{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AA4IEUNTZF5KDPAFL2B2DTMVYS","short_pith_number":"pith:AA4IEUNT","schema_version":"1.0","canonical_sha256":"00388251b3c97aa1bc055e83a1cd95c4aa554f2ad000abf0760b765976840ea1","source":{"kind":"arxiv","id":"2505.07247","version":2},"attestation_state":"computed","paper":{"title":"SAS-Bench: A Fine-Grained Benchmark for Evaluating Short Answer Scoring with Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Cui, Conghui He, Feiyang Ye, Jinhao Yan, Kexuan Zhang, Linyihan Zhang, Peichao Lai, Wentao Zhang, Yanwei Xu, Yilei Wang, Yi Lin","submitted_at":"2025-05-12T05:43:21Z","abstract_excerpt":"Subjective Answer Grading (SAG) plays a crucial role in education, standardized testing, and automated assessment systems, particularly for evaluating short-form responses in Short Answer Scoring (SAS). However, existing approaches often produce coarse-grained scores and lack detailed reasoning. Although large language models (LLMs) have demonstrated potential as zero-shot evaluators, they remain susceptible to bias, inconsistencies with human judgment, and limited transparency in scoring decisions. To overcome these limitations, we introduce SAS-Bench, a benchmark specifically designed for LL"},"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":"2505.07247","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T05:43:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5074bfffe7d3a5f558ef8e4f7c03c7b90c1dd76cda408bb6e4a805fed5628e38","abstract_canon_sha256":"77acfbac6d1003c4e50a3ff3cea9d1a65c63508ed9bd36f057f82e5d318ac829"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:24.524893Z","signature_b64":"AEMl65i+KCMM2jBB5uN2AxGmJM184EFSnfyEwFB5TjnY6rBuOQ3Qz6C98tegFl9E9GCIOAPfnfjS+5nFVgfvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00388251b3c97aa1bc055e83a1cd95c4aa554f2ad000abf0760b765976840ea1","last_reissued_at":"2026-07-05T11:03:24.524396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:24.524396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAS-Bench: A Fine-Grained Benchmark for Evaluating Short Answer Scoring with Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Cui, Conghui He, Feiyang Ye, Jinhao Yan, Kexuan Zhang, Linyihan Zhang, Peichao Lai, Wentao Zhang, Yanwei Xu, Yilei Wang, Yi Lin","submitted_at":"2025-05-12T05:43:21Z","abstract_excerpt":"Subjective Answer Grading (SAG) plays a crucial role in education, standardized testing, and automated assessment systems, particularly for evaluating short-form responses in Short Answer Scoring (SAS). However, existing approaches often produce coarse-grained scores and lack detailed reasoning. Although large language models (LLMs) have demonstrated potential as zero-shot evaluators, they remain susceptible to bias, inconsistencies with human judgment, and limited transparency in scoring decisions. To overcome these limitations, we introduce SAS-Bench, a benchmark specifically designed for LL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07247","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/2505.07247/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":"2505.07247","created_at":"2026-07-05T11:03:24.524457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07247v2","created_at":"2026-07-05T11:03:24.524457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07247","created_at":"2026-07-05T11:03:24.524457+00:00"},{"alias_kind":"pith_short_12","alias_value":"AA4IEUNTZF5K","created_at":"2026-07-05T11:03:24.524457+00:00"},{"alias_kind":"pith_short_16","alias_value":"AA4IEUNTZF5KDPAF","created_at":"2026-07-05T11:03:24.524457+00:00"},{"alias_kind":"pith_short_8","alias_value":"AA4IEUNT","created_at":"2026-07-05T11:03:24.524457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06350","citing_title":"EDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM Grading","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AA4IEUNTZF5KDPAFL2B2DTMVYS","json":"https://pith.science/pith/AA4IEUNTZF5KDPAFL2B2DTMVYS.json","graph_json":"https://pith.science/api/pith-number/AA4IEUNTZF5KDPAFL2B2DTMVYS/graph.json","events_json":"https://pith.science/api/pith-number/AA4IEUNTZF5KDPAFL2B2DTMVYS/events.json","paper":"https://pith.science/paper/AA4IEUNT"},"agent_actions":{"view_html":"https://pith.science/pith/AA4IEUNTZF5KDPAFL2B2DTMVYS","download_json":"https://pith.science/pith/AA4IEUNTZF5KDPAFL2B2DTMVYS.json","view_paper":"https://pith.science/paper/AA4IEUNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07247&json=true","fetch_graph":"https://pith.science/api/pith-number/AA4IEUNTZF5KDPAFL2B2DTMVYS/graph.json","fetch_events":"https://pith.science/api/pith-number/AA4IEUNTZF5KDPAFL2B2DTMVYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AA4IEUNTZF5KDPAFL2B2DTMVYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AA4IEUNTZF5KDPAFL2B2DTMVYS/action/storage_attestation","attest_author":"https://pith.science/pith/AA4IEUNTZF5KDPAFL2B2DTMVYS/action/author_attestation","sign_citation":"https://pith.science/pith/AA4IEUNTZF5KDPAFL2B2DTMVYS/action/citation_signature","submit_replication":"https://pith.science/pith/AA4IEUNTZF5KDPAFL2B2DTMVYS/action/replication_record"}},"created_at":"2026-07-05T11:03:24.524457+00:00","updated_at":"2026-07-05T11:03:24.524457+00:00"}