{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MORKEZUXZDZLK2JRL25GEMX6UU","short_pith_number":"pith:MORKEZUX","schema_version":"1.0","canonical_sha256":"63a2a26697c8f2b569315eba6232fea51545fa8276c535ed9618b761802dd57d","source":{"kind":"arxiv","id":"2605.29307","version":1},"attestation_state":"computed","paper":{"title":"GrepSeek: Training Search Agents for Direct Corpus Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alireza Salemi, Atharva Nijasure, Chang Zeng, Fernando Diaz, Hamed Zamani, Jui-Hui Chung, Razieh Rahimi","submitted_at":"2026-05-28T03:37:33Z","abstract_excerpt":"Large Language Model (LLM) search agents have shown strong promise for knowledge-intensive language tasks through multiple rounds of reasoning and information retrieval. Most existing systems access information using a retriever that takes a keyword or natural language query and returns a ranked list of documents using an index of pre-computed document representations. In this work, we explore a complementary perspective in which the search agent treats the corpus itself as the search environment and finds evidence by issuing executable shell commands. We introduce GrepSeek, an optimized direc"},"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":"2605.29307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T03:37:33Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"dd767aa6ae5747de99dfbf2213eeb1b2c88b92f9202e178ebdfaca0cbee926fd","abstract_canon_sha256":"aa65187db03cd7638572a60e45c614bbb341300978f75d42ac43d3f3fd350f52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:31.753566Z","signature_b64":"ub1I1WAHL8KUE07NHv1NijAOb3y43jPie3QuXp0doM5d4HPDWtNnNREyCKQmkg5COEbiZOOkxKjvGrW03tHPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63a2a26697c8f2b569315eba6232fea51545fa8276c535ed9618b761802dd57d","last_reissued_at":"2026-05-29T01:05:31.752776Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:31.752776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GrepSeek: Training Search Agents for Direct Corpus Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alireza Salemi, Atharva Nijasure, Chang Zeng, Fernando Diaz, Hamed Zamani, Jui-Hui Chung, Razieh Rahimi","submitted_at":"2026-05-28T03:37:33Z","abstract_excerpt":"Large Language Model (LLM) search agents have shown strong promise for knowledge-intensive language tasks through multiple rounds of reasoning and information retrieval. Most existing systems access information using a retriever that takes a keyword or natural language query and returns a ranked list of documents using an index of pre-computed document representations. In this work, we explore a complementary perspective in which the search agent treats the corpus itself as the search environment and finds evidence by issuing executable shell commands. We introduce GrepSeek, an optimized direc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29307","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/2605.29307/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":"2605.29307","created_at":"2026-05-29T01:05:31.752903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29307v1","created_at":"2026-05-29T01:05:31.752903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29307","created_at":"2026-05-29T01:05:31.752903+00:00"},{"alias_kind":"pith_short_12","alias_value":"MORKEZUXZDZL","created_at":"2026-05-29T01:05:31.752903+00:00"},{"alias_kind":"pith_short_16","alias_value":"MORKEZUXZDZLK2JR","created_at":"2026-05-29T01:05:31.752903+00:00"},{"alias_kind":"pith_short_8","alias_value":"MORKEZUX","created_at":"2026-05-29T01:05:31.752903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MORKEZUXZDZLK2JRL25GEMX6UU","json":"https://pith.science/pith/MORKEZUXZDZLK2JRL25GEMX6UU.json","graph_json":"https://pith.science/api/pith-number/MORKEZUXZDZLK2JRL25GEMX6UU/graph.json","events_json":"https://pith.science/api/pith-number/MORKEZUXZDZLK2JRL25GEMX6UU/events.json","paper":"https://pith.science/paper/MORKEZUX"},"agent_actions":{"view_html":"https://pith.science/pith/MORKEZUXZDZLK2JRL25GEMX6UU","download_json":"https://pith.science/pith/MORKEZUXZDZLK2JRL25GEMX6UU.json","view_paper":"https://pith.science/paper/MORKEZUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29307&json=true","fetch_graph":"https://pith.science/api/pith-number/MORKEZUXZDZLK2JRL25GEMX6UU/graph.json","fetch_events":"https://pith.science/api/pith-number/MORKEZUXZDZLK2JRL25GEMX6UU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MORKEZUXZDZLK2JRL25GEMX6UU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MORKEZUXZDZLK2JRL25GEMX6UU/action/storage_attestation","attest_author":"https://pith.science/pith/MORKEZUXZDZLK2JRL25GEMX6UU/action/author_attestation","sign_citation":"https://pith.science/pith/MORKEZUXZDZLK2JRL25GEMX6UU/action/citation_signature","submit_replication":"https://pith.science/pith/MORKEZUXZDZLK2JRL25GEMX6UU/action/replication_record"}},"created_at":"2026-05-29T01:05:31.752903+00:00","updated_at":"2026-05-29T01:05:31.752903+00:00"}