{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F3ZKWAN5AH43X6JCHUTM6HX7XJ","short_pith_number":"pith:F3ZKWAN5","canonical_record":{"source":{"id":"2409.13551","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-20T14:49:51Z","cross_cats_sorted":["cs.CL","cs.DB"],"title_canon_sha256":"1a1045bc1723216c2c5a1c2104c6ee95bf00c52905d91c22c705769f9a8de81a","abstract_canon_sha256":"4efb1eddf186590414c3fdadfd48450e9b1d7e113458f90176c5da3fdfb415e9"},"schema_version":"1.0"},"canonical_sha256":"2ef2ab01bd01f9bbf9223d26cf1effba4843fd6bf41c561fc7e6dc78db1a69ae","source":{"kind":"arxiv","id":"2409.13551","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13551","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13551v1","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13551","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"F3ZKWAN5AH43","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"F3ZKWAN5AH43X6JC","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"F3ZKWAN5","created_at":"2026-07-05T09:09:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F3ZKWAN5AH43X6JCHUTM6HX7XJ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.13551","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-20T14:49:51Z","cross_cats_sorted":["cs.CL","cs.DB"],"title_canon_sha256":"1a1045bc1723216c2c5a1c2104c6ee95bf00c52905d91c22c705769f9a8de81a","abstract_canon_sha256":"4efb1eddf186590414c3fdadfd48450e9b1d7e113458f90176c5da3fdfb415e9"},"schema_version":"1.0"},"canonical_sha256":"2ef2ab01bd01f9bbf9223d26cf1effba4843fd6bf41c561fc7e6dc78db1a69ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:37.472891Z","signature_b64":"UKjHUYGYyxBpj69UZLokAEX7Iazm3SQPzzqYJw6Fv/V0Od6H1Fn0tMBSt0BXtx9gA4Qt2ekclOvM4ASkc7hGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ef2ab01bd01f9bbf9223d26cf1effba4843fd6bf41c561fc7e6dc78db1a69ae","last_reissued_at":"2026-07-05T09:09:37.472302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:37.472302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.13551","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":"2026-07-05T09:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h9vy71URsKeHT1zzUZyrkqzi8OU0PGj8pKzooUeqLg2dz/e/mPwx7PrSd7LNF10FhhGT3orF2fvw9Fp+37VeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:18:27.924032Z"},"content_sha256":"78cf584a9b2d95f17700050cae535f2f07ae8bd9bb4ad8631ac553f90728072f","schema_version":"1.0","event_id":"sha256:78cf584a9b2d95f17700050cae535f2f07ae8bd9bb4ad8631ac553f90728072f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F3ZKWAN5AH43X6JCHUTM6HX7XJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.DB"],"primary_cat":"cs.SE","authors_text":"Chenglong Wang, Cong Yan, Daya Guo, Jeevana Priya Inala, Jianfeng Gao, Jiazhen Gu, Junjie Huang, Michael R. Lyu, Nan Duan, Shuai Lu","submitted_at":"2024-09-20T14:49:51Z","abstract_excerpt":"Data wrangling, the process of preparing raw data for further analysis in computational notebooks, is a crucial yet time-consuming step in data science. Code generation has the potential to automate the data wrangling process to reduce analysts' overhead by translating user intents into executable code. Precisely generating data wrangling code necessitates a comprehensive consideration of the rich context present in notebooks, including textual context, code context and data context. However, notebooks often interleave multiple non-linear analysis tasks into linear sequence of code blocks, whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13551","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/2409.13551/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":"2026-07-05T09:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6T/S9QTbiuLcMvS7vhRjTPFGaqIeY/OI02vcBKuugiOnOLJVnJbDncFhVoFZ4cLTvEz4ChwoppwPTIfyVf4VDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:18:27.925072Z"},"content_sha256":"59a51a05110fa0ec89df52acca626fd5c6ac4d94360a2a200dc6846af52a3269","schema_version":"1.0","event_id":"sha256:59a51a05110fa0ec89df52acca626fd5c6ac4d94360a2a200dc6846af52a3269"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3ZKWAN5AH43X6JCHUTM6HX7XJ/bundle.json","state_url":"https://pith.science/pith/F3ZKWAN5AH43X6JCHUTM6HX7XJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3ZKWAN5AH43X6JCHUTM6HX7XJ/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":"2026-08-17T19:18:27Z","links":{"resolver":"https://pith.science/pith/F3ZKWAN5AH43X6JCHUTM6HX7XJ","bundle":"https://pith.science/pith/F3ZKWAN5AH43X6JCHUTM6HX7XJ/bundle.json","state":"https://pith.science/pith/F3ZKWAN5AH43X6JCHUTM6HX7XJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3ZKWAN5AH43X6JCHUTM6HX7XJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F3ZKWAN5AH43X6JCHUTM6HX7XJ","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":"4efb1eddf186590414c3fdadfd48450e9b1d7e113458f90176c5da3fdfb415e9","cross_cats_sorted":["cs.CL","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-20T14:49:51Z","title_canon_sha256":"1a1045bc1723216c2c5a1c2104c6ee95bf00c52905d91c22c705769f9a8de81a"},"schema_version":"1.0","source":{"id":"2409.13551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13551","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13551v1","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13551","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"F3ZKWAN5AH43","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"F3ZKWAN5AH43X6JC","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"F3ZKWAN5","created_at":"2026-07-05T09:09:37Z"}],"graph_snapshots":[{"event_id":"sha256:59a51a05110fa0ec89df52acca626fd5c6ac4d94360a2a200dc6846af52a3269","target":"graph","created_at":"2026-07-05T09:09:37Z","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/2409.13551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data wrangling, the process of preparing raw data for further analysis in computational notebooks, is a crucial yet time-consuming step in data science. Code generation has the potential to automate the data wrangling process to reduce analysts' overhead by translating user intents into executable code. Precisely generating data wrangling code necessitates a comprehensive consideration of the rich context present in notebooks, including textual context, code context and data context. However, notebooks often interleave multiple non-linear analysis tasks into linear sequence of code blocks, whe","authors_text":"Chenglong Wang, Cong Yan, Daya Guo, Jeevana Priya Inala, Jianfeng Gao, Jiazhen Gu, Junjie Huang, Michael R. Lyu, Nan Duan, Shuai Lu","cross_cats":["cs.CL","cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-20T14:49:51Z","title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13551","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":"sha256:78cf584a9b2d95f17700050cae535f2f07ae8bd9bb4ad8631ac553f90728072f","target":"record","created_at":"2026-07-05T09:09:37Z","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":"4efb1eddf186590414c3fdadfd48450e9b1d7e113458f90176c5da3fdfb415e9","cross_cats_sorted":["cs.CL","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-20T14:49:51Z","title_canon_sha256":"1a1045bc1723216c2c5a1c2104c6ee95bf00c52905d91c22c705769f9a8de81a"},"schema_version":"1.0","source":{"id":"2409.13551","kind":"arxiv","version":1}},"canonical_sha256":"2ef2ab01bd01f9bbf9223d26cf1effba4843fd6bf41c561fc7e6dc78db1a69ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ef2ab01bd01f9bbf9223d26cf1effba4843fd6bf41c561fc7e6dc78db1a69ae","first_computed_at":"2026-07-05T09:09:37.472302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:37.472302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UKjHUYGYyxBpj69UZLokAEX7Iazm3SQPzzqYJw6Fv/V0Od6H1Fn0tMBSt0BXtx9gA4Qt2ekclOvM4ASkc7hGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:37.472891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13551","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78cf584a9b2d95f17700050cae535f2f07ae8bd9bb4ad8631ac553f90728072f","sha256:59a51a05110fa0ec89df52acca626fd5c6ac4d94360a2a200dc6846af52a3269"],"state_sha256":"9c539f522a40a4a0eb02a668076d2a8e15dc90c317b1b7f6f969cbd08d7a9032"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lDV1DMIhwQcEPQPHZGGEigXlwUUaQeeFpekh79aS3rwJbfLQ9T0g+L7fXXXjiROiCQgOXnHHpqXEY2ZUBvpiBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T19:18:27.931595Z","bundle_sha256":"4c0249cbcc93419450519b9d020b3520a99c291e56bfac7976ffa09e15b6335c"}}