{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2NKIQI2A526VJNRCWUQHF4Y7S2","short_pith_number":"pith:2NKIQI2A","schema_version":"1.0","canonical_sha256":"d354882340eebd54b622b52072f31f96acd49746cc70cfcb0c2de5967564c457","source":{"kind":"arxiv","id":"2405.07767","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Test Collections for Retrieval Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bhaskar Mitra, Daniel Campos, Emine Yilmaz, Hossein A. Rahmani, Nick Craswell","submitted_at":"2024-05-13T14:11:09Z","abstract_excerpt":"Test collections play a vital role in evaluation of information retrieval (IR) systems. Obtaining a diverse set of user queries for test collection construction can be challenging, and acquiring relevance judgments, which indicate the appropriateness of retrieved documents to a query, is often costly and resource-intensive. Generating synthetic datasets using Large Language Models (LLMs) has recently gained significant attention in various applications. In IR, while previous work exploited the capabilities of LLMs to generate synthetic queries or documents to augment training data and improve "},"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":"2405.07767","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-13T14:11:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db18d11e6d9fd1f62053151c4515390ef9f968c379ed5d33fde2424617e19845","abstract_canon_sha256":"c00399a4c32ce1e94cf73d9e87d1d5affe4685b5459baf0a59e15872feaf6af3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:34.334691Z","signature_b64":"YjCcqZDV8fwC2PeSL6GeKe+Y1bmJTIx76rBD648goPTDWlTLzPQclz1tltuAzM/S15TumHtw00LT3Vdck+ZvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d354882340eebd54b622b52072f31f96acd49746cc70cfcb0c2de5967564c457","last_reissued_at":"2026-07-05T08:18:34.334250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:34.334250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Test Collections for Retrieval Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bhaskar Mitra, Daniel Campos, Emine Yilmaz, Hossein A. Rahmani, Nick Craswell","submitted_at":"2024-05-13T14:11:09Z","abstract_excerpt":"Test collections play a vital role in evaluation of information retrieval (IR) systems. Obtaining a diverse set of user queries for test collection construction can be challenging, and acquiring relevance judgments, which indicate the appropriateness of retrieved documents to a query, is often costly and resource-intensive. Generating synthetic datasets using Large Language Models (LLMs) has recently gained significant attention in various applications. In IR, while previous work exploited the capabilities of LLMs to generate synthetic queries or documents to augment training data and improve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07767","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/2405.07767/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":"2405.07767","created_at":"2026-07-05T08:18:34.334325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.07767v1","created_at":"2026-07-05T08:18:34.334325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07767","created_at":"2026-07-05T08:18:34.334325+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NKIQI2A526V","created_at":"2026-07-05T08:18:34.334325+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NKIQI2A526VJNRC","created_at":"2026-07-05T08:18:34.334325+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NKIQI2A","created_at":"2026-07-05T08:18:34.334325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31575","citing_title":"SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NKIQI2A526VJNRCWUQHF4Y7S2","json":"https://pith.science/pith/2NKIQI2A526VJNRCWUQHF4Y7S2.json","graph_json":"https://pith.science/api/pith-number/2NKIQI2A526VJNRCWUQHF4Y7S2/graph.json","events_json":"https://pith.science/api/pith-number/2NKIQI2A526VJNRCWUQHF4Y7S2/events.json","paper":"https://pith.science/paper/2NKIQI2A"},"agent_actions":{"view_html":"https://pith.science/pith/2NKIQI2A526VJNRCWUQHF4Y7S2","download_json":"https://pith.science/pith/2NKIQI2A526VJNRCWUQHF4Y7S2.json","view_paper":"https://pith.science/paper/2NKIQI2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.07767&json=true","fetch_graph":"https://pith.science/api/pith-number/2NKIQI2A526VJNRCWUQHF4Y7S2/graph.json","fetch_events":"https://pith.science/api/pith-number/2NKIQI2A526VJNRCWUQHF4Y7S2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NKIQI2A526VJNRCWUQHF4Y7S2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NKIQI2A526VJNRCWUQHF4Y7S2/action/storage_attestation","attest_author":"https://pith.science/pith/2NKIQI2A526VJNRCWUQHF4Y7S2/action/author_attestation","sign_citation":"https://pith.science/pith/2NKIQI2A526VJNRCWUQHF4Y7S2/action/citation_signature","submit_replication":"https://pith.science/pith/2NKIQI2A526VJNRCWUQHF4Y7S2/action/replication_record"}},"created_at":"2026-07-05T08:18:34.334325+00:00","updated_at":"2026-07-05T08:18:34.334325+00:00"}