{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JEVYTYU2JBII4JS6MDFNGBGFKD","short_pith_number":"pith:JEVYTYU2","canonical_record":{"source":{"id":"2212.09248","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T05:06:00Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"b98b52f2f663b08ba27fe798da7f8a37bfbcbbac92be98431d7363d178075a6a","abstract_canon_sha256":"f74cca67bbf729789040ee67a120b00a494d7e1d07a4c3e242a3157ab583ec88"},"schema_version":"1.0"},"canonical_sha256":"492b89e29a48508e265e60cad304c550c50bc7650b63746efb86e73de508bd41","source":{"kind":"arxiv","id":"2212.09248","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09248","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09248v1","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09248","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_12","alias_value":"JEVYTYU2JBII","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_16","alias_value":"JEVYTYU2JBII4JS6","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_8","alias_value":"JEVYTYU2","created_at":"2026-07-05T05:26:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JEVYTYU2JBII4JS6MDFNGBGFKD","target":"record","payload":{"canonical_record":{"source":{"id":"2212.09248","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T05:06:00Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"b98b52f2f663b08ba27fe798da7f8a37bfbcbbac92be98431d7363d178075a6a","abstract_canon_sha256":"f74cca67bbf729789040ee67a120b00a494d7e1d07a4c3e242a3157ab583ec88"},"schema_version":"1.0"},"canonical_sha256":"492b89e29a48508e265e60cad304c550c50bc7650b63746efb86e73de508bd41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:19.678035Z","signature_b64":"YmNz74ViOAKA/yee8fzLNVoWHUyzE+5WzHOUNPw1+87CeUcL3J43WQYvQkJ7rhMArUdAlXW/MSLgm4/qPvQlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"492b89e29a48508e265e60cad304c550c50bc7650b63746efb86e73de508bd41","last_reissued_at":"2026-07-05T05:26:19.677515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:19.677515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.09248","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":"2026-07-05T05:26:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3f/czodIonBvQigCcagtSiN8XdCuSSaeMI5s7mWWibbZe046Ngc45PFb02AH0p5DncDsSIuAs4Nd4eelpRsAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T21:58:02.819061Z"},"content_sha256":"b2e5e69501f6d091239d80fa27cc935a5b252cca1a9a62fe853a02e73dbc23bf","schema_version":"1.0","event_id":"sha256:b2e5e69501f6d091239d80fa27cc935a5b252cca1a9a62fe853a02e73dbc23bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JEVYTYU2JBII4JS6MDFNGBGFKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Language to Code Generation in Interactive Data Science Notebooks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Abhishek Rao, Alex Polozov, Charles Sutton, Henryk Michalewski, Joshua Howland, Kefan Xiao, Kensen Shi, Michele Catasta, Paige Bailey, Pengcheng Yin, Wen-Ding Li, Yeming Wen","submitted_at":"2022-12-19T05:06:00Z","abstract_excerpt":"Computational notebooks, such as Jupyter notebooks, are interactive computing environments that are ubiquitous among data scientists to perform data wrangling and analytic tasks. To measure the performance of AI pair programmers that automatically synthesize programs for those tasks given natural language (NL) intents from users, we build ARCADE, a benchmark of 1082 code generation problems using the pandas data analysis framework in data science notebooks. ARCADE features multiple rounds of NL-to-code problems from the same notebook. It requires a model to understand rich multi-modal contexts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09248","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/2212.09248/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":"2026-07-05T05:26:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XiHXxZtLmTLPIG6utupE8XDSsxpu9w81efHUQDunSn+0CSkfVqbe4gCzIjhKQ2cw1VwH79IIPTwk3cbp0uMLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T21:58:02.819457Z"},"content_sha256":"ce5fc477dcb8077b3fc326e743cde490bac1e66f4499939a56d32b61f29482e6","schema_version":"1.0","event_id":"sha256:ce5fc477dcb8077b3fc326e743cde490bac1e66f4499939a56d32b61f29482e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JEVYTYU2JBII4JS6MDFNGBGFKD/bundle.json","state_url":"https://pith.science/pith/JEVYTYU2JBII4JS6MDFNGBGFKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JEVYTYU2JBII4JS6MDFNGBGFKD/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":"2026-07-21T21:58:02Z","links":{"resolver":"https://pith.science/pith/JEVYTYU2JBII4JS6MDFNGBGFKD","bundle":"https://pith.science/pith/JEVYTYU2JBII4JS6MDFNGBGFKD/bundle.json","state":"https://pith.science/pith/JEVYTYU2JBII4JS6MDFNGBGFKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JEVYTYU2JBII4JS6MDFNGBGFKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JEVYTYU2JBII4JS6MDFNGBGFKD","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":"f74cca67bbf729789040ee67a120b00a494d7e1d07a4c3e242a3157ab583ec88","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T05:06:00Z","title_canon_sha256":"b98b52f2f663b08ba27fe798da7f8a37bfbcbbac92be98431d7363d178075a6a"},"schema_version":"1.0","source":{"id":"2212.09248","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09248","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09248v1","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09248","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_12","alias_value":"JEVYTYU2JBII","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_16","alias_value":"JEVYTYU2JBII4JS6","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_8","alias_value":"JEVYTYU2","created_at":"2026-07-05T05:26:19Z"}],"graph_snapshots":[{"event_id":"sha256:ce5fc477dcb8077b3fc326e743cde490bac1e66f4499939a56d32b61f29482e6","target":"graph","created_at":"2026-07-05T05:26:19Z","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/2212.09248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computational notebooks, such as Jupyter notebooks, are interactive computing environments that are ubiquitous among data scientists to perform data wrangling and analytic tasks. To measure the performance of AI pair programmers that automatically synthesize programs for those tasks given natural language (NL) intents from users, we build ARCADE, a benchmark of 1082 code generation problems using the pandas data analysis framework in data science notebooks. ARCADE features multiple rounds of NL-to-code problems from the same notebook. It requires a model to understand rich multi-modal contexts","authors_text":"Abhishek Rao, Alex Polozov, Charles Sutton, Henryk Michalewski, Joshua Howland, Kefan Xiao, Kensen Shi, Michele Catasta, Paige Bailey, Pengcheng Yin, Wen-Ding Li, Yeming Wen","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T05:06:00Z","title":"Natural Language to Code Generation in Interactive Data Science Notebooks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09248","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:b2e5e69501f6d091239d80fa27cc935a5b252cca1a9a62fe853a02e73dbc23bf","target":"record","created_at":"2026-07-05T05:26:19Z","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":"f74cca67bbf729789040ee67a120b00a494d7e1d07a4c3e242a3157ab583ec88","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T05:06:00Z","title_canon_sha256":"b98b52f2f663b08ba27fe798da7f8a37bfbcbbac92be98431d7363d178075a6a"},"schema_version":"1.0","source":{"id":"2212.09248","kind":"arxiv","version":1}},"canonical_sha256":"492b89e29a48508e265e60cad304c550c50bc7650b63746efb86e73de508bd41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"492b89e29a48508e265e60cad304c550c50bc7650b63746efb86e73de508bd41","first_computed_at":"2026-07-05T05:26:19.677515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:19.677515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YmNz74ViOAKA/yee8fzLNVoWHUyzE+5WzHOUNPw1+87CeUcL3J43WQYvQkJ7rhMArUdAlXW/MSLgm4/qPvQlDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:19.678035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09248","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2e5e69501f6d091239d80fa27cc935a5b252cca1a9a62fe853a02e73dbc23bf","sha256:ce5fc477dcb8077b3fc326e743cde490bac1e66f4499939a56d32b61f29482e6"],"state_sha256":"c700c923294e45aefeb35f21c5859972ffef111dacbf0aa7f08d9b650056ff28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C63Aeo4XPJP+6H+IH4I1HoZrBsCzQMzdAtzY3x12rwWg+v+XdvbdIQ5lkvxE/w5X0ZzayK/ojaDj4ApHJ4QRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T21:58:02.821967Z","bundle_sha256":"8d13f84541d42d093a74b1d6ed8f4d5f632089ed6e84b9a6cbb29ebdb3340eb8"}}