{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:36J6BT33SQX2UTF6MAFPSWYDSD","short_pith_number":"pith:36J6BT33","schema_version":"1.0","canonical_sha256":"df93e0cf7b942faa4cbe600af95b0390fb2bc845a1d864ef12a11024e089ce0e","source":{"kind":"arxiv","id":"2509.00375","version":1},"attestation_state":"computed","paper":{"title":"Open Data Synthesis For Deep Research","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongjin Qian, Kun Luo, Zheng Liu, Ziyi Xia","submitted_at":"2025-08-30T06:02:56Z","abstract_excerpt":"Large language models (LLMs) are increasingly expected to go beyond simple factual queries toward Deep Research-tasks that require decomposing questions into sub-problems, coordinating multi-step reasoning, and synthesizing evidence from diverse sources. We formalize Deep Research tasks with verifiable answers as Hierarchical Constraint Satisfaction Problems (HCSPs), which are fundamentally different from single-constraint, multi-hop, or flat CSP formulations. However, existing benchmarks (e.g., Natural Questions, HotpotQA) fail to capture this complexity, while recent synthetic datasets often"},"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":"2509.00375","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T06:02:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"162ef7a6356dc7d6015b50de7f9d7b0922d289f9fb4518620fc4437e4eb854f5","abstract_canon_sha256":"fe4d4259265d21a6e8d3ca84bf1f431bf564a62e7a5495534277c7b2c22844e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:14.973323Z","signature_b64":"R61ez2Jlc4sl0NPo0T3dmR+/RzsCa67Cw3Bi1/0wMZkxG71Wde3CZjM1CymuL0sCy0fy1s4ACn4/wevfSaIzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df93e0cf7b942faa4cbe600af95b0390fb2bc845a1d864ef12a11024e089ce0e","last_reissued_at":"2026-07-05T12:02:14.972804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:14.972804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open Data Synthesis For Deep Research","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongjin Qian, Kun Luo, Zheng Liu, Ziyi Xia","submitted_at":"2025-08-30T06:02:56Z","abstract_excerpt":"Large language models (LLMs) are increasingly expected to go beyond simple factual queries toward Deep Research-tasks that require decomposing questions into sub-problems, coordinating multi-step reasoning, and synthesizing evidence from diverse sources. We formalize Deep Research tasks with verifiable answers as Hierarchical Constraint Satisfaction Problems (HCSPs), which are fundamentally different from single-constraint, multi-hop, or flat CSP formulations. However, existing benchmarks (e.g., Natural Questions, HotpotQA) fail to capture this complexity, while recent synthetic datasets often"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00375","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/2509.00375/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":"2509.00375","created_at":"2026-07-05T12:02:14.972863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00375v1","created_at":"2026-07-05T12:02:14.972863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00375","created_at":"2026-07-05T12:02:14.972863+00:00"},{"alias_kind":"pith_short_12","alias_value":"36J6BT33SQX2","created_at":"2026-07-05T12:02:14.972863+00:00"},{"alias_kind":"pith_short_16","alias_value":"36J6BT33SQX2UTF6","created_at":"2026-07-05T12:02:14.972863+00:00"},{"alias_kind":"pith_short_8","alias_value":"36J6BT33","created_at":"2026-07-05T12:02:14.972863+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12087","citing_title":"FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13218","citing_title":"Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04949","citing_title":"Learning to Retrieve from Agent Trajectories","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07177","citing_title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07177","citing_title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14029","citing_title":"POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36J6BT33SQX2UTF6MAFPSWYDSD","json":"https://pith.science/pith/36J6BT33SQX2UTF6MAFPSWYDSD.json","graph_json":"https://pith.science/api/pith-number/36J6BT33SQX2UTF6MAFPSWYDSD/graph.json","events_json":"https://pith.science/api/pith-number/36J6BT33SQX2UTF6MAFPSWYDSD/events.json","paper":"https://pith.science/paper/36J6BT33"},"agent_actions":{"view_html":"https://pith.science/pith/36J6BT33SQX2UTF6MAFPSWYDSD","download_json":"https://pith.science/pith/36J6BT33SQX2UTF6MAFPSWYDSD.json","view_paper":"https://pith.science/paper/36J6BT33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00375&json=true","fetch_graph":"https://pith.science/api/pith-number/36J6BT33SQX2UTF6MAFPSWYDSD/graph.json","fetch_events":"https://pith.science/api/pith-number/36J6BT33SQX2UTF6MAFPSWYDSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36J6BT33SQX2UTF6MAFPSWYDSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36J6BT33SQX2UTF6MAFPSWYDSD/action/storage_attestation","attest_author":"https://pith.science/pith/36J6BT33SQX2UTF6MAFPSWYDSD/action/author_attestation","sign_citation":"https://pith.science/pith/36J6BT33SQX2UTF6MAFPSWYDSD/action/citation_signature","submit_replication":"https://pith.science/pith/36J6BT33SQX2UTF6MAFPSWYDSD/action/replication_record"}},"created_at":"2026-07-05T12:02:14.972863+00:00","updated_at":"2026-07-05T12:02:14.972863+00:00"}