{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7RJ4CSGDFEDTCUSQQQ6AXIAJRH","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":"1e77bc6c1854a3606f7207fb82eccbf3d64379dc8c7582afb7a16cdef18617d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T06:32:02Z","title_canon_sha256":"d1f7e09ae32b28584f4873b48f508405d049c0cc9e41c18cc3fd580beddf192d"},"schema_version":"1.0","source":{"id":"2505.18549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18549","created_at":"2026-07-05T11:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18549v1","created_at":"2026-07-05T11:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18549","created_at":"2026-07-05T11:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"7RJ4CSGDFEDT","created_at":"2026-07-05T11:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"7RJ4CSGDFEDTCUSQ","created_at":"2026-07-05T11:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"7RJ4CSGD","created_at":"2026-07-05T11:08:48Z"}],"graph_snapshots":[{"event_id":"sha256:f8387a655bc58fd1e61373482a077c4130960c85f84cbc4d249e0237b4daffd5","target":"graph","created_at":"2026-07-05T11:08:48Z","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/2505.18549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MSA-MathEval, our submission to the BEA 2025 Shared Task on evaluating AI tutor responses across four instructional dimensions: Mistake Identification, Mistake Location, Providing Guidance, and Actionability. Our approach uses a unified training pipeline to fine-tune a single instruction-tuned language model across all tracks, without any task-specific architectural changes. To improve prediction reliability, we introduce a disagreement-aware ensemble inference strategy that enhances coverage of minority labels. Our system achieves strong performance across all tracks, ranking 1st i","authors_text":"Ali Hamdi, Baraa Hikal, Islam Oshallah, Mohamed Basem","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T06:32:02Z","title":"MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18549","kind":"arxiv","version":1},"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":"sha256:164b36558ac80903a7cedb5bc9d9983fd22695bf39dad435a209c2264f2e7415","target":"record","created_at":"2026-07-05T11:08:48Z","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":"1e77bc6c1854a3606f7207fb82eccbf3d64379dc8c7582afb7a16cdef18617d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T06:32:02Z","title_canon_sha256":"d1f7e09ae32b28584f4873b48f508405d049c0cc9e41c18cc3fd580beddf192d"},"schema_version":"1.0","source":{"id":"2505.18549","kind":"arxiv","version":1}},"canonical_sha256":"fc53c148c32907315250843c0ba00989e9bf1e24547156fc95670c652bd6c016","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc53c148c32907315250843c0ba00989e9bf1e24547156fc95670c652bd6c016","first_computed_at":"2026-07-05T11:08:48.264386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:48.264386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YL2gVX9nA0vw7v8zOepdKsaxDBCyVcrZ4mt9jfR7TXXie87UtscPmjlR0aloB2Gkb+f23dl8sR1gznHVj8HlCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:48.264874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:164b36558ac80903a7cedb5bc9d9983fd22695bf39dad435a209c2264f2e7415","sha256:f8387a655bc58fd1e61373482a077c4130960c85f84cbc4d249e0237b4daffd5"],"state_sha256":"196adeb6d9698796031a2d072895d493bf03a39c193988e39bb0b79c1600c2bd"}