{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FRQ3SXZ6PUETEPRC7K4AO4SWEH","short_pith_number":"pith:FRQ3SXZ6","canonical_record":{"source":{"id":"2312.12112","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T12:34:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"46e33f1d4e62c1de287e0fdbdf2a90427279a4831b7547ca609194512ba3786c","abstract_canon_sha256":"3b9823628ed01b5b5898eda634e7bbef01eda245d87e8b16e90e53af180f81ba"},"schema_version":"1.0"},"canonical_sha256":"2c61b95f3e7d09323e22fab807725621cc124c7002ffe915e3c6605f8a8a77d0","source":{"kind":"arxiv","id":"2312.12112","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12112","created_at":"2026-07-05T08:38:04Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12112v3","created_at":"2026-07-05T08:38:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12112","created_at":"2026-07-05T08:38:04Z"},{"alias_kind":"pith_short_12","alias_value":"FRQ3SXZ6PUET","created_at":"2026-07-05T08:38:04Z"},{"alias_kind":"pith_short_16","alias_value":"FRQ3SXZ6PUETEPRC","created_at":"2026-07-05T08:38:04Z"},{"alias_kind":"pith_short_8","alias_value":"FRQ3SXZ6","created_at":"2026-07-05T08:38:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FRQ3SXZ6PUETEPRC7K4AO4SWEH","target":"record","payload":{"canonical_record":{"source":{"id":"2312.12112","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T12:34:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"46e33f1d4e62c1de287e0fdbdf2a90427279a4831b7547ca609194512ba3786c","abstract_canon_sha256":"3b9823628ed01b5b5898eda634e7bbef01eda245d87e8b16e90e53af180f81ba"},"schema_version":"1.0"},"canonical_sha256":"2c61b95f3e7d09323e22fab807725621cc124c7002ffe915e3c6605f8a8a77d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:04.861992Z","signature_b64":"oJZs+81W/dJ4qyG2s2FbLSrWAE569vTMkbIPo8qFgKlhk/xAAcZyFUdSWDlYRzno1CyeBqBDM9rMXFpg6tmLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c61b95f3e7d09323e22fab807725621cc124c7002ffe915e3c6605f8a8a77d0","last_reissued_at":"2026-07-05T08:38:04.861499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:04.861499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.12112","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:38:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5aBDuTXxB8p3s2/KDmjk05jdVqYQcphnWriAZ87wGlt3NC8OP0mtiMFDpOkqnl0HS1e0wr9eU+lOMgxa/V0MCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:54:05.182862Z"},"content_sha256":"6bf8651e5291becf59019a0a05ca4f56f9d6586c70ec331da4c471ba864ee89c","schema_version":"1.0","event_id":"sha256:6bf8651e5291becf59019a0a05ca4f56f9d6586c70ec331da4c471ba864ee89c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FRQ3SXZ6PUETEPRC7K4AO4SWEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boris van Breugel, Mihaela van der Schaar, Nabeel Seedat, Nicolas Huynh","submitted_at":"2023-12-19T12:34:46Z","abstract_excerpt":"Machine Learning (ML) in low-data settings remains an underappreciated yet crucial problem. Hence, data augmentation methods to increase the sample size of datasets needed for ML are key to unlocking the transformative potential of ML in data-deprived regions and domains. Unfortunately, the limited training set constrains traditional tabular synthetic data generators in their ability to generate a large and diverse augmented dataset needed for ML tasks. To address this challenge, we introduce CLLM, which leverages the prior knowledge of Large Language Models (LLMs) for data augmentation in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12112","kind":"arxiv","version":3},"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/2312.12112/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":"2026-07-05T08:38:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/QRIQagNY3+AYj+BWkMhLtDYuToqx60TiCbudV1goMqqBVB36UEFXal8VoLypA3Y9SCR6Da+6sTQ3/Qi+2NpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:54:05.183396Z"},"content_sha256":"9331689e5b661468c59494ad27a188a37bf2f493494cc09317d524640376f3ff","schema_version":"1.0","event_id":"sha256:9331689e5b661468c59494ad27a188a37bf2f493494cc09317d524640376f3ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRQ3SXZ6PUETEPRC7K4AO4SWEH/bundle.json","state_url":"https://pith.science/pith/FRQ3SXZ6PUETEPRC7K4AO4SWEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRQ3SXZ6PUETEPRC7K4AO4SWEH/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":"2026-08-23T10:54:05Z","links":{"resolver":"https://pith.science/pith/FRQ3SXZ6PUETEPRC7K4AO4SWEH","bundle":"https://pith.science/pith/FRQ3SXZ6PUETEPRC7K4AO4SWEH/bundle.json","state":"https://pith.science/pith/FRQ3SXZ6PUETEPRC7K4AO4SWEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRQ3SXZ6PUETEPRC7K4AO4SWEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FRQ3SXZ6PUETEPRC7K4AO4SWEH","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":"3b9823628ed01b5b5898eda634e7bbef01eda245d87e8b16e90e53af180f81ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T12:34:46Z","title_canon_sha256":"46e33f1d4e62c1de287e0fdbdf2a90427279a4831b7547ca609194512ba3786c"},"schema_version":"1.0","source":{"id":"2312.12112","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12112","created_at":"2026-07-05T08:38:04Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12112v3","created_at":"2026-07-05T08:38:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12112","created_at":"2026-07-05T08:38:04Z"},{"alias_kind":"pith_short_12","alias_value":"FRQ3SXZ6PUET","created_at":"2026-07-05T08:38:04Z"},{"alias_kind":"pith_short_16","alias_value":"FRQ3SXZ6PUETEPRC","created_at":"2026-07-05T08:38:04Z"},{"alias_kind":"pith_short_8","alias_value":"FRQ3SXZ6","created_at":"2026-07-05T08:38:04Z"}],"graph_snapshots":[{"event_id":"sha256:9331689e5b661468c59494ad27a188a37bf2f493494cc09317d524640376f3ff","target":"graph","created_at":"2026-07-05T08:38:04Z","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/2312.12112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine Learning (ML) in low-data settings remains an underappreciated yet crucial problem. Hence, data augmentation methods to increase the sample size of datasets needed for ML are key to unlocking the transformative potential of ML in data-deprived regions and domains. Unfortunately, the limited training set constrains traditional tabular synthetic data generators in their ability to generate a large and diverse augmented dataset needed for ML tasks. To address this challenge, we introduce CLLM, which leverages the prior knowledge of Large Language Models (LLMs) for data augmentation in the","authors_text":"Boris van Breugel, Mihaela van der Schaar, Nabeel Seedat, Nicolas Huynh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T12:34:46Z","title":"Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12112","kind":"arxiv","version":3},"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":"sha256:6bf8651e5291becf59019a0a05ca4f56f9d6586c70ec331da4c471ba864ee89c","target":"record","created_at":"2026-07-05T08:38:04Z","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":"3b9823628ed01b5b5898eda634e7bbef01eda245d87e8b16e90e53af180f81ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T12:34:46Z","title_canon_sha256":"46e33f1d4e62c1de287e0fdbdf2a90427279a4831b7547ca609194512ba3786c"},"schema_version":"1.0","source":{"id":"2312.12112","kind":"arxiv","version":3}},"canonical_sha256":"2c61b95f3e7d09323e22fab807725621cc124c7002ffe915e3c6605f8a8a77d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c61b95f3e7d09323e22fab807725621cc124c7002ffe915e3c6605f8a8a77d0","first_computed_at":"2026-07-05T08:38:04.861499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:04.861499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oJZs+81W/dJ4qyG2s2FbLSrWAE569vTMkbIPo8qFgKlhk/xAAcZyFUdSWDlYRzno1CyeBqBDM9rMXFpg6tmLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:04.861992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.12112","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bf8651e5291becf59019a0a05ca4f56f9d6586c70ec331da4c471ba864ee89c","sha256:9331689e5b661468c59494ad27a188a37bf2f493494cc09317d524640376f3ff"],"state_sha256":"c9ae7c67adb4eae1637a92f5fbbea835657179ad4f6d6e352ae210603df622bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4NB09nRVKPAKzLkTp9Rabw39lF0S+o53JtNdbKu77iE5NUgOf3NGnYjB0M73kVldaO1VfXwdqaznmfSHLJhUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T10:54:05.186578Z","bundle_sha256":"9eea043fe340031f59f5046be7e85cb665d3982fd03ff126cf6fa3eac66161f9"}}