{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q5ZMGH2OGL5JWGDYRDJ62KQU4J","short_pith_number":"pith:Q5ZMGH2O","canonical_record":{"source":{"id":"2409.12722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T12:44:00Z","cross_cats_sorted":[],"title_canon_sha256":"4f8747740ca1fda408fb8da843a940a5db43c81c4ef323625c1d57f82b3724cf","abstract_canon_sha256":"658d1ec5386ff275f909fc80750721a76d99793d2235b94c1464117ed59bc5f7"},"schema_version":"1.0"},"canonical_sha256":"8772c31f4e32fa9b187888d3ed2a14e25d508f0716f213e7cc72b805045063d6","source":{"kind":"arxiv","id":"2409.12722","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12722","created_at":"2026-07-05T09:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12722v1","created_at":"2026-07-05T09:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12722","created_at":"2026-07-05T09:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"Q5ZMGH2OGL5J","created_at":"2026-07-05T09:09:11Z"},{"alias_kind":"pith_short_16","alias_value":"Q5ZMGH2OGL5JWGDY","created_at":"2026-07-05T09:09:11Z"},{"alias_kind":"pith_short_8","alias_value":"Q5ZMGH2O","created_at":"2026-07-05T09:09:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q5ZMGH2OGL5JWGDYRDJ62KQU4J","target":"record","payload":{"canonical_record":{"source":{"id":"2409.12722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T12:44:00Z","cross_cats_sorted":[],"title_canon_sha256":"4f8747740ca1fda408fb8da843a940a5db43c81c4ef323625c1d57f82b3724cf","abstract_canon_sha256":"658d1ec5386ff275f909fc80750721a76d99793d2235b94c1464117ed59bc5f7"},"schema_version":"1.0"},"canonical_sha256":"8772c31f4e32fa9b187888d3ed2a14e25d508f0716f213e7cc72b805045063d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:11.293965Z","signature_b64":"aRMqw4426/WysgqXG8nv5yBBZxAQPjlqozQLUmU38p/W+QUJMqdmPbasfYIeIop7A2DrtkalMVC8Lhycy+ZZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8772c31f4e32fa9b187888d3ed2a14e25d508f0716f213e7cc72b805045063d6","last_reissued_at":"2026-07-05T09:09:11.293458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:11.293458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.12722","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":"2026-07-05T09:09:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4iFFkUjWdTn0YKQP7l464QLPOCZHm7bmk7Fybdc0FQP4LpOV3lgwpCtRSTG2gc8Ypn7zEiQi45zCaOCXv0hQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:13:21.681249Z"},"content_sha256":"f9d7c7e2e3d18adbd1d1db2ca8c3fef9ff56eda7143c9b869d1c0ba06d02bedc","schema_version":"1.0","event_id":"sha256:f9d7c7e2e3d18adbd1d1db2ca8c3fef9ff56eda7143c9b869d1c0ba06d02bedc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q5ZMGH2OGL5JWGDYRDJ62KQU4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanyu Duan, Jiaxin Liu, Kar Yan Tam, Yi Yang","submitted_at":"2024-09-19T12:44:00Z","abstract_excerpt":"The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that leverages the internal hidden states of large language models (LLMs) to generate these concept measures. Specifically, the proposed method learns a concept vector that captures how the LLM internally represents the target concept, then estimates the concept value for text data by projecting the text's LLM hidden states onto the concept vector. Three replication stu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12722","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/2409.12722/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":"2026-07-05T09:09:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ucNUR81oFF2UVwgQdHtm8l10oeDySFzgmzSIPgu1Q+UbyS4DXuvqAKUxY3lwCcDgffUmPhKOlB3jyTGFJPqqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:13:21.682151Z"},"content_sha256":"2d7cba8ef9e6bcd63e17ffe9792859599604c37130f3c29943fb9aff6f785808","schema_version":"1.0","event_id":"sha256:2d7cba8ef9e6bcd63e17ffe9792859599604c37130f3c29943fb9aff6f785808"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q5ZMGH2OGL5JWGDYRDJ62KQU4J/bundle.json","state_url":"https://pith.science/pith/Q5ZMGH2OGL5JWGDYRDJ62KQU4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q5ZMGH2OGL5JWGDYRDJ62KQU4J/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":"2026-08-09T19:13:21Z","links":{"resolver":"https://pith.science/pith/Q5ZMGH2OGL5JWGDYRDJ62KQU4J","bundle":"https://pith.science/pith/Q5ZMGH2OGL5JWGDYRDJ62KQU4J/bundle.json","state":"https://pith.science/pith/Q5ZMGH2OGL5JWGDYRDJ62KQU4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q5ZMGH2OGL5JWGDYRDJ62KQU4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q5ZMGH2OGL5JWGDYRDJ62KQU4J","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":"658d1ec5386ff275f909fc80750721a76d99793d2235b94c1464117ed59bc5f7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T12:44:00Z","title_canon_sha256":"4f8747740ca1fda408fb8da843a940a5db43c81c4ef323625c1d57f82b3724cf"},"schema_version":"1.0","source":{"id":"2409.12722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12722","created_at":"2026-07-05T09:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12722v1","created_at":"2026-07-05T09:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12722","created_at":"2026-07-05T09:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"Q5ZMGH2OGL5J","created_at":"2026-07-05T09:09:11Z"},{"alias_kind":"pith_short_16","alias_value":"Q5ZMGH2OGL5JWGDY","created_at":"2026-07-05T09:09:11Z"},{"alias_kind":"pith_short_8","alias_value":"Q5ZMGH2O","created_at":"2026-07-05T09:09:11Z"}],"graph_snapshots":[{"event_id":"sha256:2d7cba8ef9e6bcd63e17ffe9792859599604c37130f3c29943fb9aff6f785808","target":"graph","created_at":"2026-07-05T09:09:11Z","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/2409.12722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that leverages the internal hidden states of large language models (LLMs) to generate these concept measures. Specifically, the proposed method learns a concept vector that captures how the LLM internally represents the target concept, then estimates the concept value for text data by projecting the text's LLM hidden states onto the concept vector. Three replication stu","authors_text":"Hanyu Duan, Jiaxin Liu, Kar Yan Tam, Yi Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T12:44:00Z","title":"LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12722","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:f9d7c7e2e3d18adbd1d1db2ca8c3fef9ff56eda7143c9b869d1c0ba06d02bedc","target":"record","created_at":"2026-07-05T09:09:11Z","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":"658d1ec5386ff275f909fc80750721a76d99793d2235b94c1464117ed59bc5f7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T12:44:00Z","title_canon_sha256":"4f8747740ca1fda408fb8da843a940a5db43c81c4ef323625c1d57f82b3724cf"},"schema_version":"1.0","source":{"id":"2409.12722","kind":"arxiv","version":1}},"canonical_sha256":"8772c31f4e32fa9b187888d3ed2a14e25d508f0716f213e7cc72b805045063d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8772c31f4e32fa9b187888d3ed2a14e25d508f0716f213e7cc72b805045063d6","first_computed_at":"2026-07-05T09:09:11.293458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:11.293458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aRMqw4426/WysgqXG8nv5yBBZxAQPjlqozQLUmU38p/W+QUJMqdmPbasfYIeIop7A2DrtkalMVC8Lhycy+ZZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:11.293965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9d7c7e2e3d18adbd1d1db2ca8c3fef9ff56eda7143c9b869d1c0ba06d02bedc","sha256:2d7cba8ef9e6bcd63e17ffe9792859599604c37130f3c29943fb9aff6f785808"],"state_sha256":"5370945e18703b5b043351a1723506c5c14e287d6ede90f7cfb4dc95d7dcca12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GNubRkZ2Jj3ZLikjXeEaJCgI0BgXTqf+hhn2Swr9c4qy2z86Zb25BxZyf0bhEmPAfMqY1cgzBUZkHrJ7ny0xCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:13:21.687559Z","bundle_sha256":"33b2d7a4e00a2f7e5d76ae3b9ecea81ef4f6972a41fd3314bc961092e06e3dd0"}}