{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BFCUZQBFPDENDZBFFFPASJ566X","short_pith_number":"pith:BFCUZQBF","schema_version":"1.0","canonical_sha256":"09454cc02578c8d1e425295e0927bef5fd1d414f26eb49deb2b51af0f2d2349a","source":{"kind":"arxiv","id":"2608.03206","version":1},"attestation_state":"computed","paper":{"title":"EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CY","authors_text":"Eunjoo Lee, Hoilym Kwon, Minchul Shin, Sookbun Lee, Unggi Lee, Yeil Jeong","submitted_at":"2026-08-04T06:47:26Z","abstract_excerpt":"Large language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point solutions been integrated into agents operating over a learning management system (LMS). Yet tutoring is long-horizon, since a learner improves over days and weeks rather than in a single turn, and no benchmark evaluates an agent tutor across a sustained relationship. We introduce EduClaw-Bench, a benchmark that places an agent tutor in a continuous 30-day relationship with a simulated learner grounded in knowledge tracing"},"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":"2608.03206","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2026-08-04T06:47:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2c33204f38d69967d6384304d64008ae632f0163610db8d3f0cd0439ce43973e","abstract_canon_sha256":"0779e157c7f9965fb7cb05f0564df0a1d086006cdf2f5ba833373fdf1242e34a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:46:15.882612Z","signature_b64":"NVWICI+pWe6OaVTCiH2BuD6h6lg8XQi2MMr5MZheqwsBjdNtxBZ4xwTGyYi+qH51wURx1ZmSQC1ITAZZZotVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09454cc02578c8d1e425295e0927bef5fd1d414f26eb49deb2b51af0f2d2349a","last_reissued_at":"2026-08-05T00:46:15.880165Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:46:15.880165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CY","authors_text":"Eunjoo Lee, Hoilym Kwon, Minchul Shin, Sookbun Lee, Unggi Lee, Yeil Jeong","submitted_at":"2026-08-04T06:47:26Z","abstract_excerpt":"Large language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point solutions been integrated into agents operating over a learning management system (LMS). Yet tutoring is long-horizon, since a learner improves over days and weeks rather than in a single turn, and no benchmark evaluates an agent tutor across a sustained relationship. We introduce EduClaw-Bench, a benchmark that places an agent tutor in a continuous 30-day relationship with a simulated learner grounded in knowledge tracing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03206","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/2608.03206/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":"2608.03206","created_at":"2026-08-05T00:46:15.881096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03206v1","created_at":"2026-08-05T00:46:15.881096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03206","created_at":"2026-08-05T00:46:15.881096+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFCUZQBFPDEN","created_at":"2026-08-05T00:46:15.881096+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFCUZQBFPDENDZBF","created_at":"2026-08-05T00:46:15.881096+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFCUZQBF","created_at":"2026-08-05T00:46:15.881096+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/BFCUZQBFPDENDZBFFFPASJ566X","json":"https://pith.science/pith/BFCUZQBFPDENDZBFFFPASJ566X.json","graph_json":"https://pith.science/api/pith-number/BFCUZQBFPDENDZBFFFPASJ566X/graph.json","events_json":"https://pith.science/api/pith-number/BFCUZQBFPDENDZBFFFPASJ566X/events.json","paper":"https://pith.science/paper/BFCUZQBF"},"agent_actions":{"view_html":"https://pith.science/pith/BFCUZQBFPDENDZBFFFPASJ566X","download_json":"https://pith.science/pith/BFCUZQBFPDENDZBFFFPASJ566X.json","view_paper":"https://pith.science/paper/BFCUZQBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03206&json=true","fetch_graph":"https://pith.science/api/pith-number/BFCUZQBFPDENDZBFFFPASJ566X/graph.json","fetch_events":"https://pith.science/api/pith-number/BFCUZQBFPDENDZBFFFPASJ566X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFCUZQBFPDENDZBFFFPASJ566X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFCUZQBFPDENDZBFFFPASJ566X/action/storage_attestation","attest_author":"https://pith.science/pith/BFCUZQBFPDENDZBFFFPASJ566X/action/author_attestation","sign_citation":"https://pith.science/pith/BFCUZQBFPDENDZBFFFPASJ566X/action/citation_signature","submit_replication":"https://pith.science/pith/BFCUZQBFPDENDZBFFFPASJ566X/action/replication_record"}},"created_at":"2026-08-05T00:46:15.881096+00:00","updated_at":"2026-08-05T00:46:15.881096+00:00"}