{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AA4IEUNTZF5KDPAFL2B2DTMVYS","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":"77acfbac6d1003c4e50a3ff3cea9d1a65c63508ed9bd36f057f82e5d318ac829","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T05:43:21Z","title_canon_sha256":"5074bfffe7d3a5f558ef8e4f7c03c7b90c1dd76cda408bb6e4a805fed5628e38"},"schema_version":"1.0","source":{"id":"2505.07247","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07247","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07247v2","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07247","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"pith_short_12","alias_value":"AA4IEUNTZF5K","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"pith_short_16","alias_value":"AA4IEUNTZF5KDPAF","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"pith_short_8","alias_value":"AA4IEUNT","created_at":"2026-07-05T11:03:24Z"}],"graph_snapshots":[{"event_id":"sha256:0904767f4d65beea5b370224198c4cf592728253291d30cb3e047d93d3cb2fcc","target":"graph","created_at":"2026-07-05T11:03:24Z","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/2505.07247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bin Cui, Conghui He, Feiyang Ye, Jinhao Yan, Kexuan Zhang, Linyihan Zhang, Peichao Lai, Wentao Zhang, Yanwei Xu, Yilei Wang, Yi Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T05:43:21Z","title":"SAS-Bench: A Fine-Grained Benchmark for Evaluating Short Answer Scoring with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07247","kind":"arxiv","version":2},"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":"sha256:43f66074cdea917bf5bdb3709f89051a2aa3a1c77e359aa7d42a9d075c466cbd","target":"record","created_at":"2026-07-05T11:03:24Z","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":"77acfbac6d1003c4e50a3ff3cea9d1a65c63508ed9bd36f057f82e5d318ac829","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T05:43:21Z","title_canon_sha256":"5074bfffe7d3a5f558ef8e4f7c03c7b90c1dd76cda408bb6e4a805fed5628e38"},"schema_version":"1.0","source":{"id":"2505.07247","kind":"arxiv","version":2}},"canonical_sha256":"00388251b3c97aa1bc055e83a1cd95c4aa554f2ad000abf0760b765976840ea1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00388251b3c97aa1bc055e83a1cd95c4aa554f2ad000abf0760b765976840ea1","first_computed_at":"2026-07-05T11:03:24.524396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:24.524396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AEMl65i+KCMM2jBB5uN2AxGmJM184EFSnfyEwFB5TjnY6rBuOQ3Qz6C98tegFl9E9GCIOAPfnfjS+5nFVgfvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:24.524893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07247","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43f66074cdea917bf5bdb3709f89051a2aa3a1c77e359aa7d42a9d075c466cbd","sha256:0904767f4d65beea5b370224198c4cf592728253291d30cb3e047d93d3cb2fcc"],"state_sha256":"9d6dd8fbd7e08af651c7433af89c7aa929433e2b6684e7b3f2dc4cc670904401"}