{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LON2GVRIXAQ44S7QH3TN32ER2I","short_pith_number":"pith:LON2GVRI","schema_version":"1.0","canonical_sha256":"5b9ba35628b821ce4bf03ee6dde891d22b0b81080329ff82daa2b56a499b07d4","source":{"kind":"arxiv","id":"2506.14927","version":1},"attestation_state":"computed","paper":{"title":"MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Payani, Joseph J. Peper, Lu Wang, Wenzhao Qiu","submitted_at":"2025-06-17T19:14:30Z","abstract_excerpt":"Natural language processing evaluation has made significant progress, largely driven by the proliferation of powerful large language mod-els (LLMs). New evaluation benchmarks are of increasing priority as the reasoning capabilities of LLMs are expanding at a rapid pace. In particular, while multi-document (MD) reasoning is an area of extreme relevance given LLM capabilities in handling longer-context inputs, few benchmarks exist to rigorously examine model behavior in this setting. Moreover, the multi-document setting is historically challenging for benchmark creation due to the expensive cost"},"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":"2506.14927","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T19:14:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8325cc707cfb10761da8386cdb37fc4c64c46c620ceab7ca37a7be3489a03dc","abstract_canon_sha256":"540727a0b97031d73821c64815921d3ae1d7f29d1843354359123f584b7d08bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:34.208248Z","signature_b64":"rHY5yLhpap+Xi2O9c8s46rCyIhKEbjnFBRJAIuphb5Z8xpwFBvEbjx3PwQK5KIU/Yl6rXUk80gwB+x23iDPEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b9ba35628b821ce4bf03ee6dde891d22b0b81080329ff82daa2b56a499b07d4","last_reissued_at":"2026-07-05T11:23:34.207759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:34.207759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Payani, Joseph J. Peper, Lu Wang, Wenzhao Qiu","submitted_at":"2025-06-17T19:14:30Z","abstract_excerpt":"Natural language processing evaluation has made significant progress, largely driven by the proliferation of powerful large language mod-els (LLMs). New evaluation benchmarks are of increasing priority as the reasoning capabilities of LLMs are expanding at a rapid pace. In particular, while multi-document (MD) reasoning is an area of extreme relevance given LLM capabilities in handling longer-context inputs, few benchmarks exist to rigorously examine model behavior in this setting. Moreover, the multi-document setting is historically challenging for benchmark creation due to the expensive cost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14927","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/2506.14927/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":"2506.14927","created_at":"2026-07-05T11:23:34.207812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14927v1","created_at":"2026-07-05T11:23:34.207812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14927","created_at":"2026-07-05T11:23:34.207812+00:00"},{"alias_kind":"pith_short_12","alias_value":"LON2GVRIXAQ4","created_at":"2026-07-05T11:23:34.207812+00:00"},{"alias_kind":"pith_short_16","alias_value":"LON2GVRIXAQ44S7Q","created_at":"2026-07-05T11:23:34.207812+00:00"},{"alias_kind":"pith_short_8","alias_value":"LON2GVRI","created_at":"2026-07-05T11:23:34.207812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29630","citing_title":"SFBench: The SciFy Scientific Feasibility Benchmark","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LON2GVRIXAQ44S7QH3TN32ER2I","json":"https://pith.science/pith/LON2GVRIXAQ44S7QH3TN32ER2I.json","graph_json":"https://pith.science/api/pith-number/LON2GVRIXAQ44S7QH3TN32ER2I/graph.json","events_json":"https://pith.science/api/pith-number/LON2GVRIXAQ44S7QH3TN32ER2I/events.json","paper":"https://pith.science/paper/LON2GVRI"},"agent_actions":{"view_html":"https://pith.science/pith/LON2GVRIXAQ44S7QH3TN32ER2I","download_json":"https://pith.science/pith/LON2GVRIXAQ44S7QH3TN32ER2I.json","view_paper":"https://pith.science/paper/LON2GVRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14927&json=true","fetch_graph":"https://pith.science/api/pith-number/LON2GVRIXAQ44S7QH3TN32ER2I/graph.json","fetch_events":"https://pith.science/api/pith-number/LON2GVRIXAQ44S7QH3TN32ER2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LON2GVRIXAQ44S7QH3TN32ER2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LON2GVRIXAQ44S7QH3TN32ER2I/action/storage_attestation","attest_author":"https://pith.science/pith/LON2GVRIXAQ44S7QH3TN32ER2I/action/author_attestation","sign_citation":"https://pith.science/pith/LON2GVRIXAQ44S7QH3TN32ER2I/action/citation_signature","submit_replication":"https://pith.science/pith/LON2GVRIXAQ44S7QH3TN32ER2I/action/replication_record"}},"created_at":"2026-07-05T11:23:34.207812+00:00","updated_at":"2026-07-05T11:23:34.207812+00:00"}