{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PF4GUNDXQ57ZAQ3JVSUSZU5MFQ","short_pith_number":"pith:PF4GUNDX","canonical_record":{"source":{"id":"2312.01678","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-04T07:01:54Z","cross_cats_sorted":["cs.CL","cs.DB","cs.LG"],"title_canon_sha256":"cf878dbf2db9dbb9702f2c770c536fc926992ffa34b0b59f54e64edd0612992b","abstract_canon_sha256":"70ed0515a205bb9fa8679d3f963ddfa5fc76361b47390ed3936ad714398f644c"},"schema_version":"1.0"},"canonical_sha256":"79786a3477877f904369aca92cd3ac2c03d9482417b191400286330ac2638cb1","source":{"kind":"arxiv","id":"2312.01678","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01678","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01678v6","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01678","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_12","alias_value":"PF4GUNDXQ57Z","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_16","alias_value":"PF4GUNDXQ57ZAQ3J","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_8","alias_value":"PF4GUNDX","created_at":"2026-07-05T09:27:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PF4GUNDXQ57ZAQ3JVSUSZU5MFQ","target":"record","payload":{"canonical_record":{"source":{"id":"2312.01678","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-04T07:01:54Z","cross_cats_sorted":["cs.CL","cs.DB","cs.LG"],"title_canon_sha256":"cf878dbf2db9dbb9702f2c770c536fc926992ffa34b0b59f54e64edd0612992b","abstract_canon_sha256":"70ed0515a205bb9fa8679d3f963ddfa5fc76361b47390ed3936ad714398f644c"},"schema_version":"1.0"},"canonical_sha256":"79786a3477877f904369aca92cd3ac2c03d9482417b191400286330ac2638cb1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:19.860967Z","signature_b64":"QEElq0XC+ongGaZR3S/Op4RB42x4E3ECi5Ym2j11uCd7aKTI8c6UxXGX/NMm8dhJwosQHzNVRFt3iPVkJ6CBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79786a3477877f904369aca92cd3ac2c03d9482417b191400286330ac2638cb1","last_reissued_at":"2026-07-05T09:27:19.860415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:19.860415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.01678","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:27:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZlY3eTDJCBhdrd5EkmRSbqVy6T+c5eeORHdQ3ZR5Wqen4g11uURQbVxzgOLBTtFL/Wjxr2wfGK0xvFagXeciAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:49:33.311034Z"},"content_sha256":"e6a4cba3909ad9371bda987251c255cffab2fa2a8f6539dfb444d65e39c4bfdc","schema_version":"1.0","event_id":"sha256:e6a4cba3909ad9371bda987251c255cffab2fa2a8f6539dfb444d65e39c4bfdc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PF4GUNDXQ57ZAQ3JVSUSZU5MFQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jellyfish: A Large Language Model for Data Preprocessing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.DB","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chuan Xiao, Haochen Zhang, Masafumi Oyamada, Yuyang Dong","submitted_at":"2023-12-04T07:01:54Z","abstract_excerpt":"This paper explores the utilization of LLMs for data preprocessing (DP), a crucial step in the data mining pipeline that transforms raw data into a clean format conducive to easy processing. Whereas the use of LLMs has sparked interest in devising universal solutions to DP, recent initiatives in this domain typically rely on GPT APIs, raising inevitable data breach concerns. Unlike these approaches, we consider instruction-tuning local LLMs (7 -- 13B models) as universal DP task solvers that operate on a local, single, and low-priced GPU, ensuring data security and enabling further customizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01678","kind":"arxiv","version":6},"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/2312.01678/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":"2026-07-05T09:27:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQpEMcZs6YLxabTW+rkPfiLGWnXCtFyeuL4yhomRDlYGvSvBltm9CHCIjYPWWe186/7ch8cfPidy+1H1b7wzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:49:33.311651Z"},"content_sha256":"1a4d894b69dcd4da64413b9cf58e6d959fa197821c8595a706a253f45bdbadcf","schema_version":"1.0","event_id":"sha256:1a4d894b69dcd4da64413b9cf58e6d959fa197821c8595a706a253f45bdbadcf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PF4GUNDXQ57ZAQ3JVSUSZU5MFQ/bundle.json","state_url":"https://pith.science/pith/PF4GUNDXQ57ZAQ3JVSUSZU5MFQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PF4GUNDXQ57ZAQ3JVSUSZU5MFQ/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":"2026-08-09T05:49:33Z","links":{"resolver":"https://pith.science/pith/PF4GUNDXQ57ZAQ3JVSUSZU5MFQ","bundle":"https://pith.science/pith/PF4GUNDXQ57ZAQ3JVSUSZU5MFQ/bundle.json","state":"https://pith.science/pith/PF4GUNDXQ57ZAQ3JVSUSZU5MFQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PF4GUNDXQ57ZAQ3JVSUSZU5MFQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PF4GUNDXQ57ZAQ3JVSUSZU5MFQ","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":"70ed0515a205bb9fa8679d3f963ddfa5fc76361b47390ed3936ad714398f644c","cross_cats_sorted":["cs.CL","cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-04T07:01:54Z","title_canon_sha256":"cf878dbf2db9dbb9702f2c770c536fc926992ffa34b0b59f54e64edd0612992b"},"schema_version":"1.0","source":{"id":"2312.01678","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01678","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01678v6","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01678","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_12","alias_value":"PF4GUNDXQ57Z","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_16","alias_value":"PF4GUNDXQ57ZAQ3J","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_8","alias_value":"PF4GUNDX","created_at":"2026-07-05T09:27:19Z"}],"graph_snapshots":[{"event_id":"sha256:1a4d894b69dcd4da64413b9cf58e6d959fa197821c8595a706a253f45bdbadcf","target":"graph","created_at":"2026-07-05T09:27:19Z","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/2312.01678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores the utilization of LLMs for data preprocessing (DP), a crucial step in the data mining pipeline that transforms raw data into a clean format conducive to easy processing. Whereas the use of LLMs has sparked interest in devising universal solutions to DP, recent initiatives in this domain typically rely on GPT APIs, raising inevitable data breach concerns. Unlike these approaches, we consider instruction-tuning local LLMs (7 -- 13B models) as universal DP task solvers that operate on a local, single, and low-priced GPU, ensuring data security and enabling further customizati","authors_text":"Chuan Xiao, Haochen Zhang, Masafumi Oyamada, Yuyang Dong","cross_cats":["cs.CL","cs.DB","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-04T07:01:54Z","title":"Jellyfish: A Large Language Model for Data Preprocessing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01678","kind":"arxiv","version":6},"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:e6a4cba3909ad9371bda987251c255cffab2fa2a8f6539dfb444d65e39c4bfdc","target":"record","created_at":"2026-07-05T09:27:19Z","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":"70ed0515a205bb9fa8679d3f963ddfa5fc76361b47390ed3936ad714398f644c","cross_cats_sorted":["cs.CL","cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-04T07:01:54Z","title_canon_sha256":"cf878dbf2db9dbb9702f2c770c536fc926992ffa34b0b59f54e64edd0612992b"},"schema_version":"1.0","source":{"id":"2312.01678","kind":"arxiv","version":6}},"canonical_sha256":"79786a3477877f904369aca92cd3ac2c03d9482417b191400286330ac2638cb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79786a3477877f904369aca92cd3ac2c03d9482417b191400286330ac2638cb1","first_computed_at":"2026-07-05T09:27:19.860415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:19.860415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QEElq0XC+ongGaZR3S/Op4RB42x4E3ECi5Ym2j11uCd7aKTI8c6UxXGX/NMm8dhJwosQHzNVRFt3iPVkJ6CBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:19.860967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.01678","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6a4cba3909ad9371bda987251c255cffab2fa2a8f6539dfb444d65e39c4bfdc","sha256:1a4d894b69dcd4da64413b9cf58e6d959fa197821c8595a706a253f45bdbadcf"],"state_sha256":"6b7ec1c15a3aa4bf2d7bb86a8830ea54e4ddc76beceb5670ed1045c3554871eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4UgSyjVoBlyygYlrcR+rHdcryJoPwIJ4CU7f9GrPOssR3NhdLYIFZR4g5GneMLWZoD7Kz3x+jkjMCrgenfjnAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:49:33.316685Z","bundle_sha256":"7ca017e4c74efa8cd2e02c94f514a8662d8ec4c67f89257605446a06356334e5"}}