{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7UBGFIG3KGEXWL3JKVSDJLW5GO","short_pith_number":"pith:7UBGFIG3","schema_version":"1.0","canonical_sha256":"fd0262a0db51897b2f69556434aedd33a158f9599b6823cca606cc77f8727fd3","source":{"kind":"arxiv","id":"2503.20201","version":1},"attestation_state":"computed","paper":{"title":"Open Deep Search: Democratizing Search with Open-source Reasoning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Arda Kaz, Chiara von Gerlach, Creston Brooks, Edoardo Contente, Himanshu Tyagi, Lucas Irwin, Pramod Viswanath, Purva Chiniya, Salaheddin Alzubi, Sewoong Oh, Windsor Nguyen, Yihan Jiang","submitted_at":"2025-03-26T03:51:32Z","abstract_excerpt":"We introduce Open Deep Search (ODS) to close the increasing gap between the proprietary search AI solutions, such as Perplexity's Sonar Reasoning Pro and OpenAI's GPT-4o Search Preview, and their open-source counterparts. The main innovation introduced in ODS is to augment the reasoning capabilities of the latest open-source LLMs with reasoning agents that can judiciously use web search tools to answer queries. Concretely, ODS consists of two components that work with a base LLM chosen by the user: Open Search Tool and Open Reasoning Agent. Open Reasoning Agent interprets the given task and co"},"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":"2503.20201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-26T03:51:32Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"aa28b03bd36866c5af5d978652d905452178e3de847e0e93df7a7ae488d6e800","abstract_canon_sha256":"5f8f7dc7621d19a5975477010c5687cf576ecb840b3da2b5dec9084cca645220"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:34.620156Z","signature_b64":"iQkM6Gngl+7A8Fe8seTcxY1TkHs+54IwgeI7FiJnNJRcoeIRME9PcxRNgJX6d/eRsaB3Cr5l2Vj5kr7mOPFwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd0262a0db51897b2f69556434aedd33a158f9599b6823cca606cc77f8727fd3","last_reissued_at":"2026-07-05T10:39:34.619638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:34.619638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open Deep Search: Democratizing Search with Open-source Reasoning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Arda Kaz, Chiara von Gerlach, Creston Brooks, Edoardo Contente, Himanshu Tyagi, Lucas Irwin, Pramod Viswanath, Purva Chiniya, Salaheddin Alzubi, Sewoong Oh, Windsor Nguyen, Yihan Jiang","submitted_at":"2025-03-26T03:51:32Z","abstract_excerpt":"We introduce Open Deep Search (ODS) to close the increasing gap between the proprietary search AI solutions, such as Perplexity's Sonar Reasoning Pro and OpenAI's GPT-4o Search Preview, and their open-source counterparts. The main innovation introduced in ODS is to augment the reasoning capabilities of the latest open-source LLMs with reasoning agents that can judiciously use web search tools to answer queries. Concretely, ODS consists of two components that work with a base LLM chosen by the user: Open Search Tool and Open Reasoning Agent. Open Reasoning Agent interprets the given task and co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20201","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/2503.20201/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":"2503.20201","created_at":"2026-07-05T10:39:34.619700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20201v1","created_at":"2026-07-05T10:39:34.619700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20201","created_at":"2026-07-05T10:39:34.619700+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UBGFIG3KGEX","created_at":"2026-07-05T10:39:34.619700+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UBGFIG3KGEXWL3J","created_at":"2026-07-05T10:39:34.619700+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UBGFIG3","created_at":"2026-07-05T10:39:34.619700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20670","citing_title":"MMSearch-R1: Incentivizing LMMs to Search","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24978","citing_title":"Don\\'t Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UBGFIG3KGEXWL3JKVSDJLW5GO","json":"https://pith.science/pith/7UBGFIG3KGEXWL3JKVSDJLW5GO.json","graph_json":"https://pith.science/api/pith-number/7UBGFIG3KGEXWL3JKVSDJLW5GO/graph.json","events_json":"https://pith.science/api/pith-number/7UBGFIG3KGEXWL3JKVSDJLW5GO/events.json","paper":"https://pith.science/paper/7UBGFIG3"},"agent_actions":{"view_html":"https://pith.science/pith/7UBGFIG3KGEXWL3JKVSDJLW5GO","download_json":"https://pith.science/pith/7UBGFIG3KGEXWL3JKVSDJLW5GO.json","view_paper":"https://pith.science/paper/7UBGFIG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20201&json=true","fetch_graph":"https://pith.science/api/pith-number/7UBGFIG3KGEXWL3JKVSDJLW5GO/graph.json","fetch_events":"https://pith.science/api/pith-number/7UBGFIG3KGEXWL3JKVSDJLW5GO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UBGFIG3KGEXWL3JKVSDJLW5GO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UBGFIG3KGEXWL3JKVSDJLW5GO/action/storage_attestation","attest_author":"https://pith.science/pith/7UBGFIG3KGEXWL3JKVSDJLW5GO/action/author_attestation","sign_citation":"https://pith.science/pith/7UBGFIG3KGEXWL3JKVSDJLW5GO/action/citation_signature","submit_replication":"https://pith.science/pith/7UBGFIG3KGEXWL3JKVSDJLW5GO/action/replication_record"}},"created_at":"2026-07-05T10:39:34.619700+00:00","updated_at":"2026-07-05T10:39:34.619700+00:00"}