{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RVL3OSTAMO5G5Z3MJTSNS3UDPJ","short_pith_number":"pith:RVL3OSTA","schema_version":"1.0","canonical_sha256":"8d57b74a6063ba6ee76c4ce4d96e837a6b9e72bbf0db1ada5a92ddf84c5f9aae","source":{"kind":"arxiv","id":"2508.11133","version":2},"attestation_state":"computed","paper":{"title":"MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Dan Roth, Harsh Trivedi, Mor Geva, Reut Tsarfaty, Tomer Wolfson, Tushar Khot, Yoav Goldberg","submitted_at":"2025-08-15T00:58:10Z","abstract_excerpt":"Automated agents, powered by Large language models (LLMs), are emerging as the go-to tool for querying information. However, evaluation benchmarks for LLM agents rarely feature natural questions that are both information-seeking and genuinely time-consuming for humans. To address this gap we introduce MoNaCo, a benchmark of 1,315 natural and time-consuming questions that require dozens, and at times hundreds, of intermediate steps to solve -- far more than any existing QA benchmark. To build MoNaCo, we developed a decomposed annotation pipeline to elicit and manually answer real-world time-con"},"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":"2508.11133","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T00:58:10Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"585bd99f0b945af1348d4df0a7e3673a39e388844d77b13b316d8f17a91facdd","abstract_canon_sha256":"0cafd2c79559a89480ad6ea2fe47f764015c653be83b152c16acb4a165cfe0f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:17.100262Z","signature_b64":"xSqqh83C3AOTYlv5xNrTbK8WQi6DvUOTb6EgIz5SdlLaFTvwHbNdKEtBWGstZIVeE7+0rAqQMFtVsHesiDdaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d57b74a6063ba6ee76c4ce4d96e837a6b9e72bbf0db1ada5a92ddf84c5f9aae","last_reissued_at":"2026-07-05T12:04:17.099720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:17.099720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Dan Roth, Harsh Trivedi, Mor Geva, Reut Tsarfaty, Tomer Wolfson, Tushar Khot, Yoav Goldberg","submitted_at":"2025-08-15T00:58:10Z","abstract_excerpt":"Automated agents, powered by Large language models (LLMs), are emerging as the go-to tool for querying information. However, evaluation benchmarks for LLM agents rarely feature natural questions that are both information-seeking and genuinely time-consuming for humans. To address this gap we introduce MoNaCo, a benchmark of 1,315 natural and time-consuming questions that require dozens, and at times hundreds, of intermediate steps to solve -- far more than any existing QA benchmark. To build MoNaCo, we developed a decomposed annotation pipeline to elicit and manually answer real-world time-con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11133","kind":"arxiv","version":2},"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/2508.11133/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":"2508.11133","created_at":"2026-07-05T12:04:17.099783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11133v2","created_at":"2026-07-05T12:04:17.099783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11133","created_at":"2026-07-05T12:04:17.099783+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVL3OSTAMO5G","created_at":"2026-07-05T12:04:17.099783+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVL3OSTAMO5G5Z3M","created_at":"2026-07-05T12:04:17.099783+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVL3OSTA","created_at":"2026-07-05T12:04:17.099783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11926","citing_title":"Toward Generalist Autonomous Research via Hypothesis-Tree Refinement","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVL3OSTAMO5G5Z3MJTSNS3UDPJ","json":"https://pith.science/pith/RVL3OSTAMO5G5Z3MJTSNS3UDPJ.json","graph_json":"https://pith.science/api/pith-number/RVL3OSTAMO5G5Z3MJTSNS3UDPJ/graph.json","events_json":"https://pith.science/api/pith-number/RVL3OSTAMO5G5Z3MJTSNS3UDPJ/events.json","paper":"https://pith.science/paper/RVL3OSTA"},"agent_actions":{"view_html":"https://pith.science/pith/RVL3OSTAMO5G5Z3MJTSNS3UDPJ","download_json":"https://pith.science/pith/RVL3OSTAMO5G5Z3MJTSNS3UDPJ.json","view_paper":"https://pith.science/paper/RVL3OSTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11133&json=true","fetch_graph":"https://pith.science/api/pith-number/RVL3OSTAMO5G5Z3MJTSNS3UDPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/RVL3OSTAMO5G5Z3MJTSNS3UDPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVL3OSTAMO5G5Z3MJTSNS3UDPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVL3OSTAMO5G5Z3MJTSNS3UDPJ/action/storage_attestation","attest_author":"https://pith.science/pith/RVL3OSTAMO5G5Z3MJTSNS3UDPJ/action/author_attestation","sign_citation":"https://pith.science/pith/RVL3OSTAMO5G5Z3MJTSNS3UDPJ/action/citation_signature","submit_replication":"https://pith.science/pith/RVL3OSTAMO5G5Z3MJTSNS3UDPJ/action/replication_record"}},"created_at":"2026-07-05T12:04:17.099783+00:00","updated_at":"2026-07-05T12:04:17.099783+00:00"}