{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K2LVLBS6XNGBQM5FQG3LN5WA45","short_pith_number":"pith:K2LVLBS6","canonical_record":{"source":{"id":"2411.17110","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-11-26T05:00:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ce80fc55b16a4df9f96cf91156c6fc4ddd0384efe568302c4cf3e02145aacdb2","abstract_canon_sha256":"e01491cc40b0566d3b3505910df98bdc6f6a1e27d67e0b8b2b0ac5dd5cd47a99"},"schema_version":"1.0"},"canonical_sha256":"569755865ebb4c1833a581b6b6f6c0e74d1d1ebed1edd885a8c343dcfa1ffb1e","source":{"kind":"arxiv","id":"2411.17110","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17110","created_at":"2026-07-05T11:55:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17110v2","created_at":"2026-07-05T11:55:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17110","created_at":"2026-07-05T11:55:36Z"},{"alias_kind":"pith_short_12","alias_value":"K2LVLBS6XNGB","created_at":"2026-07-05T11:55:36Z"},{"alias_kind":"pith_short_16","alias_value":"K2LVLBS6XNGBQM5F","created_at":"2026-07-05T11:55:36Z"},{"alias_kind":"pith_short_8","alias_value":"K2LVLBS6","created_at":"2026-07-05T11:55:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K2LVLBS6XNGBQM5FQG3LN5WA45","target":"record","payload":{"canonical_record":{"source":{"id":"2411.17110","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-11-26T05:00:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ce80fc55b16a4df9f96cf91156c6fc4ddd0384efe568302c4cf3e02145aacdb2","abstract_canon_sha256":"e01491cc40b0566d3b3505910df98bdc6f6a1e27d67e0b8b2b0ac5dd5cd47a99"},"schema_version":"1.0"},"canonical_sha256":"569755865ebb4c1833a581b6b6f6c0e74d1d1ebed1edd885a8c343dcfa1ffb1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:36.933947Z","signature_b64":"+e5+Vefq/7JfmLnN2OGoSWfj6vbULxWlJRytWuJ48I+OO60myK+SxEH7Apik9lnlaV3n8dgYriybc1oo+HZBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"569755865ebb4c1833a581b6b6f6c0e74d1d1ebed1edd885a8c343dcfa1ffb1e","last_reissued_at":"2026-07-05T11:55:36.933488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:36.933488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.17110","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:55:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J20lsxcgoR+05wk7jfio6zYlaHebmsdMB1auwGe+b5M7WEkWQ+SxQ3+3zf5uBFf6I/E3QUDNSXpo8lJOUB3lDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:35:14.818240Z"},"content_sha256":"218db611b820726ffe7d1301ca1a729b4748082c3b20fceeade19661d0eb757a","schema_version":"1.0","event_id":"sha256:218db611b820726ffe7d1301ca1a729b4748082c3b20fceeade19661d0eb757a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K2LVLBS6XNGBQM5FQG3LN5WA45","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Arash Dargahi Nobari, Davood Rafiei","submitted_at":"2024-11-26T05:00:23Z","abstract_excerpt":"The integration of tabular data from diverse sources is often hindered by inconsistencies in formatting and representation, posing significant challenges for data analysts and personal digital assistants. Existing methods for automating tabular data transformations are limited in scope, often focusing on specific types of transformations or lacking interpretability. In this paper, we introduce TabulaX, a novel framework that leverages Large Language Models (LLMs) for multi-class column-level tabular transformations. TabulaX first classifies input columns into four transformation types (string-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17110","kind":"arxiv","version":2},"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/2411.17110/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":"2026-07-05T11:55:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LmUCNO5MbK3xwyHAKATCxhKQKiCL3V5CeutDyUZgia9A8x2biUtShe6ZsgGw/BzLgrAXGjWFpkO0V5cmAgh4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:35:14.818766Z"},"content_sha256":"ec8c6214d8ef44fc0ca91c02bcdb1a9e3037b2967f7dbadb01fac77b2d71d91a","schema_version":"1.0","event_id":"sha256:ec8c6214d8ef44fc0ca91c02bcdb1a9e3037b2967f7dbadb01fac77b2d71d91a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2LVLBS6XNGBQM5FQG3LN5WA45/bundle.json","state_url":"https://pith.science/pith/K2LVLBS6XNGBQM5FQG3LN5WA45/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2LVLBS6XNGBQM5FQG3LN5WA45/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":"2026-08-23T18:35:14Z","links":{"resolver":"https://pith.science/pith/K2LVLBS6XNGBQM5FQG3LN5WA45","bundle":"https://pith.science/pith/K2LVLBS6XNGBQM5FQG3LN5WA45/bundle.json","state":"https://pith.science/pith/K2LVLBS6XNGBQM5FQG3LN5WA45/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2LVLBS6XNGBQM5FQG3LN5WA45/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K2LVLBS6XNGBQM5FQG3LN5WA45","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":"e01491cc40b0566d3b3505910df98bdc6f6a1e27d67e0b8b2b0ac5dd5cd47a99","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-11-26T05:00:23Z","title_canon_sha256":"ce80fc55b16a4df9f96cf91156c6fc4ddd0384efe568302c4cf3e02145aacdb2"},"schema_version":"1.0","source":{"id":"2411.17110","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17110","created_at":"2026-07-05T11:55:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17110v2","created_at":"2026-07-05T11:55:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17110","created_at":"2026-07-05T11:55:36Z"},{"alias_kind":"pith_short_12","alias_value":"K2LVLBS6XNGB","created_at":"2026-07-05T11:55:36Z"},{"alias_kind":"pith_short_16","alias_value":"K2LVLBS6XNGBQM5F","created_at":"2026-07-05T11:55:36Z"},{"alias_kind":"pith_short_8","alias_value":"K2LVLBS6","created_at":"2026-07-05T11:55:36Z"}],"graph_snapshots":[{"event_id":"sha256:ec8c6214d8ef44fc0ca91c02bcdb1a9e3037b2967f7dbadb01fac77b2d71d91a","target":"graph","created_at":"2026-07-05T11:55:36Z","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/2411.17110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of tabular data from diverse sources is often hindered by inconsistencies in formatting and representation, posing significant challenges for data analysts and personal digital assistants. Existing methods for automating tabular data transformations are limited in scope, often focusing on specific types of transformations or lacking interpretability. In this paper, we introduce TabulaX, a novel framework that leverages Large Language Models (LLMs) for multi-class column-level tabular transformations. TabulaX first classifies input columns into four transformation types (string-","authors_text":"Arash Dargahi Nobari, Davood Rafiei","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-11-26T05:00:23Z","title":"TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17110","kind":"arxiv","version":2},"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":"sha256:218db611b820726ffe7d1301ca1a729b4748082c3b20fceeade19661d0eb757a","target":"record","created_at":"2026-07-05T11:55:36Z","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":"e01491cc40b0566d3b3505910df98bdc6f6a1e27d67e0b8b2b0ac5dd5cd47a99","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-11-26T05:00:23Z","title_canon_sha256":"ce80fc55b16a4df9f96cf91156c6fc4ddd0384efe568302c4cf3e02145aacdb2"},"schema_version":"1.0","source":{"id":"2411.17110","kind":"arxiv","version":2}},"canonical_sha256":"569755865ebb4c1833a581b6b6f6c0e74d1d1ebed1edd885a8c343dcfa1ffb1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"569755865ebb4c1833a581b6b6f6c0e74d1d1ebed1edd885a8c343dcfa1ffb1e","first_computed_at":"2026-07-05T11:55:36.933488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:36.933488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+e5+Vefq/7JfmLnN2OGoSWfj6vbULxWlJRytWuJ48I+OO60myK+SxEH7Apik9lnlaV3n8dgYriybc1oo+HZBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:36.933947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17110","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:218db611b820726ffe7d1301ca1a729b4748082c3b20fceeade19661d0eb757a","sha256:ec8c6214d8ef44fc0ca91c02bcdb1a9e3037b2967f7dbadb01fac77b2d71d91a"],"state_sha256":"e9cecea2e947163dd571ae3d0ccde17e025333eec118848cc71aa1713d96f8ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T60DXMBIny/8q50wbNY9lfD1j58lkQeYxA0W4StmDY8GaN6rM3m0G8VXAq3C5UT81ApYogpG79Qu3o+FaaHKCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T18:35:14.823923Z","bundle_sha256":"460c5f27695d9d07fc15857e5ab0362682e0c5daedf598409d07da23e8ac8802"}}