{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q4GGTFXVNOXHKNAIFZJCXPPJDZ","short_pith_number":"pith:Q4GGTFXV","schema_version":"1.0","canonical_sha256":"870c6996f56bae7534082e522bbde91e48bbd183a11acf24848fda81ac125f86","source":{"kind":"arxiv","id":"2606.01936","version":1},"attestation_state":"computed","paper":{"title":"What to Format and How: A Benchmark and Workflow Approach for Document Formatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Li, Can Ma, Jiapeng Liu, Jing Huang, Liang Li, Peng Fu, Shihao Rao, Tong Lin, Xiyan Gao","submitted_at":"2026-06-01T09:02:33Z","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"},"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":"2606.01936","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T09:02:33Z","cross_cats_sorted":[],"title_canon_sha256":"9f2b753866b68aab921777650bace348dc6241be18d373aa2528c437076f9f56","abstract_canon_sha256":"7b3e658bee4bdaa2d4d2f82f1671c32ad903c2386266500f872e1fb56446cd13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:01.029402Z","signature_b64":"bD6UjB6fwdfzPmpLzt6MFyPcNSXsYM8bRFOhRwRRVy2o4MJHNPzLybR5AIn/eDQynR6kxqJyzyeaIXPoF14fBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"870c6996f56bae7534082e522bbde91e48bbd183a11acf24848fda81ac125f86","last_reissued_at":"2026-06-02T02:05:01.029002Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:01.029002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What to Format and How: A Benchmark and Workflow Approach for Document Formatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Li, Can Ma, Jiapeng Liu, Jing Huang, Liang Li, Peng Fu, Shihao Rao, Tong Lin, Xiyan Gao","submitted_at":"2026-06-01T09:02:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01936","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/2606.01936/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":"2606.01936","created_at":"2026-06-02T02:05:01.029057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01936v1","created_at":"2026-06-02T02:05:01.029057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01936","created_at":"2026-06-02T02:05:01.029057+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4GGTFXVNOXH","created_at":"2026-06-02T02:05:01.029057+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4GGTFXVNOXHKNAI","created_at":"2026-06-02T02:05:01.029057+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4GGTFXV","created_at":"2026-06-02T02:05:01.029057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q4GGTFXVNOXHKNAIFZJCXPPJDZ","json":"https://pith.science/pith/Q4GGTFXVNOXHKNAIFZJCXPPJDZ.json","graph_json":"https://pith.science/api/pith-number/Q4GGTFXVNOXHKNAIFZJCXPPJDZ/graph.json","events_json":"https://pith.science/api/pith-number/Q4GGTFXVNOXHKNAIFZJCXPPJDZ/events.json","paper":"https://pith.science/paper/Q4GGTFXV"},"agent_actions":{"view_html":"https://pith.science/pith/Q4GGTFXVNOXHKNAIFZJCXPPJDZ","download_json":"https://pith.science/pith/Q4GGTFXVNOXHKNAIFZJCXPPJDZ.json","view_paper":"https://pith.science/paper/Q4GGTFXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01936&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4GGTFXVNOXHKNAIFZJCXPPJDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4GGTFXVNOXHKNAIFZJCXPPJDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4GGTFXVNOXHKNAIFZJCXPPJDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4GGTFXVNOXHKNAIFZJCXPPJDZ/action/storage_attestation","attest_author":"https://pith.science/pith/Q4GGTFXVNOXHKNAIFZJCXPPJDZ/action/author_attestation","sign_citation":"https://pith.science/pith/Q4GGTFXVNOXHKNAIFZJCXPPJDZ/action/citation_signature","submit_replication":"https://pith.science/pith/Q4GGTFXVNOXHKNAIFZJCXPPJDZ/action/replication_record"}},"created_at":"2026-06-02T02:05:01.029057+00:00","updated_at":"2026-06-02T02:05:01.029057+00:00"}