{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:75QOMVP46II2W7YV4NGRM4OFZ3","short_pith_number":"pith:75QOMVP4","schema_version":"1.0","canonical_sha256":"ff60e655fcf211ab7f15e34d1671c5cee54d62692c0f94b3db9f93fb1953949d","source":{"kind":"arxiv","id":"2504.20679","version":2},"attestation_state":"computed","paper":{"title":"Are Information Retrieval Approaches Good at Harmonising Longitudinal Survey Questions in Social Science?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jon Johnson, Suparna De, Wing Yan Li, ZeQiang Wang","submitted_at":"2025-04-29T12:00:33Z","abstract_excerpt":"Automated detection of semantically equivalent questions in longitudinal social science surveys is crucial for long-term studies informing empirical research in the social, economic, and health sciences. Retrieving equivalent questions faces dual challenges: inconsistent representation of theoretical constructs (i.e. concept/sub-concept) across studies as well as between question and response options, and the evolution of vocabulary and structure in longitudinal text. To address these challenges, our multi-disciplinary collaboration of computer scientists and survey specialists presents a new "},"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":"2504.20679","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T12:00:33Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"789ef8f7638f7466826b551dac4c3f38500b0dac10de9a2778cc5850b8695f67","abstract_canon_sha256":"af5e58564eb83d65fefbbb8dcf32a3898e5e78bd213d1cb4eced34f4d9eee16f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:28.607719Z","signature_b64":"ZTXdpsteMsYbwur1BGPpsXdwQCQw0SDV83Mop1t073qC/qbOt6hebpwPThLlhpvSQgZ91vuFbB/8Ok9HQ3NTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff60e655fcf211ab7f15e34d1671c5cee54d62692c0f94b3db9f93fb1953949d","last_reissued_at":"2026-07-05T11:32:28.607098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:28.607098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Information Retrieval Approaches Good at Harmonising Longitudinal Survey Questions in Social Science?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jon Johnson, Suparna De, Wing Yan Li, ZeQiang Wang","submitted_at":"2025-04-29T12:00:33Z","abstract_excerpt":"Automated detection of semantically equivalent questions in longitudinal social science surveys is crucial for long-term studies informing empirical research in the social, economic, and health sciences. Retrieving equivalent questions faces dual challenges: inconsistent representation of theoretical constructs (i.e. concept/sub-concept) across studies as well as between question and response options, and the evolution of vocabulary and structure in longitudinal text. To address these challenges, our multi-disciplinary collaboration of computer scientists and survey specialists presents a new "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20679","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/2504.20679/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":"2504.20679","created_at":"2026-07-05T11:32:28.607161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20679v2","created_at":"2026-07-05T11:32:28.607161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20679","created_at":"2026-07-05T11:32:28.607161+00:00"},{"alias_kind":"pith_short_12","alias_value":"75QOMVP46II2","created_at":"2026-07-05T11:32:28.607161+00:00"},{"alias_kind":"pith_short_16","alias_value":"75QOMVP46II2W7YV","created_at":"2026-07-05T11:32:28.607161+00:00"},{"alias_kind":"pith_short_8","alias_value":"75QOMVP4","created_at":"2026-07-05T11:32:28.607161+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/75QOMVP46II2W7YV4NGRM4OFZ3","json":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3.json","graph_json":"https://pith.science/api/pith-number/75QOMVP46II2W7YV4NGRM4OFZ3/graph.json","events_json":"https://pith.science/api/pith-number/75QOMVP46II2W7YV4NGRM4OFZ3/events.json","paper":"https://pith.science/paper/75QOMVP4"},"agent_actions":{"view_html":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3","download_json":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3.json","view_paper":"https://pith.science/paper/75QOMVP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20679&json=true","fetch_graph":"https://pith.science/api/pith-number/75QOMVP46II2W7YV4NGRM4OFZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/75QOMVP46II2W7YV4NGRM4OFZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3/action/storage_attestation","attest_author":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3/action/author_attestation","sign_citation":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3/action/citation_signature","submit_replication":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3/action/replication_record"}},"created_at":"2026-07-05T11:32:28.607161+00:00","updated_at":"2026-07-05T11:32:28.607161+00:00"}