{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T4DGOO6YY4VSBI2VWPCT7BLIOB","short_pith_number":"pith:T4DGOO6Y","schema_version":"1.0","canonical_sha256":"9f06673bd8c72b20a355b3c53f856870539cb5e81f48534aea6d573c5821dd1f","source":{"kind":"arxiv","id":"2506.14200","version":1},"attestation_state":"computed","paper":{"title":"ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Brihi Joshi, Kaitlyn Zhou, Keyu He, Sadra Sabouri, Sahana Ramnath, Souti Chattopadhyay, Swabha Swayamdipta, Xiang Ren","submitted_at":"2025-06-17T05:36:39Z","abstract_excerpt":"Language models today are widely used in education, yet their ability to tailor responses for learners with varied informational needs and knowledge backgrounds remains under-explored. To this end, we introduce ELI-Why, a benchmark of 13.4K \"Why\" questions to evaluate the pedagogical capabilities of language models. We then conduct two extensive human studies to assess the utility of language model-generated explanatory answers (explanations) on our benchmark, tailored to three distinct educational grades: elementary, high-school and graduate school. In our first study, human raters assume the"},"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":"2506.14200","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T05:36:39Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"7cbd00687f94d774c10128cc08c36a5102d5a706158551d42dbba58d53a196bc","abstract_canon_sha256":"50cfc0ce35ec58ba68abd3add831c690a2c6f73f4c627d37d366ddc03ff7f8e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:50.727462Z","signature_b64":"ZRul1OmBftQ/AyasEesqqkxA4zUWuQgACqszdGIK97XVPzRc9KbxDoTpXwApScExWDARyyljmgaobII/cfMhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f06673bd8c72b20a355b3c53f856870539cb5e81f48534aea6d573c5821dd1f","last_reissued_at":"2026-07-05T11:22:50.726964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:50.726964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Brihi Joshi, Kaitlyn Zhou, Keyu He, Sadra Sabouri, Sahana Ramnath, Souti Chattopadhyay, Swabha Swayamdipta, Xiang Ren","submitted_at":"2025-06-17T05:36:39Z","abstract_excerpt":"Language models today are widely used in education, yet their ability to tailor responses for learners with varied informational needs and knowledge backgrounds remains under-explored. To this end, we introduce ELI-Why, a benchmark of 13.4K \"Why\" questions to evaluate the pedagogical capabilities of language models. We then conduct two extensive human studies to assess the utility of language model-generated explanatory answers (explanations) on our benchmark, tailored to three distinct educational grades: elementary, high-school and graduate school. In our first study, human raters assume the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14200","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/2506.14200/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":"2506.14200","created_at":"2026-07-05T11:22:50.727025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14200v1","created_at":"2026-07-05T11:22:50.727025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14200","created_at":"2026-07-05T11:22:50.727025+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4DGOO6YY4VS","created_at":"2026-07-05T11:22:50.727025+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4DGOO6YY4VSBI2V","created_at":"2026-07-05T11:22:50.727025+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4DGOO6Y","created_at":"2026-07-05T11:22:50.727025+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/T4DGOO6YY4VSBI2VWPCT7BLIOB","json":"https://pith.science/pith/T4DGOO6YY4VSBI2VWPCT7BLIOB.json","graph_json":"https://pith.science/api/pith-number/T4DGOO6YY4VSBI2VWPCT7BLIOB/graph.json","events_json":"https://pith.science/api/pith-number/T4DGOO6YY4VSBI2VWPCT7BLIOB/events.json","paper":"https://pith.science/paper/T4DGOO6Y"},"agent_actions":{"view_html":"https://pith.science/pith/T4DGOO6YY4VSBI2VWPCT7BLIOB","download_json":"https://pith.science/pith/T4DGOO6YY4VSBI2VWPCT7BLIOB.json","view_paper":"https://pith.science/paper/T4DGOO6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14200&json=true","fetch_graph":"https://pith.science/api/pith-number/T4DGOO6YY4VSBI2VWPCT7BLIOB/graph.json","fetch_events":"https://pith.science/api/pith-number/T4DGOO6YY4VSBI2VWPCT7BLIOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4DGOO6YY4VSBI2VWPCT7BLIOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4DGOO6YY4VSBI2VWPCT7BLIOB/action/storage_attestation","attest_author":"https://pith.science/pith/T4DGOO6YY4VSBI2VWPCT7BLIOB/action/author_attestation","sign_citation":"https://pith.science/pith/T4DGOO6YY4VSBI2VWPCT7BLIOB/action/citation_signature","submit_replication":"https://pith.science/pith/T4DGOO6YY4VSBI2VWPCT7BLIOB/action/replication_record"}},"created_at":"2026-07-05T11:22:50.727025+00:00","updated_at":"2026-07-05T11:22:50.727025+00:00"}