{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6WEC2Z2XU5V4Q6JIWEES6X54SM","short_pith_number":"pith:6WEC2Z2X","canonical_record":{"source":{"id":"2605.18654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:00:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfe150098131c5e70fe5ec19bfa9bebd792d8f01656fab383ed20021de11534c","abstract_canon_sha256":"e6a6b533026c108a1c38117433220e395fa41827c619b264d47ec0683e1abd47"},"schema_version":"1.0"},"canonical_sha256":"f5882d6757a76bc87928b1092f5fbc9305934f29dd744f49a762c80d407570fc","source":{"kind":"arxiv","id":"2605.18654","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18654","created_at":"2026-05-20T00:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18654v1","created_at":"2026-05-20T00:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18654","created_at":"2026-05-20T00:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"6WEC2Z2XU5V4","created_at":"2026-05-20T00:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"6WEC2Z2XU5V4Q6JI","created_at":"2026-05-20T00:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"6WEC2Z2X","created_at":"2026-05-20T00:06:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6WEC2Z2XU5V4Q6JIWEES6X54SM","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:00:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfe150098131c5e70fe5ec19bfa9bebd792d8f01656fab383ed20021de11534c","abstract_canon_sha256":"e6a6b533026c108a1c38117433220e395fa41827c619b264d47ec0683e1abd47"},"schema_version":"1.0"},"canonical_sha256":"f5882d6757a76bc87928b1092f5fbc9305934f29dd744f49a762c80d407570fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:13.010129Z","signature_b64":"dlky1YcjiKI/hdcL/biV8tpVd+4rLFht1LD3aOu7PRprhXJG6ixVgjutKfWC1BMjXb6epLEWnKgW/oR+91UCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5882d6757a76bc87928b1092f5fbc9305934f29dd744f49a762c80d407570fc","last_reissued_at":"2026-05-20T00:06:13.009512Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:13.009512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18654","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":"2026-05-20T00:06:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dbdzgoGQeFXn961wjrEJV8959kJnpttreLaFTA8OkvshzeDcJq8Lrazu7nRs1RGCbORfOukFC3TdX+CnH7cHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:02:52.103547Z"},"content_sha256":"60ed521be0d469dd06d7e8c052f3857a8a4c9b98832e074dd5bf06af677501b2","schema_version":"1.0","event_id":"sha256:60ed521be0d469dd06d7e8c052f3857a8a4c9b98832e074dd5bf06af677501b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6WEC2Z2XU5V4Q6JIWEES6X54SM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Tanna, Mohamed Bouadi, Nassim Bouarour, Pratinav Seth, Vinay Kumar Sankarapu","submitted_at":"2026-05-18T17:00:20Z","abstract_excerpt":"A fraud scorer needs to answer in under 2 ms. The best tabular foundation models (TFMs) take 151-1,275 ms on GPU. We close this gap by distilling the TFM offline into an XGBoost or CatBoost student that runs natively on CPU. The central obstacle is specific to in-context learning (ICL) teachers: they leak labels when scoring their own training set, so the soft targets collapse to near-one-hot vectors with no inter-class structure left to distill. Stratified out-of-fold (OOF) teacher labeling prevents this. Across 153 classification datasets drawn from TALENT, OpenML-CC18, TabZilla, and TabAren"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18654","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/2605.18654/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.163181Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"159e9878747481dc5437d2550af5cf28df4762987a13bdffe34b45c1c735b3df"},"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":"2026-05-20T00:06:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k5o89W2FMEYOcT/Wsnqm3SbG58N2wUhbpMnS+pA6+azr92jIxnokAyNdf4lTq/6yYLZcfscTH6UbgjLU+r//Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:02:52.103935Z"},"content_sha256":"793900bb875191d00b1df195f4e91cbd162fb5e78aebdd1c2393106d166a6bd3","schema_version":"1.0","event_id":"sha256:793900bb875191d00b1df195f4e91cbd162fb5e78aebdd1c2393106d166a6bd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WEC2Z2XU5V4Q6JIWEES6X54SM/bundle.json","state_url":"https://pith.science/pith/6WEC2Z2XU5V4Q6JIWEES6X54SM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WEC2Z2XU5V4Q6JIWEES6X54SM/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":"2026-06-02T20:02:52Z","links":{"resolver":"https://pith.science/pith/6WEC2Z2XU5V4Q6JIWEES6X54SM","bundle":"https://pith.science/pith/6WEC2Z2XU5V4Q6JIWEES6X54SM/bundle.json","state":"https://pith.science/pith/6WEC2Z2XU5V4Q6JIWEES6X54SM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WEC2Z2XU5V4Q6JIWEES6X54SM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6WEC2Z2XU5V4Q6JIWEES6X54SM","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":"e6a6b533026c108a1c38117433220e395fa41827c619b264d47ec0683e1abd47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:00:20Z","title_canon_sha256":"cfe150098131c5e70fe5ec19bfa9bebd792d8f01656fab383ed20021de11534c"},"schema_version":"1.0","source":{"id":"2605.18654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18654","created_at":"2026-05-20T00:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18654v1","created_at":"2026-05-20T00:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18654","created_at":"2026-05-20T00:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"6WEC2Z2XU5V4","created_at":"2026-05-20T00:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"6WEC2Z2XU5V4Q6JI","created_at":"2026-05-20T00:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"6WEC2Z2X","created_at":"2026-05-20T00:06:13Z"}],"graph_snapshots":[{"event_id":"sha256:793900bb875191d00b1df195f4e91cbd162fb5e78aebdd1c2393106d166a6bd3","target":"graph","created_at":"2026-05-20T00:06:13Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.163181Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18654/integrity.json","findings":[],"snapshot_sha256":"159e9878747481dc5437d2550af5cf28df4762987a13bdffe34b45c1c735b3df","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A fraud scorer needs to answer in under 2 ms. The best tabular foundation models (TFMs) take 151-1,275 ms on GPU. We close this gap by distilling the TFM offline into an XGBoost or CatBoost student that runs natively on CPU. The central obstacle is specific to in-context learning (ICL) teachers: they leak labels when scoring their own training set, so the soft targets collapse to near-one-hot vectors with no inter-class structure left to distill. Stratified out-of-fold (OOF) teacher labeling prevents this. Across 153 classification datasets drawn from TALENT, OpenML-CC18, TabZilla, and TabAren","authors_text":"Aditya Tanna, Mohamed Bouadi, Nassim Bouarour, Pratinav Seth, Vinay Kumar Sankarapu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:00:20Z","title":"Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18654","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":"sha256:60ed521be0d469dd06d7e8c052f3857a8a4c9b98832e074dd5bf06af677501b2","target":"record","created_at":"2026-05-20T00:06:13Z","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":"e6a6b533026c108a1c38117433220e395fa41827c619b264d47ec0683e1abd47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:00:20Z","title_canon_sha256":"cfe150098131c5e70fe5ec19bfa9bebd792d8f01656fab383ed20021de11534c"},"schema_version":"1.0","source":{"id":"2605.18654","kind":"arxiv","version":1}},"canonical_sha256":"f5882d6757a76bc87928b1092f5fbc9305934f29dd744f49a762c80d407570fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5882d6757a76bc87928b1092f5fbc9305934f29dd744f49a762c80d407570fc","first_computed_at":"2026-05-20T00:06:13.009512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:13.009512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dlky1YcjiKI/hdcL/biV8tpVd+4rLFht1LD3aOu7PRprhXJG6ixVgjutKfWC1BMjXb6epLEWnKgW/oR+91UCDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:13.010129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60ed521be0d469dd06d7e8c052f3857a8a4c9b98832e074dd5bf06af677501b2","sha256:793900bb875191d00b1df195f4e91cbd162fb5e78aebdd1c2393106d166a6bd3"],"state_sha256":"3760153b3f391efe70e0b658836652e71bd252059cef656167f60e44b7c94d27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lfKKrQ0XbfWrqgr8gpE07846VFCsx9q2M+DlBuj/lKg3N2QSHXnMtUHUgM2pogSPbfZd2NOkM6MFPL6AzjErCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T20:02:52.106067Z","bundle_sha256":"be898745947cdf893ce6dd758779e1833d90776305210ffc7c173e288b98b4f4"}}