{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JB2UKSGUBZ6YCM5Y4E3L3W27T3","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":"0e03c9d31b355bc6b117caa39ccb475a6116e2c5fd7ec5b59c08d64404b783d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T11:03:25Z","title_canon_sha256":"95c49dd84ebb3ad43674551a0560975ec752d650fc4de71a23b2ba2df91a5d56"},"schema_version":"1.0","source":{"id":"2412.09173","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09173","created_at":"2026-07-05T09:48:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09173v1","created_at":"2026-07-05T09:48:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09173","created_at":"2026-07-05T09:48:20Z"},{"alias_kind":"pith_short_12","alias_value":"JB2UKSGUBZ6Y","created_at":"2026-07-05T09:48:20Z"},{"alias_kind":"pith_short_16","alias_value":"JB2UKSGUBZ6YCM5Y","created_at":"2026-07-05T09:48:20Z"},{"alias_kind":"pith_short_8","alias_value":"JB2UKSGU","created_at":"2026-07-05T09:48:20Z"}],"graph_snapshots":[{"event_id":"sha256:29fae27cdfc796f5f18d812249de1e4981af859cb584feedbb0af50e4857411e","target":"graph","created_at":"2026-07-05T09:48:20Z","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/2412.09173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Following formatting instructions to generate well-structured content is a fundamental yet often unmet capability for large language models (LLMs). To study this capability, which we refer to as format faithfulness, we present FormatBench, a comprehensive format-related benchmark. Compared to previous format-related benchmarks, FormatBench involves a greater variety of tasks in terms of application scenes (traditional NLP tasks, creative works, autonomous agency tasks), human-LLM interaction styles (single-turn instruction, multi-turn chat), and format types (inclusion, wrapping, length, codin","authors_text":"Boao Qian, Haoyu Wen, Heyan Huang, Jiashu Yao, Wei Su, Yuhang Guo, Zeming Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T11:03:25Z","title":"ReFF: Reinforcing Format Faithfulness in Language Models across Varied Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09173","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:c2af8efddfd429e84408ade1768f85ed5e063ffc5b7f05e7ee0e2654092cdcf9","target":"record","created_at":"2026-07-05T09:48:20Z","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":"0e03c9d31b355bc6b117caa39ccb475a6116e2c5fd7ec5b59c08d64404b783d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T11:03:25Z","title_canon_sha256":"95c49dd84ebb3ad43674551a0560975ec752d650fc4de71a23b2ba2df91a5d56"},"schema_version":"1.0","source":{"id":"2412.09173","kind":"arxiv","version":1}},"canonical_sha256":"48754548d40e7d8133b8e136bddb5f9ef3eeed22f8d5912cce9c5998f88eb03b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48754548d40e7d8133b8e136bddb5f9ef3eeed22f8d5912cce9c5998f88eb03b","first_computed_at":"2026-07-05T09:48:20.634480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:20.634480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YyAcPd58L2K/hU9ti3s1zvG9p9TAx1vPhfTT9g+LnswJIf5Kck9R6t67qP4C06oXoN11ZLCuOwo30QXHFo6WAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:20.634925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09173","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2af8efddfd429e84408ade1768f85ed5e063ffc5b7f05e7ee0e2654092cdcf9","sha256:29fae27cdfc796f5f18d812249de1e4981af859cb584feedbb0af50e4857411e"],"state_sha256":"3acb7ebfcc6976001ec53e3b508d35b097805c5a7922a7e1cbb894e9af907f73"}