{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LHVJNTZ2HRMHEHJ6OY3GGBY7QB","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":"1d04ae22e95214ccdd4117825467e7427f4d0470cc1db1a1d03feffe445be4b0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T08:26:43Z","title_canon_sha256":"4be819e7c6f2c68692436b4d030f5a1be0d0a7af7dbb3be1e4fc5ec248e9e42c"},"schema_version":"1.0","source":{"id":"2402.13610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13610","created_at":"2026-07-05T07:47:34Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13610v1","created_at":"2026-07-05T07:47:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13610","created_at":"2026-07-05T07:47:34Z"},{"alias_kind":"pith_short_12","alias_value":"LHVJNTZ2HRMH","created_at":"2026-07-05T07:47:34Z"},{"alias_kind":"pith_short_16","alias_value":"LHVJNTZ2HRMHEHJ6","created_at":"2026-07-05T07:47:34Z"},{"alias_kind":"pith_short_8","alias_value":"LHVJNTZ2","created_at":"2026-07-05T07:47:34Z"}],"graph_snapshots":[{"event_id":"sha256:b76c10e4c6028e51c02eab35977a20fab54ace2955958dea3cc234115ea78329","target":"graph","created_at":"2026-07-05T07:47:34Z","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/2402.13610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the accumulation of data at an unprecedented rate, its potential to fuel scientific discovery is growing exponentially. This position paper urges the Machine Learning (ML) community to exploit the capabilities of large generative models (LGMs) to develop automated systems for end-to-end data-driven discovery -- a paradigm encompassing the search and verification of hypotheses purely from a set of provided datasets, without the need for additional data collection or physical experiments. We first outline several desiderata for an ideal data-driven discovery system. Then, through DATAVOYAGE","authors_text":"Ashish Sabharwal, Bodhisattwa Prasad Majumder, Dhruv Agarwal, Harshit Surana, Peter Clark, Sanchaita Hazra","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T08:26:43Z","title":"Data-driven Discovery with Large Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13610","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:bc6a885d39ac1c87d41456fc2ef917007a1d9e60085b9a63f17b5e812cb972d9","target":"record","created_at":"2026-07-05T07:47:34Z","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":"1d04ae22e95214ccdd4117825467e7427f4d0470cc1db1a1d03feffe445be4b0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T08:26:43Z","title_canon_sha256":"4be819e7c6f2c68692436b4d030f5a1be0d0a7af7dbb3be1e4fc5ec248e9e42c"},"schema_version":"1.0","source":{"id":"2402.13610","kind":"arxiv","version":1}},"canonical_sha256":"59ea96cf3a3c58721d3e763663071f8048ddfc09bd6cc8aaef4b349acbf112d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59ea96cf3a3c58721d3e763663071f8048ddfc09bd6cc8aaef4b349acbf112d5","first_computed_at":"2026-07-05T07:47:34.687174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:34.687174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MMXwjP3Fdrs8p68MFegPssJLEfILlxuO+0r88RpQfICrqZyO+flbTrSAh8ePuk2skm+Z0Hc79RUBKGTl2D0PCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:34.687585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc6a885d39ac1c87d41456fc2ef917007a1d9e60085b9a63f17b5e812cb972d9","sha256:b76c10e4c6028e51c02eab35977a20fab54ace2955958dea3cc234115ea78329"],"state_sha256":"66c30586ba57af65e92f117c0c0e68aa717c88ec5650f15787e2a186f5c26bb1"}