{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DCZ6OYRSC3SY7C6QHAICMFIX7R","short_pith_number":"pith:DCZ6OYRS","canonical_record":{"source":{"id":"2405.01556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-21T10:01:05Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"20e73e27725e3f84b2d8a03af7f5afb4c455cbbcbaad059e8b6b1b96ee8e2613","abstract_canon_sha256":"6d7c3e215059607ebbccb762ea231e03696579024374182c1172911c16c65b21"},"schema_version":"1.0"},"canonical_sha256":"18b3e7623216e58f8bd03810261517fc4a6374674a0cfd6cd49ed1b44f5271e1","source":{"kind":"arxiv","id":"2405.01556","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01556","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01556v1","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01556","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"DCZ6OYRSC3SY","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"DCZ6OYRSC3SY7C6Q","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"DCZ6OYRS","created_at":"2026-07-05T08:14:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DCZ6OYRSC3SY7C6QHAICMFIX7R","target":"record","payload":{"canonical_record":{"source":{"id":"2405.01556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-21T10:01:05Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"20e73e27725e3f84b2d8a03af7f5afb4c455cbbcbaad059e8b6b1b96ee8e2613","abstract_canon_sha256":"6d7c3e215059607ebbccb762ea231e03696579024374182c1172911c16c65b21"},"schema_version":"1.0"},"canonical_sha256":"18b3e7623216e58f8bd03810261517fc4a6374674a0cfd6cd49ed1b44f5271e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:57.780935Z","signature_b64":"ljefHF/dkZYFQ+Cpf1mOiph6pUgQMUwUDkBo0jWxXoFjHygXYL9LkxAEJxQI1kOmdB8REhzhk/Er1BTHJzt8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18b3e7623216e58f8bd03810261517fc4a6374674a0cfd6cd49ed1b44f5271e1","last_reissued_at":"2026-07-05T08:14:57.780391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:57.780391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.01556","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":"2026-07-05T08:14:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S9MhXoQN5vP2uT70ZzRIhXlyDWKJC30IqlvjAh/wOI9V86NdS8CQ1sQFRwMniQXrw9Kh9LQkCI4BY3J+zMSDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T00:15:50.169782Z"},"content_sha256":"41030910e9b419aa9b96b4533eaa56ac6e6a7d235c78d5862bb77019d4814b8c","schema_version":"1.0","event_id":"sha256:41030910e9b419aa9b96b4533eaa56ac6e6a7d235c78d5862bb77019d4814b8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DCZ6OYRSC3SY7C6QHAICMFIX7R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantically Aligned Question and Code Generation for Automated Insight Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Ananya Singha, Anirudh Khatry, Austin Z. Henley, Bhavya Chopra, Chris Parnin, Gust Verbruggen, Mukul Singh, Sumit Gulwani, Vu Le","submitted_at":"2024-03-21T10:01:05Z","abstract_excerpt":"Automated insight generation is a common tactic for helping knowledge workers, such as data scientists, to quickly understand the potential value of new and unfamiliar data. Unfortunately, automated insights produced by large-language models can generate code that does not correctly correspond (or align) to the insight. In this paper, we leverage the semantic knowledge of large language models to generate targeted and insightful questions about data and the corresponding code to answer those questions. Then through an empirical study on data from Open-WikiTable, we show that embeddings can be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01556","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/2405.01556/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":"2026-07-05T08:14:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obKf1c8FylGZgFLgmyAo0LrERHqfmpycDvCQqu30c8XiNn4AVaDQ8J2pivsBkTsSEdyLyAKqmcWRHUu6ZhLaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T00:15:50.170386Z"},"content_sha256":"1cb73dc665b7e292ccf044dc3b563261134771e5f1e0cca00ed2a577419a6eee","schema_version":"1.0","event_id":"sha256:1cb73dc665b7e292ccf044dc3b563261134771e5f1e0cca00ed2a577419a6eee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DCZ6OYRSC3SY7C6QHAICMFIX7R/bundle.json","state_url":"https://pith.science/pith/DCZ6OYRSC3SY7C6QHAICMFIX7R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DCZ6OYRSC3SY7C6QHAICMFIX7R/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":"2026-07-09T00:15:50Z","links":{"resolver":"https://pith.science/pith/DCZ6OYRSC3SY7C6QHAICMFIX7R","bundle":"https://pith.science/pith/DCZ6OYRSC3SY7C6QHAICMFIX7R/bundle.json","state":"https://pith.science/pith/DCZ6OYRSC3SY7C6QHAICMFIX7R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DCZ6OYRSC3SY7C6QHAICMFIX7R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DCZ6OYRSC3SY7C6QHAICMFIX7R","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":"6d7c3e215059607ebbccb762ea231e03696579024374182c1172911c16c65b21","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-21T10:01:05Z","title_canon_sha256":"20e73e27725e3f84b2d8a03af7f5afb4c455cbbcbaad059e8b6b1b96ee8e2613"},"schema_version":"1.0","source":{"id":"2405.01556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01556","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01556v1","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01556","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"DCZ6OYRSC3SY","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"DCZ6OYRSC3SY7C6Q","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"DCZ6OYRS","created_at":"2026-07-05T08:14:57Z"}],"graph_snapshots":[{"event_id":"sha256:1cb73dc665b7e292ccf044dc3b563261134771e5f1e0cca00ed2a577419a6eee","target":"graph","created_at":"2026-07-05T08:14:57Z","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/2405.01556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated insight generation is a common tactic for helping knowledge workers, such as data scientists, to quickly understand the potential value of new and unfamiliar data. Unfortunately, automated insights produced by large-language models can generate code that does not correctly correspond (or align) to the insight. In this paper, we leverage the semantic knowledge of large language models to generate targeted and insightful questions about data and the corresponding code to answer those questions. Then through an empirical study on data from Open-WikiTable, we show that embeddings can be ","authors_text":"Ananya Singha, Anirudh Khatry, Austin Z. Henley, Bhavya Chopra, Chris Parnin, Gust Verbruggen, Mukul Singh, Sumit Gulwani, Vu Le","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-21T10:01:05Z","title":"Semantically Aligned Question and Code Generation for Automated Insight Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01556","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":"sha256:41030910e9b419aa9b96b4533eaa56ac6e6a7d235c78d5862bb77019d4814b8c","target":"record","created_at":"2026-07-05T08:14:57Z","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":"6d7c3e215059607ebbccb762ea231e03696579024374182c1172911c16c65b21","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-21T10:01:05Z","title_canon_sha256":"20e73e27725e3f84b2d8a03af7f5afb4c455cbbcbaad059e8b6b1b96ee8e2613"},"schema_version":"1.0","source":{"id":"2405.01556","kind":"arxiv","version":1}},"canonical_sha256":"18b3e7623216e58f8bd03810261517fc4a6374674a0cfd6cd49ed1b44f5271e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18b3e7623216e58f8bd03810261517fc4a6374674a0cfd6cd49ed1b44f5271e1","first_computed_at":"2026-07-05T08:14:57.780391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:57.780391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ljefHF/dkZYFQ+Cpf1mOiph6pUgQMUwUDkBo0jWxXoFjHygXYL9LkxAEJxQI1kOmdB8REhzhk/Er1BTHJzt8DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:57.780935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.01556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41030910e9b419aa9b96b4533eaa56ac6e6a7d235c78d5862bb77019d4814b8c","sha256:1cb73dc665b7e292ccf044dc3b563261134771e5f1e0cca00ed2a577419a6eee"],"state_sha256":"2e54580febbba1cbe6d8eee2ed8d8ee627cd3232cd0abfb69b87503d7652e6ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TvtssbVNNdkXT8/korzwHnESRzv+yeeB8+EE9w4+pA7ooV9wG1q/qxr8sgA1Qw2ga+7I8rduZAfM3X2VBzR8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T00:15:50.172560Z","bundle_sha256":"eabe321ea19945dd6b3570d0d572e441c9c3b8f5274b986e982fa80466b27f81"}}