{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H364XADWCAYDBLXCCD3HQH6KBK","short_pith_number":"pith:H364XADW","schema_version":"1.0","canonical_sha256":"3efdcb8076103030aee210f6781fca0a811a98eddd08dbb68e83954cc25011f7","source":{"kind":"arxiv","id":"2302.14233","version":2},"attestation_state":"computed","paper":{"title":"Goal Driven Discovery of Distributional Differences via Language Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Klein, Jacob Steinhardt, Jinwoo Ahn, Peter Zhang, Ruiqi Zhong, Steve Li","submitted_at":"2023-02-28T01:32:32Z","abstract_excerpt":"Mining large corpora can generate useful discoveries but is time-consuming for humans. We formulate a new task, D5, that automatically discovers differences between two large corpora in a goal-driven way. The task input is a problem comprising a research goal \"$\\textit{comparing the side effects of drug A and drug B}$\" and a corpus pair (two large collections of patients' self-reported reactions after taking each drug). The output is a language description (discovery) of how these corpora differ (patients taking drug A \"$\\textit{mention feelings of paranoia}$\" more often). We build a D5 system"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.14233","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T01:32:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"496620dcfd66a9f37077b4dc5008bab24740653b5f11b6808a316a1fedc59841","abstract_canon_sha256":"4903193eb5e0cf80911b17167d8c82df866a63c1d9cd36e612c9af0df212987f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:45.432707Z","signature_b64":"eARpTPU9Cz5RX1CnhtnLrRgl2EIeUX6mG/kzL9VWZgDLGd+oxhw3XIe31T0v/d4gYaeZFx2HHqrsj5uNv8qkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3efdcb8076103030aee210f6781fca0a811a98eddd08dbb68e83954cc25011f7","last_reissued_at":"2026-07-05T07:04:45.432238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:45.432238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Goal Driven Discovery of Distributional Differences via Language Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Klein, Jacob Steinhardt, Jinwoo Ahn, Peter Zhang, Ruiqi Zhong, Steve Li","submitted_at":"2023-02-28T01:32:32Z","abstract_excerpt":"Mining large corpora can generate useful discoveries but is time-consuming for humans. We formulate a new task, D5, that automatically discovers differences between two large corpora in a goal-driven way. The task input is a problem comprising a research goal \"$\\textit{comparing the side effects of drug A and drug B}$\" and a corpus pair (two large collections of patients' self-reported reactions after taking each drug). The output is a language description (discovery) of how these corpora differ (patients taking drug A \"$\\textit{mention feelings of paranoia}$\" more often). We build a D5 system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14233","kind":"arxiv","version":2},"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/2302.14233/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.14233","created_at":"2026-07-05T07:04:45.432289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14233v2","created_at":"2026-07-05T07:04:45.432289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14233","created_at":"2026-07-05T07:04:45.432289+00:00"},{"alias_kind":"pith_short_12","alias_value":"H364XADWCAYD","created_at":"2026-07-05T07:04:45.432289+00:00"},{"alias_kind":"pith_short_16","alias_value":"H364XADWCAYDBLXC","created_at":"2026-07-05T07:04:45.432289+00:00"},{"alias_kind":"pith_short_8","alias_value":"H364XADW","created_at":"2026-07-05T07:04:45.432289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30775","citing_title":"A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2408.00724","citing_title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","ref_index":270,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03808","citing_title":"Agentic-imodels: Evolving agentic interpretability tools via autoresearch","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK","json":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK.json","graph_json":"https://pith.science/api/pith-number/H364XADWCAYDBLXCCD3HQH6KBK/graph.json","events_json":"https://pith.science/api/pith-number/H364XADWCAYDBLXCCD3HQH6KBK/events.json","paper":"https://pith.science/paper/H364XADW"},"agent_actions":{"view_html":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK","download_json":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK.json","view_paper":"https://pith.science/paper/H364XADW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14233&json=true","fetch_graph":"https://pith.science/api/pith-number/H364XADWCAYDBLXCCD3HQH6KBK/graph.json","fetch_events":"https://pith.science/api/pith-number/H364XADWCAYDBLXCCD3HQH6KBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK/action/storage_attestation","attest_author":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK/action/author_attestation","sign_citation":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK/action/citation_signature","submit_replication":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK/action/replication_record"}},"created_at":"2026-07-05T07:04:45.432289+00:00","updated_at":"2026-07-05T07:04:45.432289+00:00"}