{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q4GGTFXVNOXHKNAIFZJCXPPJDZ","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":"7b3e658bee4bdaa2d4d2f82f1671c32ad903c2386266500f872e1fb56446cd13","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T09:02:33Z","title_canon_sha256":"9f2b753866b68aab921777650bace348dc6241be18d373aa2528c437076f9f56"},"schema_version":"1.0","source":{"id":"2606.01936","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01936","created_at":"2026-06-02T02:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01936v1","created_at":"2026-06-02T02:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01936","created_at":"2026-06-02T02:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"Q4GGTFXVNOXH","created_at":"2026-06-02T02:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"Q4GGTFXVNOXHKNAI","created_at":"2026-06-02T02:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"Q4GGTFXV","created_at":"2026-06-02T02:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:e3634d980e7382f419fabde74676fc450f034e68c8790c9de5e802c1415e0247","target":"graph","created_at":"2026-06-02T02:05:01Z","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/2606.01936/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have opened up new possibilities for automated document formatting. However, real-world formatting often requires identifying targets based on document content. This content-aware setting remains challenging and underexplored, primarily due to the lack of dedicated evaluation datasets.To enable evaluation in realistic content-aware scenarios, we introduce DocFormBench, a benchmark that extends Text-to-Format evaluation to diverse formatting requirements, along with metrics for both accuracy and efficiency.To mitigate redundant document reading in","authors_text":"Bing Li, Can Ma, Jiapeng Liu, Jing Huang, Liang Li, Peng Fu, Shihao Rao, Tong Lin, Xiyan Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T09:02:33Z","title":"What to Format and How: A Benchmark and Workflow Approach for Document Formatting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01936","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":"sha256:33b184dfee792660b9d37fbd23bab401503057c7f730f9a3b551145314e3a78d","target":"record","created_at":"2026-06-02T02:05:01Z","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":"7b3e658bee4bdaa2d4d2f82f1671c32ad903c2386266500f872e1fb56446cd13","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T09:02:33Z","title_canon_sha256":"9f2b753866b68aab921777650bace348dc6241be18d373aa2528c437076f9f56"},"schema_version":"1.0","source":{"id":"2606.01936","kind":"arxiv","version":1}},"canonical_sha256":"870c6996f56bae7534082e522bbde91e48bbd183a11acf24848fda81ac125f86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"870c6996f56bae7534082e522bbde91e48bbd183a11acf24848fda81ac125f86","first_computed_at":"2026-06-02T02:05:01.029002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:05:01.029002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bD6UjB6fwdfzPmpLzt6MFyPcNSXsYM8bRFOhRwRRVy2o4MJHNPzLybR5AIn/eDQynR6kxqJyzyeaIXPoF14fBA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:05:01.029402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01936","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33b184dfee792660b9d37fbd23bab401503057c7f730f9a3b551145314e3a78d","sha256:e3634d980e7382f419fabde74676fc450f034e68c8790c9de5e802c1415e0247"],"state_sha256":"a0303703d6ffcc139014f6fbfdbc31fa7c482b80bfe545c55efc9c5329ca2064"}