{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KD5A7D35TFLBVKMHRVXIFC6IP6","short_pith_number":"pith:KD5A7D35","schema_version":"1.0","canonical_sha256":"50fa0f8f7d99561aa9878d6e828bc87fa476e047c9e2c719c13a3b1dfd81f463","source":{"kind":"arxiv","id":"2605.14322","version":1},"attestation_state":"computed","paper":{"title":"Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dayiheng Liu, Haobo Li, Huamin Qu, Jianhong Tu, Kashun Shum, Peng Liu, Rui Sheng, Xiaodong Deng, Zixin Chen","submitted_at":"2026-05-14T03:34:25Z","abstract_excerpt":"Language agents are increasingly deployed in complex professional workflows, with tutoring emerging as a particularly high-stakes capability that remains largely unmeasured in existing benchmarks. Effective tutor agents require more than producing correct answers or executing accurate tool calls: a robust tutor must diagnose learner state, adapt support over time, make pedagogically justified decisions grounded in educational evidence, and execute interventions within realistic learning-management systems. We introduce EduAgentBench, a source-grounded benchmark for holistically evaluating tuto"},"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":"2605.14322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T03:34:25Z","cross_cats_sorted":[],"title_canon_sha256":"f6a9362eca8c9b4ba2f35181e7679317669fe065c8b397f34a0d3ecf71364ac0","abstract_canon_sha256":"d813ca2cc74fe2a7de2f31f6515d5ef5b6f216c1b2153d7a393b05768e6555b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:09.820909Z","signature_b64":"IdCmTadPuBpUKHDWKm+sDLbDQ4oCQCpq/HTTr5XItrgSMYwgaZeO6gVLhkulRBdCXUZag+fsaYNiM/vKNQjrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50fa0f8f7d99561aa9878d6e828bc87fa476e047c9e2c719c13a3b1dfd81f463","last_reissued_at":"2026-05-17T23:39:09.818666Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:09.818666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dayiheng Liu, Haobo Li, Huamin Qu, Jianhong Tu, Kashun Shum, Peng Liu, Rui Sheng, Xiaodong Deng, Zixin Chen","submitted_at":"2026-05-14T03:34:25Z","abstract_excerpt":"Language agents are increasingly deployed in complex professional workflows, with tutoring emerging as a particularly high-stakes capability that remains largely unmeasured in existing benchmarks. Effective tutor agents require more than producing correct answers or executing accurate tool calls: a robust tutor must diagnose learner state, adapt support over time, make pedagogically justified decisions grounded in educational evidence, and execute interventions within realistic learning-management systems. We introduce EduAgentBench, a source-grounded benchmark for holistically evaluating tuto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14322","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":""},"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":"2605.14322","created_at":"2026-05-17T23:39:09.818764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14322v1","created_at":"2026-05-17T23:39:09.818764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14322","created_at":"2026-05-17T23:39:09.818764+00:00"},{"alias_kind":"pith_short_12","alias_value":"KD5A7D35TFLB","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"KD5A7D35TFLBVKMH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"KD5A7D35","created_at":"2026-05-18T12:33:37.589309+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/KD5A7D35TFLBVKMHRVXIFC6IP6","json":"https://pith.science/pith/KD5A7D35TFLBVKMHRVXIFC6IP6.json","graph_json":"https://pith.science/api/pith-number/KD5A7D35TFLBVKMHRVXIFC6IP6/graph.json","events_json":"https://pith.science/api/pith-number/KD5A7D35TFLBVKMHRVXIFC6IP6/events.json","paper":"https://pith.science/paper/KD5A7D35"},"agent_actions":{"view_html":"https://pith.science/pith/KD5A7D35TFLBVKMHRVXIFC6IP6","download_json":"https://pith.science/pith/KD5A7D35TFLBVKMHRVXIFC6IP6.json","view_paper":"https://pith.science/paper/KD5A7D35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14322&json=true","fetch_graph":"https://pith.science/api/pith-number/KD5A7D35TFLBVKMHRVXIFC6IP6/graph.json","fetch_events":"https://pith.science/api/pith-number/KD5A7D35TFLBVKMHRVXIFC6IP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KD5A7D35TFLBVKMHRVXIFC6IP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KD5A7D35TFLBVKMHRVXIFC6IP6/action/storage_attestation","attest_author":"https://pith.science/pith/KD5A7D35TFLBVKMHRVXIFC6IP6/action/author_attestation","sign_citation":"https://pith.science/pith/KD5A7D35TFLBVKMHRVXIFC6IP6/action/citation_signature","submit_replication":"https://pith.science/pith/KD5A7D35TFLBVKMHRVXIFC6IP6/action/replication_record"}},"created_at":"2026-05-17T23:39:09.818764+00:00","updated_at":"2026-05-17T23:39:09.818764+00:00"}