{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SCY4MDQZT4GIN26QGWOJ4FSHSS","short_pith_number":"pith:SCY4MDQZ","schema_version":"1.0","canonical_sha256":"90b1c60e199f0c86ebd0359c9e164794b2d34c9864d03ed2b191885084f753e0","source":{"kind":"arxiv","id":"2511.21692","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Generalization Across Difficulty Levels: It's Not So Easy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ilana Nguyen, Max Zuo, Nihal V. Nayak, Stephen H. Bach, Yeganeh Kordi","submitted_at":"2025-11-26T18:59:57Z","abstract_excerpt":"We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is mixed regarding whether training on easier or harder data leads to better results, and whether those gains come on easier or harder test data. We address this question by conducting a systematic evaluation of LLMs' generalization across models, datasets, and fine-grained groups of example difficulty. We rank examples in six datasets using the outputs of thousands of different LLMs and Item Response Theory (IRT), a we"},"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":"2511.21692","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-11-26T18:59:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cdfa46709a58ba2117f0a238743ecf2d1e6b9bbfcff73c9a17e65e1d5d6323bb","abstract_canon_sha256":"3c0d6fadc5c1cdab16642d898ba52a9621eecb9dcf6ad0699dc2ba641f188697"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:58:09.681181Z","signature_b64":"KbBC48PMBC3fZdEPdVmIwnji1kK5zTQFeP8EDclRR43l2U5JvXp4GVhJK8ZbbARKe8q4rbuC5UPR6c9JgFQqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90b1c60e199f0c86ebd0359c9e164794b2d34c9864d03ed2b191885084f753e0","last_reissued_at":"2026-08-04T01:58:09.679531Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:58:09.679531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Generalization Across Difficulty Levels: It's Not So Easy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ilana Nguyen, Max Zuo, Nihal V. Nayak, Stephen H. Bach, Yeganeh Kordi","submitted_at":"2025-11-26T18:59:57Z","abstract_excerpt":"We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is mixed regarding whether training on easier or harder data leads to better results, and whether those gains come on easier or harder test data. We address this question by conducting a systematic evaluation of LLMs' generalization across models, datasets, and fine-grained groups of example difficulty. We rank examples in six datasets using the outputs of thousands of different LLMs and Item Response Theory (IRT), a we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.21692","kind":"arxiv","version":2},"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/2511.21692/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":"2511.21692","created_at":"2026-08-04T01:58:09.680892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.21692v2","created_at":"2026-08-04T01:58:09.680892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.21692","created_at":"2026-08-04T01:58:09.680892+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCY4MDQZT4GI","created_at":"2026-08-04T01:58:09.680892+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCY4MDQZT4GIN26Q","created_at":"2026-08-04T01:58:09.680892+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCY4MDQZ","created_at":"2026-08-04T01:58:09.680892+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/SCY4MDQZT4GIN26QGWOJ4FSHSS","json":"https://pith.science/pith/SCY4MDQZT4GIN26QGWOJ4FSHSS.json","graph_json":"https://pith.science/api/pith-number/SCY4MDQZT4GIN26QGWOJ4FSHSS/graph.json","events_json":"https://pith.science/api/pith-number/SCY4MDQZT4GIN26QGWOJ4FSHSS/events.json","paper":"https://pith.science/paper/SCY4MDQZ"},"agent_actions":{"view_html":"https://pith.science/pith/SCY4MDQZT4GIN26QGWOJ4FSHSS","download_json":"https://pith.science/pith/SCY4MDQZT4GIN26QGWOJ4FSHSS.json","view_paper":"https://pith.science/paper/SCY4MDQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.21692&json=true","fetch_graph":"https://pith.science/api/pith-number/SCY4MDQZT4GIN26QGWOJ4FSHSS/graph.json","fetch_events":"https://pith.science/api/pith-number/SCY4MDQZT4GIN26QGWOJ4FSHSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCY4MDQZT4GIN26QGWOJ4FSHSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCY4MDQZT4GIN26QGWOJ4FSHSS/action/storage_attestation","attest_author":"https://pith.science/pith/SCY4MDQZT4GIN26QGWOJ4FSHSS/action/author_attestation","sign_citation":"https://pith.science/pith/SCY4MDQZT4GIN26QGWOJ4FSHSS/action/citation_signature","submit_replication":"https://pith.science/pith/SCY4MDQZT4GIN26QGWOJ4FSHSS/action/replication_record"}},"created_at":"2026-08-04T01:58:09.680892+00:00","updated_at":"2026-08-04T01:58:09.680892+00:00"}