{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AKKSMTYX6AO74ZEO3EKD7PXSIB","short_pith_number":"pith:AKKSMTYX","schema_version":"1.0","canonical_sha256":"0295264f17f01dfe648ed9143fbef24063f1a16f3c671ccd9fd5adcc9dc7aa98","source":{"kind":"arxiv","id":"2503.10671","version":1},"attestation_state":"computed","paper":{"title":"Identifying Non-Replicable Social Science Studies with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Annika Fred\\'en, Bastiaan Bruinsma, Denitsa Saynova, Kajsa Hansson, Moa Johansson","submitted_at":"2025-03-10T11:48:05Z","abstract_excerpt":"In this study, we investigate whether LLMs can be used to indicate if a study in the behavioural social sciences is replicable. Using a dataset of 14 previously replicated studies (9 successful, 5 unsuccessful), we evaluate the ability of both open-source (Llama 3 8B, Qwen 2 7B, Mistral 7B) and proprietary (GPT-4o) instruction-tuned LLMs to discriminate between replicable and non-replicable findings. We use LLMs to generate synthetic samples of responses from behavioural studies and estimate whether the measured effects support the original findings. When compared with human replication result"},"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":"2503.10671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T11:48:05Z","cross_cats_sorted":[],"title_canon_sha256":"15ee7f392e2585131a374ca33a76f3b48bd1d992691131b394119b3564869a15","abstract_canon_sha256":"accf4aceaba7644f63522a81041a92d2a521c63e142d8cfe7b939d91b32469f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:03.424958Z","signature_b64":"fDOH6WzhBepND8Z9ifo84qUJa+2ToZW9wr8mpg8xok/LcudFNVBRu/keZO1DM0CKHYhtNNJKB+jR+49K4GTsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0295264f17f01dfe648ed9143fbef24063f1a16f3c671ccd9fd5adcc9dc7aa98","last_reissued_at":"2026-07-05T10:31:03.424163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:03.424163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identifying Non-Replicable Social Science Studies with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Annika Fred\\'en, Bastiaan Bruinsma, Denitsa Saynova, Kajsa Hansson, Moa Johansson","submitted_at":"2025-03-10T11:48:05Z","abstract_excerpt":"In this study, we investigate whether LLMs can be used to indicate if a study in the behavioural social sciences is replicable. Using a dataset of 14 previously replicated studies (9 successful, 5 unsuccessful), we evaluate the ability of both open-source (Llama 3 8B, Qwen 2 7B, Mistral 7B) and proprietary (GPT-4o) instruction-tuned LLMs to discriminate between replicable and non-replicable findings. We use LLMs to generate synthetic samples of responses from behavioural studies and estimate whether the measured effects support the original findings. When compared with human replication result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10671","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/2503.10671/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":"2503.10671","created_at":"2026-07-05T10:31:03.424265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10671v1","created_at":"2026-07-05T10:31:03.424265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10671","created_at":"2026-07-05T10:31:03.424265+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKKSMTYX6AO7","created_at":"2026-07-05T10:31:03.424265+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKKSMTYX6AO74ZEO","created_at":"2026-07-05T10:31:03.424265+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKKSMTYX","created_at":"2026-07-05T10:31:03.424265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17324","citing_title":"ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10718","citing_title":"SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKKSMTYX6AO74ZEO3EKD7PXSIB","json":"https://pith.science/pith/AKKSMTYX6AO74ZEO3EKD7PXSIB.json","graph_json":"https://pith.science/api/pith-number/AKKSMTYX6AO74ZEO3EKD7PXSIB/graph.json","events_json":"https://pith.science/api/pith-number/AKKSMTYX6AO74ZEO3EKD7PXSIB/events.json","paper":"https://pith.science/paper/AKKSMTYX"},"agent_actions":{"view_html":"https://pith.science/pith/AKKSMTYX6AO74ZEO3EKD7PXSIB","download_json":"https://pith.science/pith/AKKSMTYX6AO74ZEO3EKD7PXSIB.json","view_paper":"https://pith.science/paper/AKKSMTYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10671&json=true","fetch_graph":"https://pith.science/api/pith-number/AKKSMTYX6AO74ZEO3EKD7PXSIB/graph.json","fetch_events":"https://pith.science/api/pith-number/AKKSMTYX6AO74ZEO3EKD7PXSIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKKSMTYX6AO74ZEO3EKD7PXSIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKKSMTYX6AO74ZEO3EKD7PXSIB/action/storage_attestation","attest_author":"https://pith.science/pith/AKKSMTYX6AO74ZEO3EKD7PXSIB/action/author_attestation","sign_citation":"https://pith.science/pith/AKKSMTYX6AO74ZEO3EKD7PXSIB/action/citation_signature","submit_replication":"https://pith.science/pith/AKKSMTYX6AO74ZEO3EKD7PXSIB/action/replication_record"}},"created_at":"2026-07-05T10:31:03.424265+00:00","updated_at":"2026-07-05T10:31:03.424265+00:00"}