{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GXNZ2I7XRSULLRRP427YBTQZK3","short_pith_number":"pith:GXNZ2I7X","schema_version":"1.0","canonical_sha256":"35db9d23f78ca8b5c62fe6bf80ce1956e59f5e1adf4d5793a7994436ae117c34","source":{"kind":"arxiv","id":"2605.31575","version":1},"attestation_state":"computed","paper":{"title":"SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Eric Liang","submitted_at":"2026-05-29T17:44:15Z","abstract_excerpt":"Scalable information retrieval testing needs corpora that are large enough to stress index construction, ranking latency, query routing, and evaluation tooling, yet human-judged test collections remain expensive and may be unavailable when documents are private or still under design. This paper introduces SPECTRA, a reproducible framework for generating synthetic text corpora and retrieval test collections through a separation of latent topical structure, surface text realization, metadata controls, query intent generation, and deterministic relevance oracles. The framework is intended as a di"},"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":"2605.31575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-29T17:44:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5d62d0c30ce676ea0205c1d79835f43762f3f56d35ca12a90045ad2a426ca8fd","abstract_canon_sha256":"f396c985d1244a57722d816e290e2415fdc819f0a1d12a9ebbf9e951bcd3aa5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:04:13.970235Z","signature_b64":"ppsEHrURQLABL5HLFSJbSJ8TusDt/iMt821kEcuDaVuXaTmEK0IkFqayQofOjbWEBuVs+N4FEwPOk9USIV/xDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35db9d23f78ca8b5c62fe6bf80ce1956e59f5e1adf4d5793a7994436ae117c34","last_reissued_at":"2026-06-01T02:04:13.969246Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:04:13.969246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Eric Liang","submitted_at":"2026-05-29T17:44:15Z","abstract_excerpt":"Scalable information retrieval testing needs corpora that are large enough to stress index construction, ranking latency, query routing, and evaluation tooling, yet human-judged test collections remain expensive and may be unavailable when documents are private or still under design. This paper introduces SPECTRA, a reproducible framework for generating synthetic text corpora and retrieval test collections through a separation of latent topical structure, surface text realization, metadata controls, query intent generation, and deterministic relevance oracles. The framework is intended as a di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31575","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/2605.31575/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":"2605.31575","created_at":"2026-06-01T02:04:13.969436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31575v1","created_at":"2026-06-01T02:04:13.969436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31575","created_at":"2026-06-01T02:04:13.969436+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXNZ2I7XRSUL","created_at":"2026-06-01T02:04:13.969436+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXNZ2I7XRSULLRRP","created_at":"2026-06-01T02:04:13.969436+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXNZ2I7X","created_at":"2026-06-01T02:04:13.969436+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/GXNZ2I7XRSULLRRP427YBTQZK3","json":"https://pith.science/pith/GXNZ2I7XRSULLRRP427YBTQZK3.json","graph_json":"https://pith.science/api/pith-number/GXNZ2I7XRSULLRRP427YBTQZK3/graph.json","events_json":"https://pith.science/api/pith-number/GXNZ2I7XRSULLRRP427YBTQZK3/events.json","paper":"https://pith.science/paper/GXNZ2I7X"},"agent_actions":{"view_html":"https://pith.science/pith/GXNZ2I7XRSULLRRP427YBTQZK3","download_json":"https://pith.science/pith/GXNZ2I7XRSULLRRP427YBTQZK3.json","view_paper":"https://pith.science/paper/GXNZ2I7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31575&json=true","fetch_graph":"https://pith.science/api/pith-number/GXNZ2I7XRSULLRRP427YBTQZK3/graph.json","fetch_events":"https://pith.science/api/pith-number/GXNZ2I7XRSULLRRP427YBTQZK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXNZ2I7XRSULLRRP427YBTQZK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXNZ2I7XRSULLRRP427YBTQZK3/action/storage_attestation","attest_author":"https://pith.science/pith/GXNZ2I7XRSULLRRP427YBTQZK3/action/author_attestation","sign_citation":"https://pith.science/pith/GXNZ2I7XRSULLRRP427YBTQZK3/action/citation_signature","submit_replication":"https://pith.science/pith/GXNZ2I7XRSULLRRP427YBTQZK3/action/replication_record"}},"created_at":"2026-06-01T02:04:13.969436+00:00","updated_at":"2026-06-01T02:04:13.969436+00:00"}