{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K2WGQJ6KVZRXQF6H55POREOI7V","short_pith_number":"pith:K2WGQJ6K","schema_version":"1.0","canonical_sha256":"56ac6827caae637817c7ef5ee891c8fd512af51655ce9eda1e3110bcdaaaa20c","source":{"kind":"arxiv","id":"2606.05180","version":1},"attestation_state":"computed","paper":{"title":"From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Babette B\\\"uhler, Dorottya Demszky, Enkelejda Kasneci, Heather Hill, Ivo Bueno, Philipp Stark, Tim F\\\"utterer, Ulrich Trautwein","submitted_at":"2026-04-18T14:27:51Z","abstract_excerpt":"Automated scoring models are increasingly used to assign rubric-based quality ratings to complex language performances, including classroom transcripts, yet they typically provide little insight into why a particular score is produced. We propose a general framework for sentence-level interpretability of rubric-based scoring that combines model-agnostic Shapley-value attributions with rationales generated by large language models (LLMs). Instantiated on the Quality of Feedback dimension of the CLASS framework using the NCTE corpus, the framework enables systematic comparison of fine-tuned pret"},"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":"2606.05180","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-18T14:27:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"65d5665781ae35ec9e89945f1a4148c5a88fa9b5e4d20b2aa22c34f7b8b8bfbf","abstract_canon_sha256":"f8f824f9c4eafb3c6623371b49029fd073a1884481bd295e6093d1a654063989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:47.964899Z","signature_b64":"PIaEl2Es92JunHqecFjXbiWNQ6GIzgsdqQmJxQIJy+HOBCDigi0luG3JYv38lzK7svXHKgxTuqpbZtGliIk1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56ac6827caae637817c7ef5ee891c8fd512af51655ce9eda1e3110bcdaaaa20c","last_reissued_at":"2026-06-05T00:13:47.964071Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:47.964071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Babette B\\\"uhler, Dorottya Demszky, Enkelejda Kasneci, Heather Hill, Ivo Bueno, Philipp Stark, Tim F\\\"utterer, Ulrich Trautwein","submitted_at":"2026-04-18T14:27:51Z","abstract_excerpt":"Automated scoring models are increasingly used to assign rubric-based quality ratings to complex language performances, including classroom transcripts, yet they typically provide little insight into why a particular score is produced. We propose a general framework for sentence-level interpretability of rubric-based scoring that combines model-agnostic Shapley-value attributions with rationales generated by large language models (LLMs). Instantiated on the Quality of Feedback dimension of the CLASS framework using the NCTE corpus, the framework enables systematic comparison of fine-tuned pret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05180","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/2606.05180/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":"2606.05180","created_at":"2026-06-05T00:13:47.964177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05180v1","created_at":"2026-06-05T00:13:47.964177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05180","created_at":"2026-06-05T00:13:47.964177+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2WGQJ6KVZRX","created_at":"2026-06-05T00:13:47.964177+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2WGQJ6KVZRXQF6H","created_at":"2026-06-05T00:13:47.964177+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2WGQJ6K","created_at":"2026-06-05T00:13:47.964177+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/K2WGQJ6KVZRXQF6H55POREOI7V","json":"https://pith.science/pith/K2WGQJ6KVZRXQF6H55POREOI7V.json","graph_json":"https://pith.science/api/pith-number/K2WGQJ6KVZRXQF6H55POREOI7V/graph.json","events_json":"https://pith.science/api/pith-number/K2WGQJ6KVZRXQF6H55POREOI7V/events.json","paper":"https://pith.science/paper/K2WGQJ6K"},"agent_actions":{"view_html":"https://pith.science/pith/K2WGQJ6KVZRXQF6H55POREOI7V","download_json":"https://pith.science/pith/K2WGQJ6KVZRXQF6H55POREOI7V.json","view_paper":"https://pith.science/paper/K2WGQJ6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05180&json=true","fetch_graph":"https://pith.science/api/pith-number/K2WGQJ6KVZRXQF6H55POREOI7V/graph.json","fetch_events":"https://pith.science/api/pith-number/K2WGQJ6KVZRXQF6H55POREOI7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2WGQJ6KVZRXQF6H55POREOI7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2WGQJ6KVZRXQF6H55POREOI7V/action/storage_attestation","attest_author":"https://pith.science/pith/K2WGQJ6KVZRXQF6H55POREOI7V/action/author_attestation","sign_citation":"https://pith.science/pith/K2WGQJ6KVZRXQF6H55POREOI7V/action/citation_signature","submit_replication":"https://pith.science/pith/K2WGQJ6KVZRXQF6H55POREOI7V/action/replication_record"}},"created_at":"2026-06-05T00:13:47.964177+00:00","updated_at":"2026-06-05T00:13:47.964177+00:00"}