{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:K7NH3OJL4VIVOGKIRNU26SZP3H","short_pith_number":"pith:K7NH3OJL","canonical_record":{"source":{"id":"2304.09433","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T06:00:26Z","cross_cats_sorted":[],"title_canon_sha256":"cc1a4b1d57d976500ecd33cc284d6ca05fd9c2d94e675c675fe4a6fe614f2b27","abstract_canon_sha256":"607f1dcabe2aa6f92751dea71c2e0d86861230be838deee7c074fb9263d05c10"},"schema_version":"1.0"},"canonical_sha256":"57da7db92be5515719488b69af4b2fd9ef99df9bb73c1c717ed1a8e5e60b08a7","source":{"kind":"arxiv","id":"2304.09433","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.09433","created_at":"2026-07-05T10:25:58Z"},{"alias_kind":"arxiv_version","alias_value":"2304.09433v3","created_at":"2026-07-05T10:25:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09433","created_at":"2026-07-05T10:25:58Z"},{"alias_kind":"pith_short_12","alias_value":"K7NH3OJL4VIV","created_at":"2026-07-05T10:25:58Z"},{"alias_kind":"pith_short_16","alias_value":"K7NH3OJL4VIVOGKI","created_at":"2026-07-05T10:25:58Z"},{"alias_kind":"pith_short_8","alias_value":"K7NH3OJL","created_at":"2026-07-05T10:25:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:K7NH3OJL4VIVOGKIRNU26SZP3H","target":"record","payload":{"canonical_record":{"source":{"id":"2304.09433","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T06:00:26Z","cross_cats_sorted":[],"title_canon_sha256":"cc1a4b1d57d976500ecd33cc284d6ca05fd9c2d94e675c675fe4a6fe614f2b27","abstract_canon_sha256":"607f1dcabe2aa6f92751dea71c2e0d86861230be838deee7c074fb9263d05c10"},"schema_version":"1.0"},"canonical_sha256":"57da7db92be5515719488b69af4b2fd9ef99df9bb73c1c717ed1a8e5e60b08a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:58.193142Z","signature_b64":"z5dPb5zyAlMclymnR1FaT64b/HPmMzwcpwTYTPD41dnyF9F6JtaMLOHm5JyeU9msLqpv/PVirzif5EwEL6FuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57da7db92be5515719488b69af4b2fd9ef99df9bb73c1c717ed1a8e5e60b08a7","last_reissued_at":"2026-07-05T10:25:58.192660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:58.192660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.09433","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:25:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gou0ujfK7GNBnbjFfv1cDkDPaq/pKTyh23hy58IbgfrRfXEO7upWUsrt/ZoXMHDychSTaO97Y6FXCHTVZC8hBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:15:41.904367Z"},"content_sha256":"7bc532e1a07290df7c35e38e658c6ef3f234d83623c1cc41ed474ddc8f60bc5b","schema_version":"1.0","event_id":"sha256:7bc532e1a07290df7c35e38e658c6ef3f234d83623c1cc41ed474ddc8f60bc5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:K7NH3OJL4VIVOGKIRNU26SZP3H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Hojel, Avanika Narayan, Brandon Yang, Christopher R\\'e, Immanuel Trummer, Sabri Eyuboglu, Simran Arora","submitted_at":"2023-04-19T06:00:26Z","abstract_excerpt":"A long standing goal of the data management community is to develop general, automated systems that ingest semi-structured documents and output queryable tables without human effort or domain specific customization. Given the sheer variety of potential documents, state-of-the art systems make simplifying assumptions and use domain specific training. In this work, we ask whether we can maintain generality by using large language models (LLMs). LLMs, which are pretrained on broad data, can perform diverse downstream tasks simply conditioned on natural language task descriptions.\n  We propose and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09433","kind":"arxiv","version":3},"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/2304.09433/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":"2026-07-05T10:25:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"twGrmKmz4pvFDtQE08GA2u/1Kr7r+rNtsQJfqAuNq2z80sIyhkvk5P+XpwSE9QMztHn/dMAVPkvd1M1u0MsnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:15:41.904740Z"},"content_sha256":"1a7b5a5ddeea66c21e029157c6561a25442d125c859f156e69dbb4fe4f824a74","schema_version":"1.0","event_id":"sha256:1a7b5a5ddeea66c21e029157c6561a25442d125c859f156e69dbb4fe4f824a74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K7NH3OJL4VIVOGKIRNU26SZP3H/bundle.json","state_url":"https://pith.science/pith/K7NH3OJL4VIVOGKIRNU26SZP3H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K7NH3OJL4VIVOGKIRNU26SZP3H/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":"2026-07-17T07:15:41Z","links":{"resolver":"https://pith.science/pith/K7NH3OJL4VIVOGKIRNU26SZP3H","bundle":"https://pith.science/pith/K7NH3OJL4VIVOGKIRNU26SZP3H/bundle.json","state":"https://pith.science/pith/K7NH3OJL4VIVOGKIRNU26SZP3H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K7NH3OJL4VIVOGKIRNU26SZP3H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K7NH3OJL4VIVOGKIRNU26SZP3H","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":"607f1dcabe2aa6f92751dea71c2e0d86861230be838deee7c074fb9263d05c10","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T06:00:26Z","title_canon_sha256":"cc1a4b1d57d976500ecd33cc284d6ca05fd9c2d94e675c675fe4a6fe614f2b27"},"schema_version":"1.0","source":{"id":"2304.09433","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.09433","created_at":"2026-07-05T10:25:58Z"},{"alias_kind":"arxiv_version","alias_value":"2304.09433v3","created_at":"2026-07-05T10:25:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09433","created_at":"2026-07-05T10:25:58Z"},{"alias_kind":"pith_short_12","alias_value":"K7NH3OJL4VIV","created_at":"2026-07-05T10:25:58Z"},{"alias_kind":"pith_short_16","alias_value":"K7NH3OJL4VIVOGKI","created_at":"2026-07-05T10:25:58Z"},{"alias_kind":"pith_short_8","alias_value":"K7NH3OJL","created_at":"2026-07-05T10:25:58Z"}],"graph_snapshots":[{"event_id":"sha256:1a7b5a5ddeea66c21e029157c6561a25442d125c859f156e69dbb4fe4f824a74","target":"graph","created_at":"2026-07-05T10:25:58Z","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/2304.09433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A long standing goal of the data management community is to develop general, automated systems that ingest semi-structured documents and output queryable tables without human effort or domain specific customization. Given the sheer variety of potential documents, state-of-the art systems make simplifying assumptions and use domain specific training. In this work, we ask whether we can maintain generality by using large language models (LLMs). LLMs, which are pretrained on broad data, can perform diverse downstream tasks simply conditioned on natural language task descriptions.\n  We propose and","authors_text":"Andrew Hojel, Avanika Narayan, Brandon Yang, Christopher R\\'e, Immanuel Trummer, Sabri Eyuboglu, Simran Arora","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T06:00:26Z","title":"Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09433","kind":"arxiv","version":3},"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":"sha256:7bc532e1a07290df7c35e38e658c6ef3f234d83623c1cc41ed474ddc8f60bc5b","target":"record","created_at":"2026-07-05T10:25:58Z","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":"607f1dcabe2aa6f92751dea71c2e0d86861230be838deee7c074fb9263d05c10","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T06:00:26Z","title_canon_sha256":"cc1a4b1d57d976500ecd33cc284d6ca05fd9c2d94e675c675fe4a6fe614f2b27"},"schema_version":"1.0","source":{"id":"2304.09433","kind":"arxiv","version":3}},"canonical_sha256":"57da7db92be5515719488b69af4b2fd9ef99df9bb73c1c717ed1a8e5e60b08a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57da7db92be5515719488b69af4b2fd9ef99df9bb73c1c717ed1a8e5e60b08a7","first_computed_at":"2026-07-05T10:25:58.192660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:58.192660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z5dPb5zyAlMclymnR1FaT64b/HPmMzwcpwTYTPD41dnyF9F6JtaMLOHm5JyeU9msLqpv/PVirzif5EwEL6FuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:58.193142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.09433","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bc532e1a07290df7c35e38e658c6ef3f234d83623c1cc41ed474ddc8f60bc5b","sha256:1a7b5a5ddeea66c21e029157c6561a25442d125c859f156e69dbb4fe4f824a74"],"state_sha256":"8e05ad422d0d0e4f357e36785d7b1802456344afd67cec82ff817f7c9bc33659"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZaXR6XQmCvLcnZEZ43wpa1Q6RKEufeM35XQNIabr1BWSty6RntxeXhs09ekRdc13EmUxstbWqGeKUkrafvQoDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T07:15:41.906996Z","bundle_sha256":"ba47b8af1ee0dbf822a1aca8f051bce7699d7cc7ee59e21082a843a93d29c57f"}}