{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6HJLP3I45QCWQQ53BDJGVCCSAA","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":"e731e181253f76fbfcab1caa30ac9697352f51a9804e6de02d2c8fe20c3c1f0a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T17:38:47Z","title_canon_sha256":"0d88f6488af2b782bd508612c86f4fc972f3c8b8db43a40c261ab9f034ec5a11"},"schema_version":"1.0","source":{"id":"2509.02534","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02534","created_at":"2026-07-05T12:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02534v1","created_at":"2026-07-05T12:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02534","created_at":"2026-07-05T12:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"6HJLP3I45QCW","created_at":"2026-07-05T12:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"6HJLP3I45QCWQQ53","created_at":"2026-07-05T12:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"6HJLP3I4","created_at":"2026-07-05T12:03:40Z"}],"graph_snapshots":[{"event_id":"sha256:f6c4e9e5983b59eb1849cb1eceacefac5a4e31ef4d7b58a493b93b5440ea37a3","target":"graph","created_at":"2026-07-05T12:03:40Z","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/2509.02534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training of Large Language Models (LMs) often prioritizes accuracy and helpfulness at the expense of diversity. This creates a tension: while post-training improves response quality, it also sharpens output distributions and reduces the range of ideas, limiting the usefulness of LMs in creative and exploratory tasks such as brainstorming, storytelling, or problem solving. We address this challenge with Diversity-Aware Reinforcement Learning (DARLING), a framework that jointly optimizes for response quality and semantic diversity. At its core, DARLING introduces a learned partition functio","authors_text":"Daniel Khashabi, Jack Lanchantin, Jason Weston, Ping Yu, Swarnadeep Saha, Tianjian Li, Tianlu Wang, Yiming Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T17:38:47Z","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02534","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":"sha256:6cd607ea71e1c2769d39df4b7b5782f1400f0ec615421fa447109bf9b8000caa","target":"record","created_at":"2026-07-05T12:03:40Z","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":"e731e181253f76fbfcab1caa30ac9697352f51a9804e6de02d2c8fe20c3c1f0a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T17:38:47Z","title_canon_sha256":"0d88f6488af2b782bd508612c86f4fc972f3c8b8db43a40c261ab9f034ec5a11"},"schema_version":"1.0","source":{"id":"2509.02534","kind":"arxiv","version":1}},"canonical_sha256":"f1d2b7ed1cec056843bb08d26a8852001dcfba6be0d07b8f134bd006d6738570","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1d2b7ed1cec056843bb08d26a8852001dcfba6be0d07b8f134bd006d6738570","first_computed_at":"2026-07-05T12:03:40.530064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:40.530064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d5ZvPVBIXHZqKf5PQWUWgZvwKG72i8GMEfSSQf2KSmKjxujCqTi81G1/MPlCmj3eJq374+fbMdS+pr78c5tkAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:40.530585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02534","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cd607ea71e1c2769d39df4b7b5782f1400f0ec615421fa447109bf9b8000caa","sha256:f6c4e9e5983b59eb1849cb1eceacefac5a4e31ef4d7b58a493b93b5440ea37a3"],"state_sha256":"92bca086f8354e78195e7cf0f053324fccd1b0fad06207b5b3a3bcb5d7c4e596"}