{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IO2MNCRXEXCSJHOU6ZCIDMM7W3","short_pith_number":"pith:IO2MNCRX","schema_version":"1.0","canonical_sha256":"43b4c68a3725c5249dd4f64481b19fb6ce1b4d1a0dd497b21395a25abdc16875","source":{"kind":"arxiv","id":"2104.04580","version":2},"attestation_state":"computed","paper":{"title":"Predicting the Reproducibility of Social and Behavioral Science Papers Using Supervised Learning Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DL","authors_text":"Arjun Manoj Menon, C. Lee Giles, James Caverlee, Jian Wu, Nishanth Nakshatri, Rajal Nivargi, Sai Ajay Modukuri, Sarah M. Rajtmajer, Sree Sai Teja Lanka, Xin Wei, Zhuoer Wang","submitted_at":"2021-04-08T00:45:20Z","abstract_excerpt":"In recent years, significant effort has been invested verifying the reproducibility and robustness of research claims in social and behavioral sciences (SBS), much of which has involved resource-intensive replication projects. In this paper, we investigate prediction of the reproducibility of SBS papers using machine learning methods based on a set of features. We propose a framework that extracts five types of features from scholarly work that can be used to support assessments of reproducibility of published research claims. Bibliometric features, venue features, and author features are coll"},"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":"2104.04580","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DL","submitted_at":"2021-04-08T00:45:20Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"2feb944b167d44d9bf0d2c6410ba01ffe477d696378781bce3650adbbb1f5522","abstract_canon_sha256":"a60d664d21948f35916d93390a6504de9c4ea0f27e347bafa3050ebc0ef0b84b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:29.089522Z","signature_b64":"RbKY3R6v+87ZyYivdJZ2N9YLhexfosiwuF/aPKIUE4VEAZPLJ3bE9v7FhBzPhrYtuOZDg77UGxQpsfSMaDzMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43b4c68a3725c5249dd4f64481b19fb6ce1b4d1a0dd497b21395a25abdc16875","last_reissued_at":"2026-07-05T03:24:29.089029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:29.089029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting the Reproducibility of Social and Behavioral Science Papers Using Supervised Learning Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DL","authors_text":"Arjun Manoj Menon, C. Lee Giles, James Caverlee, Jian Wu, Nishanth Nakshatri, Rajal Nivargi, Sai Ajay Modukuri, Sarah M. Rajtmajer, Sree Sai Teja Lanka, Xin Wei, Zhuoer Wang","submitted_at":"2021-04-08T00:45:20Z","abstract_excerpt":"In recent years, significant effort has been invested verifying the reproducibility and robustness of research claims in social and behavioral sciences (SBS), much of which has involved resource-intensive replication projects. In this paper, we investigate prediction of the reproducibility of SBS papers using machine learning methods based on a set of features. We propose a framework that extracts five types of features from scholarly work that can be used to support assessments of reproducibility of published research claims. Bibliometric features, venue features, and author features are coll"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04580","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/2104.04580/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":"2104.04580","created_at":"2026-07-05T03:24:29.089086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04580v2","created_at":"2026-07-05T03:24:29.089086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04580","created_at":"2026-07-05T03:24:29.089086+00:00"},{"alias_kind":"pith_short_12","alias_value":"IO2MNCRXEXCS","created_at":"2026-07-05T03:24:29.089086+00:00"},{"alias_kind":"pith_short_16","alias_value":"IO2MNCRXEXCSJHOU","created_at":"2026-07-05T03:24:29.089086+00:00"},{"alias_kind":"pith_short_8","alias_value":"IO2MNCRX","created_at":"2026-07-05T03:24:29.089086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.27394","citing_title":"Human-AI Collaboration for Estimating Scientific Replicability","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IO2MNCRXEXCSJHOU6ZCIDMM7W3","json":"https://pith.science/pith/IO2MNCRXEXCSJHOU6ZCIDMM7W3.json","graph_json":"https://pith.science/api/pith-number/IO2MNCRXEXCSJHOU6ZCIDMM7W3/graph.json","events_json":"https://pith.science/api/pith-number/IO2MNCRXEXCSJHOU6ZCIDMM7W3/events.json","paper":"https://pith.science/paper/IO2MNCRX"},"agent_actions":{"view_html":"https://pith.science/pith/IO2MNCRXEXCSJHOU6ZCIDMM7W3","download_json":"https://pith.science/pith/IO2MNCRXEXCSJHOU6ZCIDMM7W3.json","view_paper":"https://pith.science/paper/IO2MNCRX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04580&json=true","fetch_graph":"https://pith.science/api/pith-number/IO2MNCRXEXCSJHOU6ZCIDMM7W3/graph.json","fetch_events":"https://pith.science/api/pith-number/IO2MNCRXEXCSJHOU6ZCIDMM7W3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IO2MNCRXEXCSJHOU6ZCIDMM7W3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IO2MNCRXEXCSJHOU6ZCIDMM7W3/action/storage_attestation","attest_author":"https://pith.science/pith/IO2MNCRXEXCSJHOU6ZCIDMM7W3/action/author_attestation","sign_citation":"https://pith.science/pith/IO2MNCRXEXCSJHOU6ZCIDMM7W3/action/citation_signature","submit_replication":"https://pith.science/pith/IO2MNCRXEXCSJHOU6ZCIDMM7W3/action/replication_record"}},"created_at":"2026-07-05T03:24:29.089086+00:00","updated_at":"2026-07-05T03:24:29.089086+00:00"}