{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GHUAI744USNAIIE5IS3ZTI5IWS","short_pith_number":"pith:GHUAI744","canonical_record":{"source":{"id":"2402.18679","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-28T19:49:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ddf726c4ec1e8feb99199f2dc2b7f92644d075d82bdecaa4d93d1a5f5d16cecb","abstract_canon_sha256":"abcc7e7331df8c4c4054cd1168f277f40f519620081a0d8b4ba2c02615bcacca"},"schema_version":"1.0"},"canonical_sha256":"31e8047f9ca49a04209d44b799a3a8b48ea34fad4736b6ebb9aac9d186ded778","source":{"kind":"arxiv","id":"2402.18679","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18679","created_at":"2026-07-05T09:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18679v4","created_at":"2026-07-05T09:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18679","created_at":"2026-07-05T09:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"GHUAI744USNA","created_at":"2026-07-05T09:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"GHUAI744USNAIIE5","created_at":"2026-07-05T09:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"GHUAI744","created_at":"2026-07-05T09:20:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GHUAI744USNAIIE5IS3ZTI5IWS","target":"record","payload":{"canonical_record":{"source":{"id":"2402.18679","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-28T19:49:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ddf726c4ec1e8feb99199f2dc2b7f92644d075d82bdecaa4d93d1a5f5d16cecb","abstract_canon_sha256":"abcc7e7331df8c4c4054cd1168f277f40f519620081a0d8b4ba2c02615bcacca"},"schema_version":"1.0"},"canonical_sha256":"31e8047f9ca49a04209d44b799a3a8b48ea34fad4736b6ebb9aac9d186ded778","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:40.820124Z","signature_b64":"/tlDpOQJUdui+8U3SBH+UMfEvNSmadPu1SdTn3byTd2SwuMOUzjBTTE1+dwyGGGNTjczUidOGYUL1VV3MSERBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31e8047f9ca49a04209d44b799a3a8b48ea34fad4736b6ebb9aac9d186ded778","last_reissued_at":"2026-07-05T09:20:40.819646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:40.819646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.18679","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:20:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NO1iMvz5pBOoniLMPEGFR9JLXD/PEeEhG3Vc/f7GiOLj9hI/IMm09jazxuQwzn6ubjiKCVQvOsyVESAyWX3/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T20:13:34.983061Z"},"content_sha256":"f3ded721314ad9a0e257c27c0ab2ab9e6a4b73872dc9de600a1073273785c617","schema_version":"1.0","event_id":"sha256:f3ded721314ad9a0e257c27c0ab2ab9e6a4b73872dc9de600a1073273785c617"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GHUAI744USNAIIE5IS3ZTI5IWS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Interpreter: An LLM Agent For Data Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bangbang Liu, Bang Liu, Binhao Wu, Ceyao Zhang, Chenglin Wu, Chenxing Wei, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Lingyao Zhang, Li Zhang, Mingchen Zhuge, Min Yang, Sirui Hong, Taicheng Guo, Tuo Zhou, Wei Tao, Xiangru Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yizhang Lin, Yuheng Cheng, Zhibin Gou, Zongze Xu","submitted_at":"2024-02-28T19:49:55Z","abstract_excerpt":"Large Language Model (LLM)-based agents have shown effectiveness across many applications. However, their use in data science scenarios requiring solving long-term interconnected tasks, dynamic data adjustments and domain expertise remains challenging. Previous approaches primarily focus on individual tasks, making it difficult to assess the complete data science workflow. Moreover, they struggle to handle real-time changes in intermediate data and fail to adapt dynamically to evolving task dependencies inherent to data science problems. In this paper, we present Data Interpreter, an LLM-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18679","kind":"arxiv","version":4},"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/2402.18679/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":"2026-07-05T09:20:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Iq249DV9iuZ9Tzq+A/940MLo+hfGBoTu7BNB0j0H6a2aGEx0dkk/nZBPUeRpzuSWaBoW4+zgPyymt0/Ky4TAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T20:13:34.983458Z"},"content_sha256":"4f4895c2be18725fa66bbcc10f859d1c4a6338e9267b6f17926e64247d4757d3","schema_version":"1.0","event_id":"sha256:4f4895c2be18725fa66bbcc10f859d1c4a6338e9267b6f17926e64247d4757d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS/bundle.json","state_url":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHUAI744USNAIIE5IS3ZTI5IWS/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":"2026-07-17T20:13:34Z","links":{"resolver":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS","bundle":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS/bundle.json","state":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHUAI744USNAIIE5IS3ZTI5IWS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GHUAI744USNAIIE5IS3ZTI5IWS","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":"abcc7e7331df8c4c4054cd1168f277f40f519620081a0d8b4ba2c02615bcacca","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-28T19:49:55Z","title_canon_sha256":"ddf726c4ec1e8feb99199f2dc2b7f92644d075d82bdecaa4d93d1a5f5d16cecb"},"schema_version":"1.0","source":{"id":"2402.18679","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18679","created_at":"2026-07-05T09:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18679v4","created_at":"2026-07-05T09:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18679","created_at":"2026-07-05T09:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"GHUAI744USNA","created_at":"2026-07-05T09:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"GHUAI744USNAIIE5","created_at":"2026-07-05T09:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"GHUAI744","created_at":"2026-07-05T09:20:40Z"}],"graph_snapshots":[{"event_id":"sha256:4f4895c2be18725fa66bbcc10f859d1c4a6338e9267b6f17926e64247d4757d3","target":"graph","created_at":"2026-07-05T09:20:40Z","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/2402.18679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM)-based agents have shown effectiveness across many applications. However, their use in data science scenarios requiring solving long-term interconnected tasks, dynamic data adjustments and domain expertise remains challenging. Previous approaches primarily focus on individual tasks, making it difficult to assess the complete data science workflow. Moreover, they struggle to handle real-time changes in intermediate data and fail to adapt dynamically to evolving task dependencies inherent to data science problems. In this paper, we present Data Interpreter, an LLM-based","authors_text":"Bangbang Liu, Bang Liu, Binhao Wu, Ceyao Zhang, Chenglin Wu, Chenxing Wei, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Lingyao Zhang, Li Zhang, Mingchen Zhuge, Min Yang, Sirui Hong, Taicheng Guo, Tuo Zhou, Wei Tao, Xiangru Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yizhang Lin, Yuheng Cheng, Zhibin Gou, Zongze Xu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-28T19:49:55Z","title":"Data Interpreter: An LLM Agent For Data Science"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18679","kind":"arxiv","version":4},"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:f3ded721314ad9a0e257c27c0ab2ab9e6a4b73872dc9de600a1073273785c617","target":"record","created_at":"2026-07-05T09:20:40Z","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":"abcc7e7331df8c4c4054cd1168f277f40f519620081a0d8b4ba2c02615bcacca","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-28T19:49:55Z","title_canon_sha256":"ddf726c4ec1e8feb99199f2dc2b7f92644d075d82bdecaa4d93d1a5f5d16cecb"},"schema_version":"1.0","source":{"id":"2402.18679","kind":"arxiv","version":4}},"canonical_sha256":"31e8047f9ca49a04209d44b799a3a8b48ea34fad4736b6ebb9aac9d186ded778","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31e8047f9ca49a04209d44b799a3a8b48ea34fad4736b6ebb9aac9d186ded778","first_computed_at":"2026-07-05T09:20:40.819646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:40.819646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/tlDpOQJUdui+8U3SBH+UMfEvNSmadPu1SdTn3byTd2SwuMOUzjBTTE1+dwyGGGNTjczUidOGYUL1VV3MSERBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:40.820124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18679","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3ded721314ad9a0e257c27c0ab2ab9e6a4b73872dc9de600a1073273785c617","sha256:4f4895c2be18725fa66bbcc10f859d1c4a6338e9267b6f17926e64247d4757d3"],"state_sha256":"e83b42ddd3fe25f8fa47927bcfa18313d3e316cd008976c9975251d2314b204b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M1PdbJMoTLVDtJKeqcUvLWU1x7FIHL5SKy8QvnKZHmAlexLEgZg9ooG60nURS3QCu9bYmOo9j1AUJwXr+NpeAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T20:13:34.986073Z","bundle_sha256":"0a2c8c89bde88cf0f14639bbaee81a76bf404355d4f614cbdda7a0e5c658cc9e"}}