{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:POHJ6WXT3ZC3QMZH3DNV2WR2NQ","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":"debc54688eaac810c5f44daa126e92068b83458efa6613a5840652686def2af7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T02:16:53Z","title_canon_sha256":"db2174631458d8aa1c5bc7a0190a5735a60d032b567b3eb1b226f2d6f0e3ef3f"},"schema_version":"1.0","source":{"id":"2506.15068","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15068","created_at":"2026-07-05T11:23:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15068v1","created_at":"2026-07-05T11:23:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15068","created_at":"2026-07-05T11:23:36Z"},{"alias_kind":"pith_short_12","alias_value":"POHJ6WXT3ZC3","created_at":"2026-07-05T11:23:36Z"},{"alias_kind":"pith_short_16","alias_value":"POHJ6WXT3ZC3QMZH","created_at":"2026-07-05T11:23:36Z"},{"alias_kind":"pith_short_8","alias_value":"POHJ6WXT","created_at":"2026-07-05T11:23:36Z"}],"graph_snapshots":[{"event_id":"sha256:13503b2112a75ae4da28ff68bd854c31ea23f82db24ef083b68a41e0f45fa07e","target":"graph","created_at":"2026-07-05T11:23:36Z","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/2506.15068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating open-ended long-form generation is challenging because it is hard to define what clearly separates good from bad outputs. Existing methods often miss key aspects like coherence, style, or relevance, or are biased by pretraining data, making open-ended long-form evaluation an underexplored problem. To address this gap, we propose PrefBERT, a scoring model for evaluating open-ended long-form generation in GRPO and guiding its training with distinct rewards for good and bad outputs. Trained on two response evaluation datasets with diverse long-form styles and Likert-rated quality, Pref","authors_text":"Jordan Lee Boyd-Graber, Xiyang Wu, Yapei Chang, Yoo Yeon Sung, Yuhang Zhou, Zichao Liang, Zongxia Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T02:16:53Z","title":"Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15068","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:b8f82a5e4bcbea2d9fef98277cf678daaccc0cd0c6f0024c66379e35926d79fc","target":"record","created_at":"2026-07-05T11:23:36Z","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":"debc54688eaac810c5f44daa126e92068b83458efa6613a5840652686def2af7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T02:16:53Z","title_canon_sha256":"db2174631458d8aa1c5bc7a0190a5735a60d032b567b3eb1b226f2d6f0e3ef3f"},"schema_version":"1.0","source":{"id":"2506.15068","kind":"arxiv","version":1}},"canonical_sha256":"7b8e9f5af3de45b83327d8db5d5a3a6c3f9663ec7a4e5c290cc7eaec1b8c9897","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b8e9f5af3de45b83327d8db5d5a3a6c3f9663ec7a4e5c290cc7eaec1b8c9897","first_computed_at":"2026-07-05T11:23:36.474420Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:36.474420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5b/HrZ7vZKsnQK7VFfG0Rb6gDoMoxAAQ8MfI08WjCPsCujZnf9e8oKdeUA8xA/m6385evzlgo935y210NPakDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:36.474906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15068","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8f82a5e4bcbea2d9fef98277cf678daaccc0cd0c6f0024c66379e35926d79fc","sha256:13503b2112a75ae4da28ff68bd854c31ea23f82db24ef083b68a41e0f45fa07e"],"state_sha256":"175f2994a677b2a5a74df2a6ffed902e9de23222a8169391739fab7c27c11848"}