{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YRRPNQNUIPRYLGAAPO6QL6M46Q","short_pith_number":"pith:YRRPNQNU","canonical_record":{"source":{"id":"2405.06510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-10T14:44:04Z","cross_cats_sorted":[],"title_canon_sha256":"47fa542ba1506608248069d962a5be3d75d0fcc81f1f0516486b2e5220ce3867","abstract_canon_sha256":"895aa3f4ebd76947fd4dbcc8bfd8f2b8ac4c298a060d140c695011001de20b2c"},"schema_version":"1.0"},"canonical_sha256":"c462f6c1b443e38598007bbd05f99cf43ce5d3918c5d489801e22e37f59f783a","source":{"kind":"arxiv","id":"2405.06510","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.06510","created_at":"2026-07-05T08:17:50Z"},{"alias_kind":"arxiv_version","alias_value":"2405.06510v1","created_at":"2026-07-05T08:17:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06510","created_at":"2026-07-05T08:17:50Z"},{"alias_kind":"pith_short_12","alias_value":"YRRPNQNUIPRY","created_at":"2026-07-05T08:17:50Z"},{"alias_kind":"pith_short_16","alias_value":"YRRPNQNUIPRYLGAA","created_at":"2026-07-05T08:17:50Z"},{"alias_kind":"pith_short_8","alias_value":"YRRPNQNU","created_at":"2026-07-05T08:17:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YRRPNQNUIPRYLGAAPO6QL6M46Q","target":"record","payload":{"canonical_record":{"source":{"id":"2405.06510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-10T14:44:04Z","cross_cats_sorted":[],"title_canon_sha256":"47fa542ba1506608248069d962a5be3d75d0fcc81f1f0516486b2e5220ce3867","abstract_canon_sha256":"895aa3f4ebd76947fd4dbcc8bfd8f2b8ac4c298a060d140c695011001de20b2c"},"schema_version":"1.0"},"canonical_sha256":"c462f6c1b443e38598007bbd05f99cf43ce5d3918c5d489801e22e37f59f783a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:50.523329Z","signature_b64":"DyUEQjLrgcpXPM86GsGuMRcEDLYaE0Z6fqKv/cF0AuL3DH496x9tS+J/1OWWmqfq7vAUyoIrv1FKczK6CJwyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c462f6c1b443e38598007bbd05f99cf43ce5d3918c5d489801e22e37f59f783a","last_reissued_at":"2026-07-05T08:17:50.522811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:50.522811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.06510","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":"2026-07-05T08:17:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2T8pcVM9KNnv9NYPdEQ6E4NnWxqXAlDhU29b4qJFb6SuMoJwxGlbl6Tn27IUQ2x4rwjVP1i0N37rX2LPdNCbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T07:38:21.532993Z"},"content_sha256":"a5db0b6b59d2280ac0b736da3d1741c29a357a672db849a96490bfc61de6d481","schema_version":"1.0","event_id":"sha256:a5db0b6b59d2280ac0b736da3d1741c29a357a672db849a96490bfc61de6d481"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YRRPNQNUIPRYLGAAPO6QL6M46Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniDM: A Unified Framework for Data Manipulation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bolin Ding, Defu Lian, Haibin Wang, Jingren Zhou, Jintao Huang, Rong Zhu, Xiuyu Sun, Yaohua Wang, Yichen Qian, Yongyi He, Zhijian Ma","submitted_at":"2024-05-10T14:44:04Z","abstract_excerpt":"Designing effective data manipulation methods is a long standing problem in data lakes. Traditional methods, which rely on rules or machine learning models, require extensive human efforts on training data collection and tuning models. Recent methods apply Large Language Models (LLMs) to resolve multiple data manipulation tasks. They exhibit bright benefits in terms of performance but still require customized designs to fit each specific task. This is very costly and can not catch up with the requirements of big data lake platforms. In this paper, inspired by the cross-task generality of LLMs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06510","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/2405.06510/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":"2026-07-05T08:17:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n+3C2pHTg3vvymzhkfO3b9bXV51AyoqOqUOwnzC/VmvMR7fwv2OqSifJt2CxJn5fCDLGsldzo/bBY9BWfjVOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T07:38:21.533400Z"},"content_sha256":"1bd3cc5db1e1fb43200c209adf69cff8a45e9d01fa3892e2ec649c4753385f52","schema_version":"1.0","event_id":"sha256:1bd3cc5db1e1fb43200c209adf69cff8a45e9d01fa3892e2ec649c4753385f52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YRRPNQNUIPRYLGAAPO6QL6M46Q/bundle.json","state_url":"https://pith.science/pith/YRRPNQNUIPRYLGAAPO6QL6M46Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YRRPNQNUIPRYLGAAPO6QL6M46Q/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":"2026-07-27T07:38:21Z","links":{"resolver":"https://pith.science/pith/YRRPNQNUIPRYLGAAPO6QL6M46Q","bundle":"https://pith.science/pith/YRRPNQNUIPRYLGAAPO6QL6M46Q/bundle.json","state":"https://pith.science/pith/YRRPNQNUIPRYLGAAPO6QL6M46Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YRRPNQNUIPRYLGAAPO6QL6M46Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YRRPNQNUIPRYLGAAPO6QL6M46Q","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":"895aa3f4ebd76947fd4dbcc8bfd8f2b8ac4c298a060d140c695011001de20b2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-10T14:44:04Z","title_canon_sha256":"47fa542ba1506608248069d962a5be3d75d0fcc81f1f0516486b2e5220ce3867"},"schema_version":"1.0","source":{"id":"2405.06510","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.06510","created_at":"2026-07-05T08:17:50Z"},{"alias_kind":"arxiv_version","alias_value":"2405.06510v1","created_at":"2026-07-05T08:17:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06510","created_at":"2026-07-05T08:17:50Z"},{"alias_kind":"pith_short_12","alias_value":"YRRPNQNUIPRY","created_at":"2026-07-05T08:17:50Z"},{"alias_kind":"pith_short_16","alias_value":"YRRPNQNUIPRYLGAA","created_at":"2026-07-05T08:17:50Z"},{"alias_kind":"pith_short_8","alias_value":"YRRPNQNU","created_at":"2026-07-05T08:17:50Z"}],"graph_snapshots":[{"event_id":"sha256:1bd3cc5db1e1fb43200c209adf69cff8a45e9d01fa3892e2ec649c4753385f52","target":"graph","created_at":"2026-07-05T08:17:50Z","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/2405.06510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing effective data manipulation methods is a long standing problem in data lakes. Traditional methods, which rely on rules or machine learning models, require extensive human efforts on training data collection and tuning models. Recent methods apply Large Language Models (LLMs) to resolve multiple data manipulation tasks. They exhibit bright benefits in terms of performance but still require customized designs to fit each specific task. This is very costly and can not catch up with the requirements of big data lake platforms. In this paper, inspired by the cross-task generality of LLMs ","authors_text":"Bolin Ding, Defu Lian, Haibin Wang, Jingren Zhou, Jintao Huang, Rong Zhu, Xiuyu Sun, Yaohua Wang, Yichen Qian, Yongyi He, Zhijian Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-10T14:44:04Z","title":"UniDM: A Unified Framework for Data Manipulation with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06510","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:a5db0b6b59d2280ac0b736da3d1741c29a357a672db849a96490bfc61de6d481","target":"record","created_at":"2026-07-05T08:17:50Z","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":"895aa3f4ebd76947fd4dbcc8bfd8f2b8ac4c298a060d140c695011001de20b2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-10T14:44:04Z","title_canon_sha256":"47fa542ba1506608248069d962a5be3d75d0fcc81f1f0516486b2e5220ce3867"},"schema_version":"1.0","source":{"id":"2405.06510","kind":"arxiv","version":1}},"canonical_sha256":"c462f6c1b443e38598007bbd05f99cf43ce5d3918c5d489801e22e37f59f783a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c462f6c1b443e38598007bbd05f99cf43ce5d3918c5d489801e22e37f59f783a","first_computed_at":"2026-07-05T08:17:50.522811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:50.522811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DyUEQjLrgcpXPM86GsGuMRcEDLYaE0Z6fqKv/cF0AuL3DH496x9tS+J/1OWWmqfq7vAUyoIrv1FKczK6CJwyBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:50.523329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.06510","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5db0b6b59d2280ac0b736da3d1741c29a357a672db849a96490bfc61de6d481","sha256:1bd3cc5db1e1fb43200c209adf69cff8a45e9d01fa3892e2ec649c4753385f52"],"state_sha256":"e1c623635d49a18bc3e0fd38697d7c9367d8949e254f0feca13f4996b647b8ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pM5UKTB0xeXS8gYzRi3egh5JlyVVYkoSnShjC3jZ6jmt9NIzISKi/Q5W0vmJwPMSVU4+nFB9UNFC7Ir6fgc8DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T07:38:21.536003Z","bundle_sha256":"12fe67e4a96b28204d71c4a6c39a91906b7e3c2226346498cbfb65ba88cf7180"}}