{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4DOYVAKXPFUFOKZVOXYSVOVGRA","short_pith_number":"pith:4DOYVAKX","canonical_record":{"source":{"id":"2306.09610","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-06-16T03:58:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"101269869982b76067100e73d8a4e375a08afa4f9baed7fc7a5ba6327ef7f630","abstract_canon_sha256":"85ec170a73f5a99dfc21663997429749f2f2ca334f48cb4d303b623090cfd463"},"schema_version":"1.0"},"canonical_sha256":"e0dd8a81577968572b3575f12abaa6882a4946af122020ba23295dc48733cd41","source":{"kind":"arxiv","id":"2306.09610","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09610","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09610v3","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09610","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"4DOYVAKXPFUF","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"4DOYVAKXPFUFOKZV","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"4DOYVAKX","created_at":"2026-07-05T08:04:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4DOYVAKXPFUFOKZVOXYSVOVGRA","target":"record","payload":{"canonical_record":{"source":{"id":"2306.09610","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-06-16T03:58:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"101269869982b76067100e73d8a4e375a08afa4f9baed7fc7a5ba6327ef7f630","abstract_canon_sha256":"85ec170a73f5a99dfc21663997429749f2f2ca334f48cb4d303b623090cfd463"},"schema_version":"1.0"},"canonical_sha256":"e0dd8a81577968572b3575f12abaa6882a4946af122020ba23295dc48733cd41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:59.241067Z","signature_b64":"vG9jTgpdrt9QWugUkwsTyCjWdRubUkZd5kcVcjv2C3izpXqL3IJ5fAvwiJ02NCAhWQSLzTD/Pj4sSdUhZkT+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0dd8a81577968572b3575f12abaa6882a4946af122020ba23295dc48733cd41","last_reissued_at":"2026-07-05T08:04:59.240652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:59.240652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.09610","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":"2026-07-05T08:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZvtxXpIsLddiIkKXFqdamCX7NtJO7dUb5TxUfYhZ7BEozkNIA2gJKvKwidy4Mf08VEhAU9+NGeVlNfdeJ4RxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:17:35.012923Z"},"content_sha256":"56f8960146835a696c7a45f027a594351c6015ff033e93660c4f81c27abf52b7","schema_version":"1.0","event_id":"sha256:56f8960146835a696c7a45f027a594351c6015ff033e93660c4f81c27abf52b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4DOYVAKXPFUFOKZVOXYSVOVGRA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CHORUS: Foundation Models for Unified Data Discovery and Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Anton Lykov, Dan Olteanu, Dan Suciu, Ilias Fountalis, Moe Kayali, Nikolaos Vasiloglou","submitted_at":"2023-06-16T03:58:42Z","abstract_excerpt":"We apply foundation models to data discovery and exploration tasks. Foundation models include large language models (LLMs) that show promising performance on a range of diverse tasks unrelated to their training. We show that these models are highly applicable to the data discovery and data exploration domain. When carefully used, they have superior capability on three representative tasks: table-class detection, column-type annotation and join-column prediction. On all three tasks, we show that a foundation-model-based approach outperforms the task-specific models and so the state of the art. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09610","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/2306.09610/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":"2026-07-05T08:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M2YEHrCLiGFbLCL+MTcKGN8yXGIHp6++uasZrVV7MfVv1HbWSUKUACwJXnRYxeEeDnRLyk6jzfm0tjiZq+DABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:17:35.013801Z"},"content_sha256":"fd2c333a71a018e39334eb1c52b18c3c171c238789a277b47dedcf37732a6f5e","schema_version":"1.0","event_id":"sha256:fd2c333a71a018e39334eb1c52b18c3c171c238789a277b47dedcf37732a6f5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4DOYVAKXPFUFOKZVOXYSVOVGRA/bundle.json","state_url":"https://pith.science/pith/4DOYVAKXPFUFOKZVOXYSVOVGRA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4DOYVAKXPFUFOKZVOXYSVOVGRA/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":"2026-08-05T08:17:35Z","links":{"resolver":"https://pith.science/pith/4DOYVAKXPFUFOKZVOXYSVOVGRA","bundle":"https://pith.science/pith/4DOYVAKXPFUFOKZVOXYSVOVGRA/bundle.json","state":"https://pith.science/pith/4DOYVAKXPFUFOKZVOXYSVOVGRA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4DOYVAKXPFUFOKZVOXYSVOVGRA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4DOYVAKXPFUFOKZVOXYSVOVGRA","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":"85ec170a73f5a99dfc21663997429749f2f2ca334f48cb4d303b623090cfd463","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-06-16T03:58:42Z","title_canon_sha256":"101269869982b76067100e73d8a4e375a08afa4f9baed7fc7a5ba6327ef7f630"},"schema_version":"1.0","source":{"id":"2306.09610","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09610","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09610v3","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09610","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"4DOYVAKXPFUF","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"4DOYVAKXPFUFOKZV","created_at":"2026-07-05T08:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"4DOYVAKX","created_at":"2026-07-05T08:04:59Z"}],"graph_snapshots":[{"event_id":"sha256:fd2c333a71a018e39334eb1c52b18c3c171c238789a277b47dedcf37732a6f5e","target":"graph","created_at":"2026-07-05T08:04:59Z","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/2306.09610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We apply foundation models to data discovery and exploration tasks. Foundation models include large language models (LLMs) that show promising performance on a range of diverse tasks unrelated to their training. We show that these models are highly applicable to the data discovery and data exploration domain. When carefully used, they have superior capability on three representative tasks: table-class detection, column-type annotation and join-column prediction. On all three tasks, we show that a foundation-model-based approach outperforms the task-specific models and so the state of the art. ","authors_text":"Anton Lykov, Dan Olteanu, Dan Suciu, Ilias Fountalis, Moe Kayali, Nikolaos Vasiloglou","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-06-16T03:58:42Z","title":"CHORUS: Foundation Models for Unified Data Discovery and Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09610","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":"sha256:56f8960146835a696c7a45f027a594351c6015ff033e93660c4f81c27abf52b7","target":"record","created_at":"2026-07-05T08:04:59Z","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":"85ec170a73f5a99dfc21663997429749f2f2ca334f48cb4d303b623090cfd463","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-06-16T03:58:42Z","title_canon_sha256":"101269869982b76067100e73d8a4e375a08afa4f9baed7fc7a5ba6327ef7f630"},"schema_version":"1.0","source":{"id":"2306.09610","kind":"arxiv","version":3}},"canonical_sha256":"e0dd8a81577968572b3575f12abaa6882a4946af122020ba23295dc48733cd41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0dd8a81577968572b3575f12abaa6882a4946af122020ba23295dc48733cd41","first_computed_at":"2026-07-05T08:04:59.240652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:59.240652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vG9jTgpdrt9QWugUkwsTyCjWdRubUkZd5kcVcjv2C3izpXqL3IJ5fAvwiJ02NCAhWQSLzTD/Pj4sSdUhZkT+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:59.241067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09610","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56f8960146835a696c7a45f027a594351c6015ff033e93660c4f81c27abf52b7","sha256:fd2c333a71a018e39334eb1c52b18c3c171c238789a277b47dedcf37732a6f5e"],"state_sha256":"e08fa930d079a382fd157b900dd029f8027563f1532cff7b3a238e063f848c6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XwSOfSgGknKDTbb1QEd9rEIgqFYynv2prWW0UY1tug5e8IW1BBFDou4NW3q3W7jXbiJIYIViwaljuyWMav2xDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:17:35.019768Z","bundle_sha256":"35a1dcb1bd006e300dab853a7f92c9cec013071f6518289deccf6ec7d5d003b4"}}