{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KPWYTBV3AGMDUIUKYXPFTHVUGG","short_pith_number":"pith:KPWYTBV3","schema_version":"1.0","canonical_sha256":"53ed8986bb01983a228ac5de599eb43189f195d00263017d19deee54c9cead7c","source":{"kind":"arxiv","id":"2508.04183","version":1},"attestation_state":"computed","paper":{"title":"Characterizing Deep Research: A Benchmark and Formal Definition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Halfaker, Abhinav Java, Amit Deshpande, Amit Sharma, Ankur Gupta, Ashmit Khandelwal, Nagarajan Natarajan, Navin Goyal, Sukruta Midigeshi","submitted_at":"2025-08-06T08:09:28Z","abstract_excerpt":"Information tasks such as writing surveys or analytical reports require complex search and reasoning, and have recently been grouped under the umbrella of \\textit{deep research} -- a term also adopted by recent models targeting these capabilities. Despite growing interest, the scope of the deep research task remains underdefined and its distinction from other reasoning-intensive problems is poorly understood. In this paper, we propose a formal characterization of the deep research (DR) task and introduce a benchmark to evaluate the performance of DR systems. We argue that the core defining fea"},"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":"2508.04183","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-06T08:09:28Z","cross_cats_sorted":[],"title_canon_sha256":"5a23f17d80a63eb6c7157d53201f8f04480b3e24b813240c04d1eaee7cbbc482","abstract_canon_sha256":"cc3c147c358f8af35610a10ddcc0b8f07fded718b506ac78592fd5ee8b91aeb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:22.265881Z","signature_b64":"+c/fZWevj08SI7n9pm/qs1ck5zTHBOdnGUKtb4StHRGwvJKqR6CFasX6I27j7Wlw36SdbzlLkD24XtQO889bCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53ed8986bb01983a228ac5de599eb43189f195d00263017d19deee54c9cead7c","last_reissued_at":"2026-07-05T11:49:22.265405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:22.265405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Characterizing Deep Research: A Benchmark and Formal Definition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Halfaker, Abhinav Java, Amit Deshpande, Amit Sharma, Ankur Gupta, Ashmit Khandelwal, Nagarajan Natarajan, Navin Goyal, Sukruta Midigeshi","submitted_at":"2025-08-06T08:09:28Z","abstract_excerpt":"Information tasks such as writing surveys or analytical reports require complex search and reasoning, and have recently been grouped under the umbrella of \\textit{deep research} -- a term also adopted by recent models targeting these capabilities. Despite growing interest, the scope of the deep research task remains underdefined and its distinction from other reasoning-intensive problems is poorly understood. In this paper, we propose a formal characterization of the deep research (DR) task and introduce a benchmark to evaluate the performance of DR systems. We argue that the core defining fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04183","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/2508.04183/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":"2508.04183","created_at":"2026-07-05T11:49:22.265462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04183v1","created_at":"2026-07-05T11:49:22.265462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04183","created_at":"2026-07-05T11:49:22.265462+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPWYTBV3AGMD","created_at":"2026-07-05T11:49:22.265462+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPWYTBV3AGMDUIUK","created_at":"2026-07-05T11:49:22.265462+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPWYTBV3","created_at":"2026-07-05T11:49:22.265462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10460","citing_title":"LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake","ref_index":5,"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":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPWYTBV3AGMDUIUKYXPFTHVUGG","json":"https://pith.science/pith/KPWYTBV3AGMDUIUKYXPFTHVUGG.json","graph_json":"https://pith.science/api/pith-number/KPWYTBV3AGMDUIUKYXPFTHVUGG/graph.json","events_json":"https://pith.science/api/pith-number/KPWYTBV3AGMDUIUKYXPFTHVUGG/events.json","paper":"https://pith.science/paper/KPWYTBV3"},"agent_actions":{"view_html":"https://pith.science/pith/KPWYTBV3AGMDUIUKYXPFTHVUGG","download_json":"https://pith.science/pith/KPWYTBV3AGMDUIUKYXPFTHVUGG.json","view_paper":"https://pith.science/paper/KPWYTBV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04183&json=true","fetch_graph":"https://pith.science/api/pith-number/KPWYTBV3AGMDUIUKYXPFTHVUGG/graph.json","fetch_events":"https://pith.science/api/pith-number/KPWYTBV3AGMDUIUKYXPFTHVUGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPWYTBV3AGMDUIUKYXPFTHVUGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPWYTBV3AGMDUIUKYXPFTHVUGG/action/storage_attestation","attest_author":"https://pith.science/pith/KPWYTBV3AGMDUIUKYXPFTHVUGG/action/author_attestation","sign_citation":"https://pith.science/pith/KPWYTBV3AGMDUIUKYXPFTHVUGG/action/citation_signature","submit_replication":"https://pith.science/pith/KPWYTBV3AGMDUIUKYXPFTHVUGG/action/replication_record"}},"created_at":"2026-07-05T11:49:22.265462+00:00","updated_at":"2026-07-05T11:49:22.265462+00:00"}