{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I4PXRFCR7AMIMDSUMXDBJ554FY","short_pith_number":"pith:I4PXRFCR","schema_version":"1.0","canonical_sha256":"471f789451f818860e5465c614f7bc2e236161457f3343cfbab29edc26bbc2e9","source":{"kind":"arxiv","id":"2607.15253","version":1},"attestation_state":"computed","paper":{"title":"Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Debayan Mukhopadhyay, Shubham Chatterjee, Utshab Kumar Ghosh","submitted_at":"2026-07-16T17:48:29Z","abstract_excerpt":"Retrieval systems are trained and evaluated on a static idea of usefulness: hand a document and a question to a reader model, see whether the answer improves, and score the document accordingly. The idea holds up when a document is read on its own. It breaks when a language model works as a search agent, issuing several queries and reasoning across turns, because a document can matter for what it lets the agent do next rather than for what it says about the current question.\n  We measure that gap rather than argue it. Using a ReAct style agent over HotpotQA, we replay 1000 development question"},"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":"2607.15253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-16T17:48:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a82ffca1bb4e4a1299ae2cdcd4f4eaac92cd72e8d3aa82512a373cd3a6f09a6c","abstract_canon_sha256":"27304ee8c4ca12edd76d2680aa3a0cf05cb71e9fcdd4147f3ce7f9f6b69dd00e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:22:16.851167Z","signature_b64":"/S8DViy2u6SQmLrUAwGcpy1m+6AwaRQHwfPSFe/RI9yLvMwBjaYbMNjAcHqBrOrDokr2R7MEZr+85WMIQdo9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"471f789451f818860e5465c614f7bc2e236161457f3343cfbab29edc26bbc2e9","last_reissued_at":"2026-07-17T01:22:16.850346Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:22:16.850346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Debayan Mukhopadhyay, Shubham Chatterjee, Utshab Kumar Ghosh","submitted_at":"2026-07-16T17:48:29Z","abstract_excerpt":"Retrieval systems are trained and evaluated on a static idea of usefulness: hand a document and a question to a reader model, see whether the answer improves, and score the document accordingly. The idea holds up when a document is read on its own. It breaks when a language model works as a search agent, issuing several queries and reasoning across turns, because a document can matter for what it lets the agent do next rather than for what it says about the current question.\n  We measure that gap rather than argue it. Using a ReAct style agent over HotpotQA, we replay 1000 development question"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15253","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/2607.15253/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":"2607.15253","created_at":"2026-07-17T01:22:16.850767+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.15253v1","created_at":"2026-07-17T01:22:16.850767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15253","created_at":"2026-07-17T01:22:16.850767+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4PXRFCR7AMI","created_at":"2026-07-17T01:22:16.850767+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4PXRFCR7AMIMDSU","created_at":"2026-07-17T01:22:16.850767+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4PXRFCR","created_at":"2026-07-17T01:22:16.850767+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08944","citing_title":"What Would Fix This RAG Failure? Auditing Counterfactual Response with Paired Evidence Interventions","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4PXRFCR7AMIMDSUMXDBJ554FY","json":"https://pith.science/pith/I4PXRFCR7AMIMDSUMXDBJ554FY.json","graph_json":"https://pith.science/api/pith-number/I4PXRFCR7AMIMDSUMXDBJ554FY/graph.json","events_json":"https://pith.science/api/pith-number/I4PXRFCR7AMIMDSUMXDBJ554FY/events.json","paper":"https://pith.science/paper/I4PXRFCR"},"agent_actions":{"view_html":"https://pith.science/pith/I4PXRFCR7AMIMDSUMXDBJ554FY","download_json":"https://pith.science/pith/I4PXRFCR7AMIMDSUMXDBJ554FY.json","view_paper":"https://pith.science/paper/I4PXRFCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.15253&json=true","fetch_graph":"https://pith.science/api/pith-number/I4PXRFCR7AMIMDSUMXDBJ554FY/graph.json","fetch_events":"https://pith.science/api/pith-number/I4PXRFCR7AMIMDSUMXDBJ554FY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4PXRFCR7AMIMDSUMXDBJ554FY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4PXRFCR7AMIMDSUMXDBJ554FY/action/storage_attestation","attest_author":"https://pith.science/pith/I4PXRFCR7AMIMDSUMXDBJ554FY/action/author_attestation","sign_citation":"https://pith.science/pith/I4PXRFCR7AMIMDSUMXDBJ554FY/action/citation_signature","submit_replication":"https://pith.science/pith/I4PXRFCR7AMIMDSUMXDBJ554FY/action/replication_record"}},"created_at":"2026-07-17T01:22:16.850767+00:00","updated_at":"2026-07-17T01:22:16.850767+00:00"}