{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EIA2TTK54GAA3SBRRUARQOKJOM","short_pith_number":"pith:EIA2TTK5","canonical_record":{"source":{"id":"2503.06985","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T07:05:07Z","cross_cats_sorted":[],"title_canon_sha256":"a131d85de7f37365ed82980d2e1ac173b3f21b65df1afeebdfc12b675124e6b1","abstract_canon_sha256":"4a6735a3d95299f7380161ef40cdab89c1363ef3e694ef4ec253c085fb0095f8"},"schema_version":"1.0"},"canonical_sha256":"2201a9cd5de1800dc8318d011839497304c23dbff2f4280d3e90cc8bccaf990a","source":{"kind":"arxiv","id":"2503.06985","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06985","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06985v1","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06985","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_12","alias_value":"EIA2TTK54GAA","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_16","alias_value":"EIA2TTK54GAA3SBR","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_8","alias_value":"EIA2TTK5","created_at":"2026-07-05T10:27:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EIA2TTK54GAA3SBRRUARQOKJOM","target":"record","payload":{"canonical_record":{"source":{"id":"2503.06985","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T07:05:07Z","cross_cats_sorted":[],"title_canon_sha256":"a131d85de7f37365ed82980d2e1ac173b3f21b65df1afeebdfc12b675124e6b1","abstract_canon_sha256":"4a6735a3d95299f7380161ef40cdab89c1363ef3e694ef4ec253c085fb0095f8"},"schema_version":"1.0"},"canonical_sha256":"2201a9cd5de1800dc8318d011839497304c23dbff2f4280d3e90cc8bccaf990a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:47.223300Z","signature_b64":"WskICQCUn4e05/iPTAPfgSbSWzdC/1hh3PuNXNAVSdTxNZk4HKiEThAWlBicpxQ4bmS0kCsD160+XyffaP2eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2201a9cd5de1800dc8318d011839497304c23dbff2f4280d3e90cc8bccaf990a","last_reissued_at":"2026-07-05T10:27:47.222489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:47.222489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.06985","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":"2026-07-05T10:27:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BUvo7yi+qDUBNx7vsxdKzqM9eKaLrYqnKw9ytk7Uz4h6Fqz6hW+Mzi06dT5C0JowitDeM9R1ZoIqI8JhNU2SCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:02:55.782990Z"},"content_sha256":"7ea96c842e2207eac77ccd3ff9207a878ba5286560ef579d28e49b8fa9a16606","schema_version":"1.0","event_id":"sha256:7ea96c842e2207eac77ccd3ff9207a878ba5286560ef579d28e49b8fa9a16606"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EIA2TTK54GAA3SBRRUARQOKJOM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Decision Trees as Amortized Structure Inference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex Hernandez-Garcia, Ghait Boukachab, Micha{\\l} Koziarski, Mohammed Mahfoud, Nikolay Malkin, Stefan Bauer, Yoshua Bengio","submitted_at":"2025-03-10T07:05:07Z","abstract_excerpt":"Building predictive models for tabular data presents fundamental challenges, notably in scaling consistently, i.e., more resources translating to better performance, and generalizing systematically beyond the training data distribution. Designing decision tree models remains especially challenging given the intractably large search space, and most existing methods rely on greedy heuristics, while deep learning inductive biases expect a temporal or spatial structure not naturally present in tabular data. We propose a hybrid amortized structure inference approach to learn predictive decision tre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06985","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/2503.06985/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":"2026-07-05T10:27:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z8T6qXfCwedNr0PGkfcc7rNUbuq5h8c2g6pUKa1TMbnhSBq+Zs1NyNLKQh06LVJ21jCDHuXkNEnwYmGV2TL9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:02:55.783564Z"},"content_sha256":"cf7f9e2df2e1af61a4d736fd1c14723ea555ac1a6a9b592d0d4e3ccab59657e6","schema_version":"1.0","event_id":"sha256:cf7f9e2df2e1af61a4d736fd1c14723ea555ac1a6a9b592d0d4e3ccab59657e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EIA2TTK54GAA3SBRRUARQOKJOM/bundle.json","state_url":"https://pith.science/pith/EIA2TTK54GAA3SBRRUARQOKJOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EIA2TTK54GAA3SBRRUARQOKJOM/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":"2026-08-19T02:02:55Z","links":{"resolver":"https://pith.science/pith/EIA2TTK54GAA3SBRRUARQOKJOM","bundle":"https://pith.science/pith/EIA2TTK54GAA3SBRRUARQOKJOM/bundle.json","state":"https://pith.science/pith/EIA2TTK54GAA3SBRRUARQOKJOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EIA2TTK54GAA3SBRRUARQOKJOM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EIA2TTK54GAA3SBRRUARQOKJOM","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":"4a6735a3d95299f7380161ef40cdab89c1363ef3e694ef4ec253c085fb0095f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T07:05:07Z","title_canon_sha256":"a131d85de7f37365ed82980d2e1ac173b3f21b65df1afeebdfc12b675124e6b1"},"schema_version":"1.0","source":{"id":"2503.06985","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06985","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06985v1","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06985","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_12","alias_value":"EIA2TTK54GAA","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_16","alias_value":"EIA2TTK54GAA3SBR","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_8","alias_value":"EIA2TTK5","created_at":"2026-07-05T10:27:47Z"}],"graph_snapshots":[{"event_id":"sha256:cf7f9e2df2e1af61a4d736fd1c14723ea555ac1a6a9b592d0d4e3ccab59657e6","target":"graph","created_at":"2026-07-05T10:27:47Z","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/2503.06985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building predictive models for tabular data presents fundamental challenges, notably in scaling consistently, i.e., more resources translating to better performance, and generalizing systematically beyond the training data distribution. Designing decision tree models remains especially challenging given the intractably large search space, and most existing methods rely on greedy heuristics, while deep learning inductive biases expect a temporal or spatial structure not naturally present in tabular data. We propose a hybrid amortized structure inference approach to learn predictive decision tre","authors_text":"Alex Hernandez-Garcia, Ghait Boukachab, Micha{\\l} Koziarski, Mohammed Mahfoud, Nikolay Malkin, Stefan Bauer, Yoshua Bengio","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T07:05:07Z","title":"Learning Decision Trees as Amortized Structure Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06985","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":"sha256:7ea96c842e2207eac77ccd3ff9207a878ba5286560ef579d28e49b8fa9a16606","target":"record","created_at":"2026-07-05T10:27:47Z","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":"4a6735a3d95299f7380161ef40cdab89c1363ef3e694ef4ec253c085fb0095f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T07:05:07Z","title_canon_sha256":"a131d85de7f37365ed82980d2e1ac173b3f21b65df1afeebdfc12b675124e6b1"},"schema_version":"1.0","source":{"id":"2503.06985","kind":"arxiv","version":1}},"canonical_sha256":"2201a9cd5de1800dc8318d011839497304c23dbff2f4280d3e90cc8bccaf990a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2201a9cd5de1800dc8318d011839497304c23dbff2f4280d3e90cc8bccaf990a","first_computed_at":"2026-07-05T10:27:47.222489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:47.222489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WskICQCUn4e05/iPTAPfgSbSWzdC/1hh3PuNXNAVSdTxNZk4HKiEThAWlBicpxQ4bmS0kCsD160+XyffaP2eCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:47.223300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.06985","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ea96c842e2207eac77ccd3ff9207a878ba5286560ef579d28e49b8fa9a16606","sha256:cf7f9e2df2e1af61a4d736fd1c14723ea555ac1a6a9b592d0d4e3ccab59657e6"],"state_sha256":"81f2d0a0151d2a25dcbb1618cc4705986c13e628d512271e14726d6a580120ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"95UeX02kV04GwnkyUt9fNmT5aOrTyUccUT0wN2Oa0sYCkJcy/sA/jSv16i+TuwyNYjvR4mDd32UqlckMBcHiDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:02:55.788855Z","bundle_sha256":"07be7b7bbe59d138fb34b29f7232b47f3779f12b417c7822ea1b4b9055c65571"}}