{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:75QOMVP46II2W7YV4NGRM4OFZ3","short_pith_number":"pith:75QOMVP4","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"},"canonical_sha256":"ff60e655fcf211ab7f15e34d1671c5cee54d62692c0f94b3db9f93fb1953949d","source":{"kind":"arxiv","id":"2504.20679","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20679","created_at":"2026-07-05T11:32:28Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20679v2","created_at":"2026-07-05T11:32:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20679","created_at":"2026-07-05T11:32:28Z"},{"alias_kind":"pith_short_12","alias_value":"75QOMVP46II2","created_at":"2026-07-05T11:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"75QOMVP46II2W7YV","created_at":"2026-07-05T11:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"75QOMVP4","created_at":"2026-07-05T11:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:75QOMVP46II2W7YV4NGRM4OFZ3","target":"record","payload":{"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"},"canonical_sha256":"ff60e655fcf211ab7f15e34d1671c5cee54d62692c0f94b3db9f93fb1953949d","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"},"source_kind":"arxiv","source_id":"2504.20679","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHI8ga34RpW+i2a+d4VvGCTsOGZ5N6SPRiQjF4ghvvYosbXLznXWCjmD15W6zKPw9N7OYzKyhQJ+333ZYO45Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:56:03.752700Z"},"content_sha256":"6733b2e6cfae75acbd31e1966f757de0624099d92ba930969d6c2c6f9f61b1c5","schema_version":"1.0","event_id":"sha256:6733b2e6cfae75acbd31e1966f757de0624099d92ba930969d6c2c6f9f61b1c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:75QOMVP46II2W7YV4NGRM4OFZ3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"udErBO+zsLzUs9XRbE/XAYFaP+1TTAWbHhwKPKRGiHtr7KULiuX5g0xJrjW/dKl5cG/T/xhABzRfkYzCsyj8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:56:03.753035Z"},"content_sha256":"35879dcae4131973b70fdd37dfcaedda0c6c7b51942f72e8c04fd1188d2d6b82","schema_version":"1.0","event_id":"sha256:35879dcae4131973b70fdd37dfcaedda0c6c7b51942f72e8c04fd1188d2d6b82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3/bundle.json","state_url":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/75QOMVP46II2W7YV4NGRM4OFZ3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T22:56:03Z","links":{"resolver":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3","bundle":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3/bundle.json","state":"https://pith.science/pith/75QOMVP46II2W7YV4NGRM4OFZ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/75QOMVP46II2W7YV4NGRM4OFZ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:75QOMVP46II2W7YV4NGRM4OFZ3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"af5e58564eb83d65fefbbb8dcf32a3898e5e78bd213d1cb4eced34f4d9eee16f","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T12:00:33Z","title_canon_sha256":"789ef8f7638f7466826b551dac4c3f38500b0dac10de9a2778cc5850b8695f67"},"schema_version":"1.0","source":{"id":"2504.20679","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20679","created_at":"2026-07-05T11:32:28Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20679v2","created_at":"2026-07-05T11:32:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20679","created_at":"2026-07-05T11:32:28Z"},{"alias_kind":"pith_short_12","alias_value":"75QOMVP46II2","created_at":"2026-07-05T11:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"75QOMVP46II2W7YV","created_at":"2026-07-05T11:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"75QOMVP4","created_at":"2026-07-05T11:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:35879dcae4131973b70fdd37dfcaedda0c6c7b51942f72e8c04fd1188d2d6b82","target":"graph","created_at":"2026-07-05T11:32:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.20679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jon Johnson, Suparna De, Wing Yan Li, ZeQiang Wang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T12:00:33Z","title":"Are Information Retrieval Approaches Good at Harmonising Longitudinal Survey Questions in Social Science?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20679","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6733b2e6cfae75acbd31e1966f757de0624099d92ba930969d6c2c6f9f61b1c5","target":"record","created_at":"2026-07-05T11:32:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"af5e58564eb83d65fefbbb8dcf32a3898e5e78bd213d1cb4eced34f4d9eee16f","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T12:00:33Z","title_canon_sha256":"789ef8f7638f7466826b551dac4c3f38500b0dac10de9a2778cc5850b8695f67"},"schema_version":"1.0","source":{"id":"2504.20679","kind":"arxiv","version":2}},"canonical_sha256":"ff60e655fcf211ab7f15e34d1671c5cee54d62692c0f94b3db9f93fb1953949d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff60e655fcf211ab7f15e34d1671c5cee54d62692c0f94b3db9f93fb1953949d","first_computed_at":"2026-07-05T11:32:28.607098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:28.607098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZTXdpsteMsYbwur1BGPpsXdwQCQw0SDV83Mop1t073qC/qbOt6hebpwPThLlhpvSQgZ91vuFbB/8Ok9HQ3NTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:28.607719Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20679","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6733b2e6cfae75acbd31e1966f757de0624099d92ba930969d6c2c6f9f61b1c5","sha256:35879dcae4131973b70fdd37dfcaedda0c6c7b51942f72e8c04fd1188d2d6b82"],"state_sha256":"61f676e02dc7c2ea01291d2f4189f7454abe7c5a8d0ee71b9c3619c03b0a0b55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fCcj9y5aBqL1Tmd+cCjqhYc0Dr0WZwkaJys0M+EeFRgLZZjpOg3rGZW4RXPkE/JNEaP++yC2OSK2womL0psTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T22:56:03.756886Z","bundle_sha256":"fcd986267f7658f08cb09e80209f361bedaf472f0a2effe7fa3aaea2b910868f"}}