{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LB2ILFMAH24Y7UR77X5WNGVCCL","short_pith_number":"pith:LB2ILFMA","schema_version":"1.0","canonical_sha256":"58748595803eb98fd23ffdfb669aa212f4cfc3f1303a6527e33853687b5b4a39","source":{"kind":"arxiv","id":"2411.18104","version":6},"attestation_state":"computed","paper":{"title":"Training and Evaluating Language Models with Template-based Data Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Yifan Zhang","submitted_at":"2024-11-27T07:32:56Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) such as GPT-3, PaLM, and Llama has significantly transformed natural language processing, showcasing remarkable capabilities in understanding and generating language. However, a fundamental bottleneck persists: these models often struggle with tasks requiring complex, multi-step reasoning, particularly in mathematical problem-solving. This deficiency stems from the critical scarcity of large-scale, high-quality, domain-specific datasets necessary for cultivating sophisticated reasoning abilities. To overcome this challenge, we introduce Tem"},"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":"2411.18104","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T07:32:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4554cc462a015589ccb5f9262da58050dbfbb68e2673a8e79f3b449682effa95","abstract_canon_sha256":"f67134a2c6f292b6c4faccc01511225af32ab4f86a7ba702e8685854a7ff0f4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:18.292388Z","signature_b64":"lNG1V2d5Ab6rUwt5OoqaIJwDMSf2dTuZtt1mLzOaR/NJeh0/WFp1aoDbSFqmXU4qnU/DvocOpcQbP7+LMwceAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58748595803eb98fd23ffdfb669aa212f4cfc3f1303a6527e33853687b5b4a39","last_reissued_at":"2026-05-17T23:39:18.290914Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:18.290914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training and Evaluating Language Models with Template-based Data Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Yifan Zhang","submitted_at":"2024-11-27T07:32:56Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) such as GPT-3, PaLM, and Llama has significantly transformed natural language processing, showcasing remarkable capabilities in understanding and generating language. However, a fundamental bottleneck persists: these models often struggle with tasks requiring complex, multi-step reasoning, particularly in mathematical problem-solving. This deficiency stems from the critical scarcity of large-scale, high-quality, domain-specific datasets necessary for cultivating sophisticated reasoning abilities. To overcome this challenge, we introduce Tem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18104","kind":"arxiv","version":6},"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":"2411.18104","created_at":"2026-05-17T23:39:18.291048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18104v6","created_at":"2026-05-17T23:39:18.291048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18104","created_at":"2026-05-17T23:39:18.291048+00:00"},{"alias_kind":"pith_short_12","alias_value":"LB2ILFMAH24Y","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LB2ILFMAH24Y7UR7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LB2ILFMA","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/LB2ILFMAH24Y7UR77X5WNGVCCL","json":"https://pith.science/pith/LB2ILFMAH24Y7UR77X5WNGVCCL.json","graph_json":"https://pith.science/api/pith-number/LB2ILFMAH24Y7UR77X5WNGVCCL/graph.json","events_json":"https://pith.science/api/pith-number/LB2ILFMAH24Y7UR77X5WNGVCCL/events.json","paper":"https://pith.science/paper/LB2ILFMA"},"agent_actions":{"view_html":"https://pith.science/pith/LB2ILFMAH24Y7UR77X5WNGVCCL","download_json":"https://pith.science/pith/LB2ILFMAH24Y7UR77X5WNGVCCL.json","view_paper":"https://pith.science/paper/LB2ILFMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18104&json=true","fetch_graph":"https://pith.science/api/pith-number/LB2ILFMAH24Y7UR77X5WNGVCCL/graph.json","fetch_events":"https://pith.science/api/pith-number/LB2ILFMAH24Y7UR77X5WNGVCCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LB2ILFMAH24Y7UR77X5WNGVCCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LB2ILFMAH24Y7UR77X5WNGVCCL/action/storage_attestation","attest_author":"https://pith.science/pith/LB2ILFMAH24Y7UR77X5WNGVCCL/action/author_attestation","sign_citation":"https://pith.science/pith/LB2ILFMAH24Y7UR77X5WNGVCCL/action/citation_signature","submit_replication":"https://pith.science/pith/LB2ILFMAH24Y7UR77X5WNGVCCL/action/replication_record"}},"created_at":"2026-05-17T23:39:18.291048+00:00","updated_at":"2026-05-17T23:39:18.291048+00:00"}