{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KVPX66DL2NZRWNK4P5MRLMVOVN","short_pith_number":"pith:KVPX66DL","schema_version":"1.0","canonical_sha256":"555f7f786bd3731b355c7f5915b2aeab53da3116db88eec741b8cbc108fe9188","source":{"kind":"arxiv","id":"2504.09984","version":1},"attestation_state":"computed","paper":{"title":"On Precomputation and Caching in Information Retrieval Experiments with Pipeline Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Craig Macdonald, Sean MacAvaney","submitted_at":"2025-04-14T08:51:35Z","abstract_excerpt":"Modern information retrieval systems often rely on multiple components executed in a pipeline. In a research setting, this can lead to substantial redundant computations (e.g., retrieving the same query multiple times for evaluating different downstream rerankers). To overcome this, researchers take cached \"result\" files as inputs, which represent the output of another pipeline. However, these result files can be brittle and can cause a disconnect between the conceptual design of the pipeline and its logical implementation. To overcome both the redundancy problem (when executing complete pipel"},"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":"2504.09984","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-04-14T08:51:35Z","cross_cats_sorted":[],"title_canon_sha256":"3e5cfa9bdfde50d00341bee57204a62aac581eefbed12efd7c7141cfbe264801","abstract_canon_sha256":"1e98a2b8ffca69f4cf3af16ee7ced3a7e06d994995d2f1ea479285d932c590d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:45.978908Z","signature_b64":"ZAVaEmrceZmE3VNQBUdJW06wpRWwzDthu1eH+1uP+zjp7ahdkwLP8vVykEL1DjRbLMVZdzkAW3lp65/4Y2j7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"555f7f786bd3731b355c7f5915b2aeab53da3116db88eec741b8cbc108fe9188","last_reissued_at":"2026-07-05T10:48:45.978426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:45.978426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Precomputation and Caching in Information Retrieval Experiments with Pipeline Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Craig Macdonald, Sean MacAvaney","submitted_at":"2025-04-14T08:51:35Z","abstract_excerpt":"Modern information retrieval systems often rely on multiple components executed in a pipeline. In a research setting, this can lead to substantial redundant computations (e.g., retrieving the same query multiple times for evaluating different downstream rerankers). To overcome this, researchers take cached \"result\" files as inputs, which represent the output of another pipeline. However, these result files can be brittle and can cause a disconnect between the conceptual design of the pipeline and its logical implementation. To overcome both the redundancy problem (when executing complete pipel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09984","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/2504.09984/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":"2504.09984","created_at":"2026-07-05T10:48:45.978487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09984v1","created_at":"2026-07-05T10:48:45.978487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09984","created_at":"2026-07-05T10:48:45.978487+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVPX66DL2NZR","created_at":"2026-07-05T10:48:45.978487+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVPX66DL2NZRWNK4","created_at":"2026-07-05T10:48:45.978487+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVPX66DL","created_at":"2026-07-05T10:48:45.978487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10802","citing_title":"Constructing and Evaluating Declarative RAG Pipelines in PyTerrier","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVPX66DL2NZRWNK4P5MRLMVOVN","json":"https://pith.science/pith/KVPX66DL2NZRWNK4P5MRLMVOVN.json","graph_json":"https://pith.science/api/pith-number/KVPX66DL2NZRWNK4P5MRLMVOVN/graph.json","events_json":"https://pith.science/api/pith-number/KVPX66DL2NZRWNK4P5MRLMVOVN/events.json","paper":"https://pith.science/paper/KVPX66DL"},"agent_actions":{"view_html":"https://pith.science/pith/KVPX66DL2NZRWNK4P5MRLMVOVN","download_json":"https://pith.science/pith/KVPX66DL2NZRWNK4P5MRLMVOVN.json","view_paper":"https://pith.science/paper/KVPX66DL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09984&json=true","fetch_graph":"https://pith.science/api/pith-number/KVPX66DL2NZRWNK4P5MRLMVOVN/graph.json","fetch_events":"https://pith.science/api/pith-number/KVPX66DL2NZRWNK4P5MRLMVOVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVPX66DL2NZRWNK4P5MRLMVOVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVPX66DL2NZRWNK4P5MRLMVOVN/action/storage_attestation","attest_author":"https://pith.science/pith/KVPX66DL2NZRWNK4P5MRLMVOVN/action/author_attestation","sign_citation":"https://pith.science/pith/KVPX66DL2NZRWNK4P5MRLMVOVN/action/citation_signature","submit_replication":"https://pith.science/pith/KVPX66DL2NZRWNK4P5MRLMVOVN/action/replication_record"}},"created_at":"2026-07-05T10:48:45.978487+00:00","updated_at":"2026-07-05T10:48:45.978487+00:00"}