{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JEVQTAWDSUAMCWFEV2XQ7OH6XY","short_pith_number":"pith:JEVQTAWD","canonical_record":{"source":{"id":"2202.09166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2022-02-18T12:35:46Z","cross_cats_sorted":["cs.CL","stat.AP","stat.ME"],"title_canon_sha256":"f7407e7bffe80194c0bb54eda757fc491c51b32bd567d02ebcd66a33380ba77b","abstract_canon_sha256":"e24f5a76b0912c39a72eb4123d8d28c34d85e5c948b8cd0041233991ed556b4b"},"schema_version":"1.0"},"canonical_sha256":"492b0982c39500c158a4aeaf0fb8febe19ad67e8e7517592a8541dbe6fdbe062","source":{"kind":"arxiv","id":"2202.09166","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.09166","created_at":"2026-07-05T05:34:43Z"},{"alias_kind":"arxiv_version","alias_value":"2202.09166v1","created_at":"2026-07-05T05:34:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09166","created_at":"2026-07-05T05:34:43Z"},{"alias_kind":"pith_short_12","alias_value":"JEVQTAWDSUAM","created_at":"2026-07-05T05:34:43Z"},{"alias_kind":"pith_short_16","alias_value":"JEVQTAWDSUAMCWFE","created_at":"2026-07-05T05:34:43Z"},{"alias_kind":"pith_short_8","alias_value":"JEVQTAWD","created_at":"2026-07-05T05:34:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JEVQTAWDSUAMCWFEV2XQ7OH6XY","target":"record","payload":{"canonical_record":{"source":{"id":"2202.09166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2022-02-18T12:35:46Z","cross_cats_sorted":["cs.CL","stat.AP","stat.ME"],"title_canon_sha256":"f7407e7bffe80194c0bb54eda757fc491c51b32bd567d02ebcd66a33380ba77b","abstract_canon_sha256":"e24f5a76b0912c39a72eb4123d8d28c34d85e5c948b8cd0041233991ed556b4b"},"schema_version":"1.0"},"canonical_sha256":"492b0982c39500c158a4aeaf0fb8febe19ad67e8e7517592a8541dbe6fdbe062","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:43.782435Z","signature_b64":"Sm5wBw+3pZlmRMtnQBWiucKzwf3UucrxiJGvUoOPmpNcFMO0BsZ9gu8hxoKxdu8jTSCducTm6X5ld/8wZonnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"492b0982c39500c158a4aeaf0fb8febe19ad67e8e7517592a8541dbe6fdbe062","last_reissued_at":"2026-07-05T05:34:43.781955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:43.781955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.09166","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:34:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ocW82IE7qiznmosp4ZP9NsgQCwJP00lP4WxJC0OP7ChrKjqSpeVJWI/1H/zRcIGYtKAtJr1tyvbQGxlNxY++DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:14:00.972405Z"},"content_sha256":"3308e21e50b72b6c7b273365c0878a9f84e3c65d838723b2d900c824b690d358","schema_version":"1.0","event_id":"sha256:3308e21e50b72b6c7b273365c0878a9f84e3c65d838723b2d900c824b690d358"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JEVQTAWDSUAMCWFEV2XQ7OH6XY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating the Construct Validity of Text Embeddings with Application to Survey Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.AP","stat.ME"],"primary_cat":"cs.CY","authors_text":"Daniel L Oberski, Dong Nguyen, Qixiang Fang","submitted_at":"2022-02-18T12:35:46Z","abstract_excerpt":"Text embedding models from Natural Language Processing can map text data (e.g. words, sentences, documents) to supposedly meaningful numerical representations (a.k.a. text embeddings). While such models are increasingly applied in social science research, one important issue is often not addressed: the extent to which these embeddings are valid representations of constructs relevant for social science research. We therefore propose the use of the classic construct validity framework to evaluate the validity of text embeddings. We show how this framework can be adapted to the opaque and high-di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09166","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/2202.09166/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":"2026-07-05T05:34:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iEWqVy6h+0sbDDA7atXaf2Ema7siMLkB4KU7p60vVYz9/eklcVqaBkJixpdgX9XC+2j4ekub7LJ+U/qgLeUVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:14:00.973413Z"},"content_sha256":"6967de2e8b1a6f693013ab44b5a463775c1aba97221c2ffe42ff46966e77394b","schema_version":"1.0","event_id":"sha256:6967de2e8b1a6f693013ab44b5a463775c1aba97221c2ffe42ff46966e77394b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JEVQTAWDSUAMCWFEV2XQ7OH6XY/bundle.json","state_url":"https://pith.science/pith/JEVQTAWDSUAMCWFEV2XQ7OH6XY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JEVQTAWDSUAMCWFEV2XQ7OH6XY/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":"2026-08-23T17:14:00Z","links":{"resolver":"https://pith.science/pith/JEVQTAWDSUAMCWFEV2XQ7OH6XY","bundle":"https://pith.science/pith/JEVQTAWDSUAMCWFEV2XQ7OH6XY/bundle.json","state":"https://pith.science/pith/JEVQTAWDSUAMCWFEV2XQ7OH6XY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JEVQTAWDSUAMCWFEV2XQ7OH6XY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JEVQTAWDSUAMCWFEV2XQ7OH6XY","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":"e24f5a76b0912c39a72eb4123d8d28c34d85e5c948b8cd0041233991ed556b4b","cross_cats_sorted":["cs.CL","stat.AP","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2022-02-18T12:35:46Z","title_canon_sha256":"f7407e7bffe80194c0bb54eda757fc491c51b32bd567d02ebcd66a33380ba77b"},"schema_version":"1.0","source":{"id":"2202.09166","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.09166","created_at":"2026-07-05T05:34:43Z"},{"alias_kind":"arxiv_version","alias_value":"2202.09166v1","created_at":"2026-07-05T05:34:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09166","created_at":"2026-07-05T05:34:43Z"},{"alias_kind":"pith_short_12","alias_value":"JEVQTAWDSUAM","created_at":"2026-07-05T05:34:43Z"},{"alias_kind":"pith_short_16","alias_value":"JEVQTAWDSUAMCWFE","created_at":"2026-07-05T05:34:43Z"},{"alias_kind":"pith_short_8","alias_value":"JEVQTAWD","created_at":"2026-07-05T05:34:43Z"}],"graph_snapshots":[{"event_id":"sha256:6967de2e8b1a6f693013ab44b5a463775c1aba97221c2ffe42ff46966e77394b","target":"graph","created_at":"2026-07-05T05:34:43Z","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/2202.09166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text embedding models from Natural Language Processing can map text data (e.g. words, sentences, documents) to supposedly meaningful numerical representations (a.k.a. text embeddings). While such models are increasingly applied in social science research, one important issue is often not addressed: the extent to which these embeddings are valid representations of constructs relevant for social science research. We therefore propose the use of the classic construct validity framework to evaluate the validity of text embeddings. We show how this framework can be adapted to the opaque and high-di","authors_text":"Daniel L Oberski, Dong Nguyen, Qixiang Fang","cross_cats":["cs.CL","stat.AP","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2022-02-18T12:35:46Z","title":"Evaluating the Construct Validity of Text Embeddings with Application to Survey Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09166","kind":"arxiv","version":1},"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":"sha256:3308e21e50b72b6c7b273365c0878a9f84e3c65d838723b2d900c824b690d358","target":"record","created_at":"2026-07-05T05:34:43Z","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":"e24f5a76b0912c39a72eb4123d8d28c34d85e5c948b8cd0041233991ed556b4b","cross_cats_sorted":["cs.CL","stat.AP","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2022-02-18T12:35:46Z","title_canon_sha256":"f7407e7bffe80194c0bb54eda757fc491c51b32bd567d02ebcd66a33380ba77b"},"schema_version":"1.0","source":{"id":"2202.09166","kind":"arxiv","version":1}},"canonical_sha256":"492b0982c39500c158a4aeaf0fb8febe19ad67e8e7517592a8541dbe6fdbe062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"492b0982c39500c158a4aeaf0fb8febe19ad67e8e7517592a8541dbe6fdbe062","first_computed_at":"2026-07-05T05:34:43.781955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:34:43.781955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sm5wBw+3pZlmRMtnQBWiucKzwf3UucrxiJGvUoOPmpNcFMO0BsZ9gu8hxoKxdu8jTSCducTm6X5ld/8wZonnDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:34:43.782435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.09166","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3308e21e50b72b6c7b273365c0878a9f84e3c65d838723b2d900c824b690d358","sha256:6967de2e8b1a6f693013ab44b5a463775c1aba97221c2ffe42ff46966e77394b"],"state_sha256":"4b13d7f9debbd0e17bb711026d2addbacaee729f36335386a659502c419b4ca0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dfl29cK6siZo5nFARR5hntD+hnQC8Mxj/0NaUUEv+VlBdSkaDROV1R8SH7MCr4xAoWXfSbjWlr+L11FF+v84Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:14:00.978391Z","bundle_sha256":"4ad61f8b77e6cd90be2e16ea410dc71871f82c1ecac85d156b297f9507cea9f1"}}