{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XGUQHO5SOHMZXKOQ2P7K5KWZEB","short_pith_number":"pith:XGUQHO5S","schema_version":"1.0","canonical_sha256":"b9a903bbb271d99ba9d0d3feaeaad9204b239237dd92d7095fc0a4525c491dde","source":{"kind":"arxiv","id":"2607.13920","version":1},"attestation_state":"computed","paper":{"title":"DeepStress: Stress-Testing Deep Search Agents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Frederic Bechet, Geraldine Damnati, Ismael Rousseau","submitted_at":"2026-07-15T14:59:29Z","abstract_excerpt":"While search agents demonstrate impressive capabilities in multi-step question answering, their robustness to poor-quality evidence remains under-explored. This phenomenon occurs rarely in realistic benchmarks but can lead to dramatic failure in real life applications. Therefore in this study we propose DeepStress, a stress testing framework that controls the frequency of challenging evidence by replacing the retrieval module of search agents with a controlled synthetic environment. We use this framework to control three dimensions that can affect document reliability: trustworthiness, relevan"},"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":"2607.13920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-15T14:59:29Z","cross_cats_sorted":[],"title_canon_sha256":"8427468ceb787096e02f22aada3273be211a108700cc040284e5620a11c89780","abstract_canon_sha256":"f012472e6e2ed509eb57198c5383643e33b745c148ca2cdd08cc39d4ffe969fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:23:13.741572Z","signature_b64":"w8pTmjANFuyL+9PKfjYol2kHVHTiHv+urIk6O9g1mHTiQmoAwAfp5oArtWiL+WwUuDnxup1JPSUsVQPk5NIECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9a903bbb271d99ba9d0d3feaeaad9204b239237dd92d7095fc0a4525c491dde","last_reissued_at":"2026-07-16T01:23:13.740699Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:23:13.740699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepStress: Stress-Testing Deep Search Agents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Frederic Bechet, Geraldine Damnati, Ismael Rousseau","submitted_at":"2026-07-15T14:59:29Z","abstract_excerpt":"While search agents demonstrate impressive capabilities in multi-step question answering, their robustness to poor-quality evidence remains under-explored. This phenomenon occurs rarely in realistic benchmarks but can lead to dramatic failure in real life applications. Therefore in this study we propose DeepStress, a stress testing framework that controls the frequency of challenging evidence by replacing the retrieval module of search agents with a controlled synthetic environment. We use this framework to control three dimensions that can affect document reliability: trustworthiness, relevan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13920","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/2607.13920/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":"2607.13920","created_at":"2026-07-16T01:23:13.741151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13920v1","created_at":"2026-07-16T01:23:13.741151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13920","created_at":"2026-07-16T01:23:13.741151+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGUQHO5SOHMZ","created_at":"2026-07-16T01:23:13.741151+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGUQHO5SOHMZXKOQ","created_at":"2026-07-16T01:23:13.741151+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGUQHO5S","created_at":"2026-07-16T01:23:13.741151+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/XGUQHO5SOHMZXKOQ2P7K5KWZEB","json":"https://pith.science/pith/XGUQHO5SOHMZXKOQ2P7K5KWZEB.json","graph_json":"https://pith.science/api/pith-number/XGUQHO5SOHMZXKOQ2P7K5KWZEB/graph.json","events_json":"https://pith.science/api/pith-number/XGUQHO5SOHMZXKOQ2P7K5KWZEB/events.json","paper":"https://pith.science/paper/XGUQHO5S"},"agent_actions":{"view_html":"https://pith.science/pith/XGUQHO5SOHMZXKOQ2P7K5KWZEB","download_json":"https://pith.science/pith/XGUQHO5SOHMZXKOQ2P7K5KWZEB.json","view_paper":"https://pith.science/paper/XGUQHO5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13920&json=true","fetch_graph":"https://pith.science/api/pith-number/XGUQHO5SOHMZXKOQ2P7K5KWZEB/graph.json","fetch_events":"https://pith.science/api/pith-number/XGUQHO5SOHMZXKOQ2P7K5KWZEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGUQHO5SOHMZXKOQ2P7K5KWZEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGUQHO5SOHMZXKOQ2P7K5KWZEB/action/storage_attestation","attest_author":"https://pith.science/pith/XGUQHO5SOHMZXKOQ2P7K5KWZEB/action/author_attestation","sign_citation":"https://pith.science/pith/XGUQHO5SOHMZXKOQ2P7K5KWZEB/action/citation_signature","submit_replication":"https://pith.science/pith/XGUQHO5SOHMZXKOQ2P7K5KWZEB/action/replication_record"}},"created_at":"2026-07-16T01:23:13.741151+00:00","updated_at":"2026-07-16T01:23:13.741151+00:00"}