{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4NYBJRDY4BPL6RRZX637VQQFLM","short_pith_number":"pith:4NYBJRDY","schema_version":"1.0","canonical_sha256":"e37014c478e05ebf4639bfb7fac2055b35e2ccc5e8ec7dd864241a9382f701f8","source":{"kind":"arxiv","id":"2607.03028","version":1},"attestation_state":"computed","paper":{"title":"HETERQA: Benchmarking Record Retrieval over Multiple Heterogeneous Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chuanhui Yang, Hanchang Li, Quanqing Xu, Yaodong Su, Yixiang Fang","submitted_at":"2026-07-03T07:18:33Z","abstract_excerpt":"In emerging systems (e.g., social media and e-commerce platforms), data records are often drawn from heterogeneous sources, such as relational tables, text documents, image repositories, spatial databases, and knowledge graphs. Accordingly, retrieving target records for question-answering (QA) tasks requires us to jointly exploit these heterogeneous sources. However, most existing benchmarks are constructed from individual sources, and only a very few recent benchmarks have considered two or three sources. To alleviate this issue, we introduce HETERQA, a comprehensive benchmark with 857 QA pai"},"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":"2607.03028","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-03T07:18:33Z","cross_cats_sorted":[],"title_canon_sha256":"b811b2f2fe5b41b4252abd57351c3c70400eeb6f97bdf99457e7a6cac7bff9ec","abstract_canon_sha256":"7863ef2199242e2b5831d1666675bd905db12c7290378bf140da3db7fe966cc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:40.285934Z","signature_b64":"d9yUughcMtBhNinNzxsmteK85nAF0V9+vh1ukq14MempLnmuIMj7GfkqfHIrYb9nk2fcftEMCLwBQe5BcCQvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e37014c478e05ebf4639bfb7fac2055b35e2ccc5e8ec7dd864241a9382f701f8","last_reissued_at":"2026-07-07T01:16:40.285370Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:40.285370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HETERQA: Benchmarking Record Retrieval over Multiple Heterogeneous Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chuanhui Yang, Hanchang Li, Quanqing Xu, Yaodong Su, Yixiang Fang","submitted_at":"2026-07-03T07:18:33Z","abstract_excerpt":"In emerging systems (e.g., social media and e-commerce platforms), data records are often drawn from heterogeneous sources, such as relational tables, text documents, image repositories, spatial databases, and knowledge graphs. Accordingly, retrieving target records for question-answering (QA) tasks requires us to jointly exploit these heterogeneous sources. However, most existing benchmarks are constructed from individual sources, and only a very few recent benchmarks have considered two or three sources. To alleviate this issue, we introduce HETERQA, a comprehensive benchmark with 857 QA pai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03028","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/2607.03028/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":"2607.03028","created_at":"2026-07-07T01:16:40.285462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03028v1","created_at":"2026-07-07T01:16:40.285462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03028","created_at":"2026-07-07T01:16:40.285462+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NYBJRDY4BPL","created_at":"2026-07-07T01:16:40.285462+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NYBJRDY4BPL6RRZ","created_at":"2026-07-07T01:16:40.285462+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NYBJRDY","created_at":"2026-07-07T01:16:40.285462+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/4NYBJRDY4BPL6RRZX637VQQFLM","json":"https://pith.science/pith/4NYBJRDY4BPL6RRZX637VQQFLM.json","graph_json":"https://pith.science/api/pith-number/4NYBJRDY4BPL6RRZX637VQQFLM/graph.json","events_json":"https://pith.science/api/pith-number/4NYBJRDY4BPL6RRZX637VQQFLM/events.json","paper":"https://pith.science/paper/4NYBJRDY"},"agent_actions":{"view_html":"https://pith.science/pith/4NYBJRDY4BPL6RRZX637VQQFLM","download_json":"https://pith.science/pith/4NYBJRDY4BPL6RRZX637VQQFLM.json","view_paper":"https://pith.science/paper/4NYBJRDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03028&json=true","fetch_graph":"https://pith.science/api/pith-number/4NYBJRDY4BPL6RRZX637VQQFLM/graph.json","fetch_events":"https://pith.science/api/pith-number/4NYBJRDY4BPL6RRZX637VQQFLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NYBJRDY4BPL6RRZX637VQQFLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NYBJRDY4BPL6RRZX637VQQFLM/action/storage_attestation","attest_author":"https://pith.science/pith/4NYBJRDY4BPL6RRZX637VQQFLM/action/author_attestation","sign_citation":"https://pith.science/pith/4NYBJRDY4BPL6RRZX637VQQFLM/action/citation_signature","submit_replication":"https://pith.science/pith/4NYBJRDY4BPL6RRZX637VQQFLM/action/replication_record"}},"created_at":"2026-07-07T01:16:40.285462+00:00","updated_at":"2026-07-07T01:16:40.285462+00:00"}