{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V4V44SXSEVTTRRBSC52FP5RMHZ","short_pith_number":"pith:V4V44SXS","schema_version":"1.0","canonical_sha256":"af2bce4af2256738c432177457f62c3e4ea3c7021ce2f9f61004d68fe4dae527","source":{"kind":"arxiv","id":"2504.13128","version":2},"attestation_state":"computed","paper":{"title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Andrew Drozdov, Jimmy Lin, Michael Carbin, Nandan Thakur, Omar Khattab, Sam Havens","submitted_at":"2025-04-17T17:44:06Z","abstract_excerpt":"We introduce FreshStack, a holistic framework for automatically building information retrieval (IR) evaluation benchmarks by incorporating challenging questions and answers. FreshStack conducts the following steps: (1) automatic corpus collection from code and technical documentation, (2) nugget generation from community-asked questions and answers, and (3) nugget-level support, retrieving documents using a fusion of retrieval techniques and hybrid architectures. We use FreshStack to build five datasets on fast-growing, recent, and niche topics to ensure the tasks are sufficiently challenging."},"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":"2504.13128","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-17T17:44:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"66303809cbf126e2833fdaef32d4296ee4ad4a7e7292a3b79ddbc8b9a12ec7b1","abstract_canon_sha256":"d3edfb31dff7c2d3025b09fbd9e8227bdc58e6ad9fc76aac17a3b516dcd3f7ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:52.823143Z","signature_b64":"1rjICWBtp1zpL/i4JQ4P8Imr9b+S16I1bjDvZ+F25r2rruJljekUb+PiWR/ZiBElRVK6AAHA9rvCioTCOgyOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af2bce4af2256738c432177457f62c3e4ea3c7021ce2f9f61004d68fe4dae527","last_reissued_at":"2026-07-05T11:20:52.822647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:52.822647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Andrew Drozdov, Jimmy Lin, Michael Carbin, Nandan Thakur, Omar Khattab, Sam Havens","submitted_at":"2025-04-17T17:44:06Z","abstract_excerpt":"We introduce FreshStack, a holistic framework for automatically building information retrieval (IR) evaluation benchmarks by incorporating challenging questions and answers. FreshStack conducts the following steps: (1) automatic corpus collection from code and technical documentation, (2) nugget generation from community-asked questions and answers, and (3) nugget-level support, retrieving documents using a fusion of retrieval techniques and hybrid architectures. We use FreshStack to build five datasets on fast-growing, recent, and niche topics to ensure the tasks are sufficiently challenging."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13128","kind":"arxiv","version":2},"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/2504.13128/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":"2504.13128","created_at":"2026-07-05T11:20:52.822706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13128v2","created_at":"2026-07-05T11:20:52.822706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13128","created_at":"2026-07-05T11:20:52.822706+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4V44SXSEVTT","created_at":"2026-07-05T11:20:52.822706+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4V44SXSEVTTRRBS","created_at":"2026-07-05T11:20:52.822706+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4V44SXS","created_at":"2026-07-05T11:20:52.822706+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/V4V44SXSEVTTRRBSC52FP5RMHZ","json":"https://pith.science/pith/V4V44SXSEVTTRRBSC52FP5RMHZ.json","graph_json":"https://pith.science/api/pith-number/V4V44SXSEVTTRRBSC52FP5RMHZ/graph.json","events_json":"https://pith.science/api/pith-number/V4V44SXSEVTTRRBSC52FP5RMHZ/events.json","paper":"https://pith.science/paper/V4V44SXS"},"agent_actions":{"view_html":"https://pith.science/pith/V4V44SXSEVTTRRBSC52FP5RMHZ","download_json":"https://pith.science/pith/V4V44SXSEVTTRRBSC52FP5RMHZ.json","view_paper":"https://pith.science/paper/V4V44SXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13128&json=true","fetch_graph":"https://pith.science/api/pith-number/V4V44SXSEVTTRRBSC52FP5RMHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/V4V44SXSEVTTRRBSC52FP5RMHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4V44SXSEVTTRRBSC52FP5RMHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4V44SXSEVTTRRBSC52FP5RMHZ/action/storage_attestation","attest_author":"https://pith.science/pith/V4V44SXSEVTTRRBSC52FP5RMHZ/action/author_attestation","sign_citation":"https://pith.science/pith/V4V44SXSEVTTRRBSC52FP5RMHZ/action/citation_signature","submit_replication":"https://pith.science/pith/V4V44SXSEVTTRRBSC52FP5RMHZ/action/replication_record"}},"created_at":"2026-07-05T11:20:52.822706+00:00","updated_at":"2026-07-05T11:20:52.822706+00:00"}