{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FQ27K776DVPLUQRX2W22KY3EXD","short_pith_number":"pith:FQ27K776","schema_version":"1.0","canonical_sha256":"2c35f57ffe1d5eba4237d5b5a56364b8d48f482274ea95a01fe4243cbe6a8a4b","source":{"kind":"arxiv","id":"2407.02209","version":1},"attestation_state":"computed","paper":{"title":"Generative Monoculture in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Emily Black, Fan Wu, Varun Chandrasekaran","submitted_at":"2024-07-02T12:17:07Z","abstract_excerpt":"We introduce {\\em generative monoculture}, a behavior observed in large language models (LLMs) characterized by a significant narrowing of model output diversity relative to available training data for a given task: for example, generating only positive book reviews for books with a mixed reception. While in some cases, generative monoculture enhances performance (e.g., LLMs more often produce efficient code), the dangers are exacerbated in others (e.g., LLMs refuse to share diverse opinions). As LLMs are increasingly used in high-impact settings such as education and web search, careful maint"},"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":"2407.02209","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T12:17:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fc5563f98c2162b818cb5f90feeca06786ab19b62db1cf94d90ad197a7f95a5d","abstract_canon_sha256":"51982bd7b7e6d55b93659442218331f3d4be5c43e13f264472e299ff033096a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:11.687358Z","signature_b64":"Fc4KQSyOLMZEjgKGuqbWhnkRnR+p2nFtnMgc/oL/OqrVy5vaBRnkHrMr/VSenH81ZBKFXxojVe1LV5UeF/CUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c35f57ffe1d5eba4237d5b5a56364b8d48f482274ea95a01fe4243cbe6a8a4b","last_reissued_at":"2026-07-05T08:39:11.686959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:11.686959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Monoculture in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Emily Black, Fan Wu, Varun Chandrasekaran","submitted_at":"2024-07-02T12:17:07Z","abstract_excerpt":"We introduce {\\em generative monoculture}, a behavior observed in large language models (LLMs) characterized by a significant narrowing of model output diversity relative to available training data for a given task: for example, generating only positive book reviews for books with a mixed reception. While in some cases, generative monoculture enhances performance (e.g., LLMs more often produce efficient code), the dangers are exacerbated in others (e.g., LLMs refuse to share diverse opinions). As LLMs are increasingly used in high-impact settings such as education and web search, careful maint"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02209","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/2407.02209/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":"2407.02209","created_at":"2026-07-05T08:39:11.687017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02209v1","created_at":"2026-07-05T08:39:11.687017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02209","created_at":"2026-07-05T08:39:11.687017+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQ27K776DVPL","created_at":"2026-07-05T08:39:11.687017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQ27K776DVPLUQRX","created_at":"2026-07-05T08:39:11.687017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQ27K776","created_at":"2026-07-05T08:39:11.687017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10574","citing_title":"LLM Jaggedness Unlocks Scientific Creativity","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10574","citing_title":"LLM Jaggedness Unlocks Scientific Creativity","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQ27K776DVPLUQRX2W22KY3EXD","json":"https://pith.science/pith/FQ27K776DVPLUQRX2W22KY3EXD.json","graph_json":"https://pith.science/api/pith-number/FQ27K776DVPLUQRX2W22KY3EXD/graph.json","events_json":"https://pith.science/api/pith-number/FQ27K776DVPLUQRX2W22KY3EXD/events.json","paper":"https://pith.science/paper/FQ27K776"},"agent_actions":{"view_html":"https://pith.science/pith/FQ27K776DVPLUQRX2W22KY3EXD","download_json":"https://pith.science/pith/FQ27K776DVPLUQRX2W22KY3EXD.json","view_paper":"https://pith.science/paper/FQ27K776","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02209&json=true","fetch_graph":"https://pith.science/api/pith-number/FQ27K776DVPLUQRX2W22KY3EXD/graph.json","fetch_events":"https://pith.science/api/pith-number/FQ27K776DVPLUQRX2W22KY3EXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQ27K776DVPLUQRX2W22KY3EXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQ27K776DVPLUQRX2W22KY3EXD/action/storage_attestation","attest_author":"https://pith.science/pith/FQ27K776DVPLUQRX2W22KY3EXD/action/author_attestation","sign_citation":"https://pith.science/pith/FQ27K776DVPLUQRX2W22KY3EXD/action/citation_signature","submit_replication":"https://pith.science/pith/FQ27K776DVPLUQRX2W22KY3EXD/action/replication_record"}},"created_at":"2026-07-05T08:39:11.687017+00:00","updated_at":"2026-07-05T08:39:11.687017+00:00"}