{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5IDSX2NLW7U3C2YPQKK5GAEVZZ","short_pith_number":"pith:5IDSX2NL","schema_version":"1.0","canonical_sha256":"ea072be9abb7e9b16b0f8295d30095ce43927985734109310ed3597b08733db9","source":{"kind":"arxiv","id":"2503.11827","version":1},"attestation_state":"computed","paper":{"title":"Bridging the LLM Accessibility Divide? Performance, Fairness, and Cost of Closed versus Open LLMs for Automated Essay Scoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Abbasi, John P. Lalor, Kezia Oketch, Yi Yang","submitted_at":"2025-03-14T19:34:40Z","abstract_excerpt":"Closed large language models (LLMs) such as GPT-4 have set state-of-the-art results across a number of NLP tasks and have become central to NLP and machine learning (ML)-driven solutions. Closed LLMs' performance and wide adoption has sparked considerable debate about their accessibility in terms of availability, cost, and transparency. In this study, we perform a rigorous comparative analysis of nine leading LLMs, spanning closed, open, and open-source LLM ecosystems, across text assessment and generation tasks related to automated essay scoring. Our findings reveal that for few-shot learning"},"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":"2503.11827","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-14T19:34:40Z","cross_cats_sorted":[],"title_canon_sha256":"d254061d07713168a2311f7a47338f0159cc39b3ca056e7a9c96e201344f06f6","abstract_canon_sha256":"c1ef4d2517bad60b72f715db837d061e1ae530e21475efea761ef47cafb910e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:00.545108Z","signature_b64":"s8J1g2bnipPBrMGOTTS23SWgduaMqkwwbMCX+8fGGVW6I9VdyFlArGLCuZssUxk0TBkA+med2iqX/FihWcnwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea072be9abb7e9b16b0f8295d30095ce43927985734109310ed3597b08733db9","last_reissued_at":"2026-07-05T10:32:00.544261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:00.544261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the LLM Accessibility Divide? Performance, Fairness, and Cost of Closed versus Open LLMs for Automated Essay Scoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Abbasi, John P. Lalor, Kezia Oketch, Yi Yang","submitted_at":"2025-03-14T19:34:40Z","abstract_excerpt":"Closed large language models (LLMs) such as GPT-4 have set state-of-the-art results across a number of NLP tasks and have become central to NLP and machine learning (ML)-driven solutions. Closed LLMs' performance and wide adoption has sparked considerable debate about their accessibility in terms of availability, cost, and transparency. In this study, we perform a rigorous comparative analysis of nine leading LLMs, spanning closed, open, and open-source LLM ecosystems, across text assessment and generation tasks related to automated essay scoring. Our findings reveal that for few-shot learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11827","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/2503.11827/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":"2503.11827","created_at":"2026-07-05T10:32:00.544388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11827v1","created_at":"2026-07-05T10:32:00.544388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11827","created_at":"2026-07-05T10:32:00.544388+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IDSX2NLW7U3","created_at":"2026-07-05T10:32:00.544388+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IDSX2NLW7U3C2YP","created_at":"2026-07-05T10:32:00.544388+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IDSX2NL","created_at":"2026-07-05T10:32:00.544388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20287","citing_title":"PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IDSX2NLW7U3C2YPQKK5GAEVZZ","json":"https://pith.science/pith/5IDSX2NLW7U3C2YPQKK5GAEVZZ.json","graph_json":"https://pith.science/api/pith-number/5IDSX2NLW7U3C2YPQKK5GAEVZZ/graph.json","events_json":"https://pith.science/api/pith-number/5IDSX2NLW7U3C2YPQKK5GAEVZZ/events.json","paper":"https://pith.science/paper/5IDSX2NL"},"agent_actions":{"view_html":"https://pith.science/pith/5IDSX2NLW7U3C2YPQKK5GAEVZZ","download_json":"https://pith.science/pith/5IDSX2NLW7U3C2YPQKK5GAEVZZ.json","view_paper":"https://pith.science/paper/5IDSX2NL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11827&json=true","fetch_graph":"https://pith.science/api/pith-number/5IDSX2NLW7U3C2YPQKK5GAEVZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5IDSX2NLW7U3C2YPQKK5GAEVZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IDSX2NLW7U3C2YPQKK5GAEVZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IDSX2NLW7U3C2YPQKK5GAEVZZ/action/storage_attestation","attest_author":"https://pith.science/pith/5IDSX2NLW7U3C2YPQKK5GAEVZZ/action/author_attestation","sign_citation":"https://pith.science/pith/5IDSX2NLW7U3C2YPQKK5GAEVZZ/action/citation_signature","submit_replication":"https://pith.science/pith/5IDSX2NLW7U3C2YPQKK5GAEVZZ/action/replication_record"}},"created_at":"2026-07-05T10:32:00.544388+00:00","updated_at":"2026-07-05T10:32:00.544388+00:00"}