-07-05T12:11:36Z"},{"alias_kind":"pith_short_8","alias_value":"TMJ4R5UW","created_at":"2026-07-05T12:11:36Z"}],"graph_snapshots":[{"event_id":"sha256:81b8eab01e3693b69323f647a175b3478b86c8858a8f79199cdb9399205d34d8","target":"graph","created_at":"2026-07-05T12:11:36Z","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/2509.11259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Schiff, Ofir Lindenbaum, Yonathan Efroni","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-14T13:09:58Z","title":"Gradient Free Deep Reinforcement Learning With TabPFN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.11259","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":"sha256:4027fcf23a04b356646fa6808884a056cd4b813059ac9257b334d7fe0e6ca4de","target":"record","created_at":"2026-07-05T12:11:36Z","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":"635705379bf9996277dc646f31351f5dbff01b443d307570aaa729a076c2be94","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-14T13:09:58Z","title_canon_sha256":"361e80a039a99b15511dfd35d4d4c953b194a42a8a66d836ecddc4d889bf35b0"},"schema_version":"1.0","source":{"id":"2509.11259","kind":"arxiv","version":1}},"canonical_sha256":"9b13c8f696bf33d6eaa594c7818dfb7798cd4fc57e0a5070c9cd1d31989f15d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b13c8f696bf33d6eaa594c7818dfb7798cd4fc57e0a5070c9cd1d31989f15d2","first_computed_at":"2026-07-05T12:11:36.275466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:36.275466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YtbJV792E7v7EW0ueAoAXcFqVlQPho2yxFRlf44ickgkPHyeX3enokkmaf/eSpgu1mL9zixY6OEOHBV9slv0DA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:36.275985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.11259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4027fcf23a04b356646fa6808884a056cd4b813059ac9257b334d7fe0e6ca4de","sha256:81b8eab01e3693b69323f647a175b3478b86c8858a8f79199cdb9399205d34d8"],"state_sha256":"ab5ecd9f98b60a727e992f1ebb3c77b165f72e650e380cd8fe541c42d13f37b8"}