{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AEPI2C3UEIX6N3S42M5XS4NWDD","short_pith_number":"pith:AEPI2C3U","schema_version":"1.0","canonical_sha256":"011e8d0b74222fe6ee5cd33b7971b618c0276a219ed351f0048850e4f1f93464","source":{"kind":"arxiv","id":"2505.00061","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Security and Strengthening Defenses in Automated Short-Answer Grading Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CL","authors_text":"Brian Clauser, Peter Baldwin, Polina Harikeo, Saed Rezayi, Sahar Yarmohammadtoosky, Victoria Yaneva, Yiyun Zhou","submitted_at":"2025-04-30T14:53:09Z","abstract_excerpt":"This study examines vulnerabilities in transformer-based automated short-answer grading systems used in medical education, with a focus on how these systems can be manipulated through adversarial gaming strategies. Our research identifies three main types of gaming strategies that exploit the system's weaknesses, potentially leading to false positives. To counteract these vulnerabilities, we implement several adversarial training methods designed to enhance the systems' robustness. Our results indicate that these methods significantly reduce the susceptibility of grading systems to such manipu"},"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":"2505.00061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T14:53:09Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"ddf989cf7f22c3a19a6da07c67fcac8a82672338c01d6bd65fbaf463673c07d4","abstract_canon_sha256":"b6300bd1f3572cb414d138b4723ead0f0d757412a28da7f0342dce439f77736f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:41.345418Z","signature_b64":"s0hJiArSHOG1aHZtb56z6KbIAPrFBfm3ixtwl0x8mmahuDkv/4E/PN+rMohj/kFbADMwuyLpltgvuXRXdNpmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"011e8d0b74222fe6ee5cd33b7971b618c0276a219ed351f0048850e4f1f93464","last_reissued_at":"2026-07-05T10:56:41.344903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:41.344903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Security and Strengthening Defenses in Automated Short-Answer Grading Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CL","authors_text":"Brian Clauser, Peter Baldwin, Polina Harikeo, Saed Rezayi, Sahar Yarmohammadtoosky, Victoria Yaneva, Yiyun Zhou","submitted_at":"2025-04-30T14:53:09Z","abstract_excerpt":"This study examines vulnerabilities in transformer-based automated short-answer grading systems used in medical education, with a focus on how these systems can be manipulated through adversarial gaming strategies. Our research identifies three main types of gaming strategies that exploit the system's weaknesses, potentially leading to false positives. To counteract these vulnerabilities, we implement several adversarial training methods designed to enhance the systems' robustness. Our results indicate that these methods significantly reduce the susceptibility of grading systems to such manipu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00061","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/2505.00061/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":"2505.00061","created_at":"2026-07-05T10:56:41.344960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00061v1","created_at":"2026-07-05T10:56:41.344960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00061","created_at":"2026-07-05T10:56:41.344960+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEPI2C3UEIX6","created_at":"2026-07-05T10:56:41.344960+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEPI2C3UEIX6N3S4","created_at":"2026-07-05T10:56:41.344960+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEPI2C3U","created_at":"2026-07-05T10:56:41.344960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEPI2C3UEIX6N3S42M5XS4NWDD","json":"https://pith.science/pith/AEPI2C3UEIX6N3S42M5XS4NWDD.json","graph_json":"https://pith.science/api/pith-number/AEPI2C3UEIX6N3S42M5XS4NWDD/graph.json","events_json":"https://pith.science/api/pith-number/AEPI2C3UEIX6N3S42M5XS4NWDD/events.json","paper":"https://pith.science/paper/AEPI2C3U"},"agent_actions":{"view_html":"https://pith.science/pith/AEPI2C3UEIX6N3S42M5XS4NWDD","download_json":"https://pith.science/pith/AEPI2C3UEIX6N3S42M5XS4NWDD.json","view_paper":"https://pith.science/paper/AEPI2C3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00061&json=true","fetch_graph":"https://pith.science/api/pith-number/AEPI2C3UEIX6N3S42M5XS4NWDD/graph.json","fetch_events":"https://pith.science/api/pith-number/AEPI2C3UEIX6N3S42M5XS4NWDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEPI2C3UEIX6N3S42M5XS4NWDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEPI2C3UEIX6N3S42M5XS4NWDD/action/storage_attestation","attest_author":"https://pith.science/pith/AEPI2C3UEIX6N3S42M5XS4NWDD/action/author_attestation","sign_citation":"https://pith.science/pith/AEPI2C3UEIX6N3S42M5XS4NWDD/action/citation_signature","submit_replication":"https://pith.science/pith/AEPI2C3UEIX6N3S42M5XS4NWDD/action/replication_record"}},"created_at":"2026-07-05T10:56:41.344960+00:00","updated_at":"2026-07-05T10:56:41.344960+00:00"}