{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VQLSOKNB2TM7R3XO23VENXQX2Y","short_pith_number":"pith:VQLSOKNB","canonical_record":{"source":{"id":"2307.00422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-01T20:18:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ba9265393565ecacc2c773307c8cbb9fc927259e24f64f7fd934701c476e0613","abstract_canon_sha256":"0ba494c5a4cec80d0f7371abbad5ab078296cee79a4b3e39ab0e636a19beca8f"},"schema_version":"1.0"},"canonical_sha256":"ac172729a1d4d9f8eeeed6ea46de17d63cd1b9fbfc5a79c307dff17af5b0aa6c","source":{"kind":"arxiv","id":"2307.00422","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00422","created_at":"2026-07-05T06:26:56Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00422v1","created_at":"2026-07-05T06:26:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00422","created_at":"2026-07-05T06:26:56Z"},{"alias_kind":"pith_short_12","alias_value":"VQLSOKNB2TM7","created_at":"2026-07-05T06:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"VQLSOKNB2TM7R3XO","created_at":"2026-07-05T06:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"VQLSOKNB","created_at":"2026-07-05T06:26:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VQLSOKNB2TM7R3XO23VENXQX2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2307.00422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-01T20:18:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ba9265393565ecacc2c773307c8cbb9fc927259e24f64f7fd934701c476e0613","abstract_canon_sha256":"0ba494c5a4cec80d0f7371abbad5ab078296cee79a4b3e39ab0e636a19beca8f"},"schema_version":"1.0"},"canonical_sha256":"ac172729a1d4d9f8eeeed6ea46de17d63cd1b9fbfc5a79c307dff17af5b0aa6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:56.011425Z","signature_b64":"3v/ZdKtCo0Nal4EwLHMI17yfWEG+bKk3O6GqLc/fmVblE5IX0LJ7WJiJ7rXQ/qm1QSyqtJeBKXIUUGbPOPgGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac172729a1d4d9f8eeeed6ea46de17d63cd1b9fbfc5a79c307dff17af5b0aa6c","last_reissued_at":"2026-07-05T06:26:56.010985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:56.010985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.00422","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":"2026-07-05T06:26:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5aZ0f1k9C/EodNMSV1SC2nbf7gesqc0ardHb7ZPgDXLzKRH5LMruqNLFUGFCXsmLDfcXutXe0Jis2LQ278jnBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:32:34.618099Z"},"content_sha256":"b62a5dcea6784bc23f8738244ede0e2b82dcf14601ff8af9003d0e8e00d3607f","schema_version":"1.0","event_id":"sha256:b62a5dcea6784bc23f8738244ede0e2b82dcf14601ff8af9003d0e8e00d3607f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VQLSOKNB2TM7R3XO23VENXQX2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"JoinBoost: Grow Trees Over Normalized Data Using Only SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Eugene Wu, Jiaxiang Liu, Rathijit Sen, Zezhou Huang","submitted_at":"2023-07-01T20:18:45Z","abstract_excerpt":"Although dominant for tabular data, ML libraries that train tree models over normalized databases (e.g., LightGBM, XGBoost) require the data to be denormalized as a single table, materialized, and exported. This process is not scalable, slow, and poses security risks. In-DB ML aims to train models within DBMSes to avoid data movement and provide data governance. Rather than modify a DBMS to support In-DB ML, is it possible to offer competitive tree training performance to specialized ML libraries...with only SQL?\n  We present JoinBoost, a Python library that rewrites tree training algorithms o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00422","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/2307.00422/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":"2026-07-05T06:26:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0fZ/Y+flM09gTCud/quZoUJRRNYfIItKlR0biWaZNTp3h21AJ8rjAnveu29AbsMYSz4/EBAJxXY/ByBa21rnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:32:34.618506Z"},"content_sha256":"85a589f7715c197bfcc1902a575ea202871521976bae39ddd6f7e7c1dc1d1bb8","schema_version":"1.0","event_id":"sha256:85a589f7715c197bfcc1902a575ea202871521976bae39ddd6f7e7c1dc1d1bb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQLSOKNB2TM7R3XO23VENXQX2Y/bundle.json","state_url":"https://pith.science/pith/VQLSOKNB2TM7R3XO23VENXQX2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQLSOKNB2TM7R3XO23VENXQX2Y/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":"2026-07-05T13:32:34Z","links":{"resolver":"https://pith.science/pith/VQLSOKNB2TM7R3XO23VENXQX2Y","bundle":"https://pith.science/pith/VQLSOKNB2TM7R3XO23VENXQX2Y/bundle.json","state":"https://pith.science/pith/VQLSOKNB2TM7R3XO23VENXQX2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQLSOKNB2TM7R3XO23VENXQX2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VQLSOKNB2TM7R3XO23VENXQX2Y","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":"0ba494c5a4cec80d0f7371abbad5ab078296cee79a4b3e39ab0e636a19beca8f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-01T20:18:45Z","title_canon_sha256":"ba9265393565ecacc2c773307c8cbb9fc927259e24f64f7fd934701c476e0613"},"schema_version":"1.0","source":{"id":"2307.00422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00422","created_at":"2026-07-05T06:26:56Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00422v1","created_at":"2026-07-05T06:26:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00422","created_at":"2026-07-05T06:26:56Z"},{"alias_kind":"pith_short_12","alias_value":"VQLSOKNB2TM7","created_at":"2026-07-05T06:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"VQLSOKNB2TM7R3XO","created_at":"2026-07-05T06:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"VQLSOKNB","created_at":"2026-07-05T06:26:56Z"}],"graph_snapshots":[{"event_id":"sha256:85a589f7715c197bfcc1902a575ea202871521976bae39ddd6f7e7c1dc1d1bb8","target":"graph","created_at":"2026-07-05T06:26:56Z","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/2307.00422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although dominant for tabular data, ML libraries that train tree models over normalized databases (e.g., LightGBM, XGBoost) require the data to be denormalized as a single table, materialized, and exported. This process is not scalable, slow, and poses security risks. In-DB ML aims to train models within DBMSes to avoid data movement and provide data governance. Rather than modify a DBMS to support In-DB ML, is it possible to offer competitive tree training performance to specialized ML libraries...with only SQL?\n  We present JoinBoost, a Python library that rewrites tree training algorithms o","authors_text":"Eugene Wu, Jiaxiang Liu, Rathijit Sen, Zezhou Huang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-01T20:18:45Z","title":"JoinBoost: Grow Trees Over Normalized Data Using Only SQL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00422","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:b62a5dcea6784bc23f8738244ede0e2b82dcf14601ff8af9003d0e8e00d3607f","target":"record","created_at":"2026-07-05T06:26:56Z","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":"0ba494c5a4cec80d0f7371abbad5ab078296cee79a4b3e39ab0e636a19beca8f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-01T20:18:45Z","title_canon_sha256":"ba9265393565ecacc2c773307c8cbb9fc927259e24f64f7fd934701c476e0613"},"schema_version":"1.0","source":{"id":"2307.00422","kind":"arxiv","version":1}},"canonical_sha256":"ac172729a1d4d9f8eeeed6ea46de17d63cd1b9fbfc5a79c307dff17af5b0aa6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac172729a1d4d9f8eeeed6ea46de17d63cd1b9fbfc5a79c307dff17af5b0aa6c","first_computed_at":"2026-07-05T06:26:56.010985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:56.010985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3v/ZdKtCo0Nal4EwLHMI17yfWEG+bKk3O6GqLc/fmVblE5IX0LJ7WJiJ7rXQ/qm1QSyqtJeBKXIUUGbPOPgGDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:56.011425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.00422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b62a5dcea6784bc23f8738244ede0e2b82dcf14601ff8af9003d0e8e00d3607f","sha256:85a589f7715c197bfcc1902a575ea202871521976bae39ddd6f7e7c1dc1d1bb8"],"state_sha256":"bdbe8a17364ce78698e45ff83cb3297e5303b29d7c03f23bbd234cfceb971978"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nAYeZEsMQy8wjq0uBhryKNSWt1lvnpXbT4cBZ8TxDaRdLKIhTGOvIyg86u3HfL+WZH7n4Oj7JpCbZZXiIKxeCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:32:34.621136Z","bundle_sha256":"9ded6a193467d0fdc57b4e868a7aef021b1d066b99ebacb0db634263e38ce536"}}