{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M63DA7GXRXB5CESMG23CEV5VXG","short_pith_number":"pith:M63DA7GX","schema_version":"1.0","canonical_sha256":"67b6307cd78dc3d1124c36b62257b5b9b96057683c3d7a304b8ccbe3c2b82eb7","source":{"kind":"arxiv","id":"2505.21819","version":1},"attestation_state":"computed","paper":{"title":"Representative Language Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Charlotte Peale, Omer Reingold, Vinod Raman","submitted_at":"2025-05-27T23:02:54Z","abstract_excerpt":"We introduce \"representative generation,\" extending the theoretical framework for generation proposed by Kleinberg et al. (2024) and formalized by Li et al. (2024), to additionally address diversity and bias concerns in generative models. Our notion requires outputs of a generative model to proportionally represent groups of interest from the training data. We characterize representative uniform and non-uniform generation, introducing the \"group closure dimension\" as a key combinatorial quantity. For representative generation in the limit, we analyze both information-theoretic and computationa"},"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":"2505.21819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T23:02:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9bab7cd2b59d7b7aa03a7a4ba6d42d0b39da6704eec9bc9ba440ebc38225602d","abstract_canon_sha256":"3aadc85048956f4c9c4a76159e44c23f619c53409b6a488be73d8816fc062b12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:04.141263Z","signature_b64":"qmDFOQLcAgmNcnuNpfelYwWxV3nrCJmODJRAsBoX4DgOINVK4iY7RlZgJrfvcOwX13pmH1ysSF4UuIft4sxLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67b6307cd78dc3d1124c36b62257b5b9b96057683c3d7a304b8ccbe3c2b82eb7","last_reissued_at":"2026-07-05T11:11:04.140859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:04.140859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representative Language Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Charlotte Peale, Omer Reingold, Vinod Raman","submitted_at":"2025-05-27T23:02:54Z","abstract_excerpt":"We introduce \"representative generation,\" extending the theoretical framework for generation proposed by Kleinberg et al. (2024) and formalized by Li et al. (2024), to additionally address diversity and bias concerns in generative models. Our notion requires outputs of a generative model to proportionally represent groups of interest from the training data. We characterize representative uniform and non-uniform generation, introducing the \"group closure dimension\" as a key combinatorial quantity. For representative generation in the limit, we analyze both information-theoretic and computationa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21819","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/2505.21819/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":"2505.21819","created_at":"2026-07-05T11:11:04.140912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21819v1","created_at":"2026-07-05T11:11:04.140912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21819","created_at":"2026-07-05T11:11:04.140912+00:00"},{"alias_kind":"pith_short_12","alias_value":"M63DA7GXRXB5","created_at":"2026-07-05T11:11:04.140912+00:00"},{"alias_kind":"pith_short_16","alias_value":"M63DA7GXRXB5CESM","created_at":"2026-07-05T11:11:04.140912+00:00"},{"alias_kind":"pith_short_8","alias_value":"M63DA7GX","created_at":"2026-07-05T11:11:04.140912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25777","citing_title":"Space-Efficient Language Generation in the Limit","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10809","citing_title":"Mistake-Bounded Language Generation","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M63DA7GXRXB5CESMG23CEV5VXG","json":"https://pith.science/pith/M63DA7GXRXB5CESMG23CEV5VXG.json","graph_json":"https://pith.science/api/pith-number/M63DA7GXRXB5CESMG23CEV5VXG/graph.json","events_json":"https://pith.science/api/pith-number/M63DA7GXRXB5CESMG23CEV5VXG/events.json","paper":"https://pith.science/paper/M63DA7GX"},"agent_actions":{"view_html":"https://pith.science/pith/M63DA7GXRXB5CESMG23CEV5VXG","download_json":"https://pith.science/pith/M63DA7GXRXB5CESMG23CEV5VXG.json","view_paper":"https://pith.science/paper/M63DA7GX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21819&json=true","fetch_graph":"https://pith.science/api/pith-number/M63DA7GXRXB5CESMG23CEV5VXG/graph.json","fetch_events":"https://pith.science/api/pith-number/M63DA7GXRXB5CESMG23CEV5VXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M63DA7GXRXB5CESMG23CEV5VXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M63DA7GXRXB5CESMG23CEV5VXG/action/storage_attestation","attest_author":"https://pith.science/pith/M63DA7GXRXB5CESMG23CEV5VXG/action/author_attestation","sign_citation":"https://pith.science/pith/M63DA7GXRXB5CESMG23CEV5VXG/action/citation_signature","submit_replication":"https://pith.science/pith/M63DA7GXRXB5CESMG23CEV5VXG/action/replication_record"}},"created_at":"2026-07-05T11:11:04.140912+00:00","updated_at":"2026-07-05T11:11:04.140912+00:00"}