{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N5EMFOU6PROKT6KDAZ3FHDUSIF","short_pith_number":"pith:N5EMFOU6","schema_version":"1.0","canonical_sha256":"6f48c2ba9e7c5ca9f9430676538e92416a053f2ef72ff236db6e3157c13e7a06","source":{"kind":"arxiv","id":"2508.13037","version":1},"attestation_state":"computed","paper":{"title":"Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiajun Liu, Peng Wang, Xinhe Li","submitted_at":"2025-08-18T15:56:10Z","abstract_excerpt":"Recent studies have demonstrated that Large Language Models (LLMs) have strong mathematical reasoning abilities but rely on hundreds of billions of parameters. To tackle the challenge of poor reasoning in Small Language Models (SLMs), existing methods typically leverage LLMs to generate massive amounts of data for cramming training. In psychology, they are akin to System 1 thinking, which resolves reasoning problems rapidly based on experience and intuition. However, human learning also requires System 2 thinking, where knowledge is first acquired and then reinforced through practice. Inspired"},"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":"2508.13037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T15:56:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b540b306adf64fe94792ddd1d4664741a2b48427cd23f4f84a666ca92b31c976","abstract_canon_sha256":"9804d9ff47c70113cc5b70d3ddc483e903522621c5df5bbf1b8acd91b7abdb8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:31.247447Z","signature_b64":"1hNbUtenKPuNwJIIu9NBdk0N6tpwcztLa2ASVh6gFATylQxcqEgpUAMeKe8opeYKqL3BkGECpfQlqmHdS+JqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f48c2ba9e7c5ca9f9430676538e92416a053f2ef72ff236db6e3157c13e7a06","last_reissued_at":"2026-07-05T11:55:31.246962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:31.246962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiajun Liu, Peng Wang, Xinhe Li","submitted_at":"2025-08-18T15:56:10Z","abstract_excerpt":"Recent studies have demonstrated that Large Language Models (LLMs) have strong mathematical reasoning abilities but rely on hundreds of billions of parameters. To tackle the challenge of poor reasoning in Small Language Models (SLMs), existing methods typically leverage LLMs to generate massive amounts of data for cramming training. In psychology, they are akin to System 1 thinking, which resolves reasoning problems rapidly based on experience and intuition. However, human learning also requires System 2 thinking, where knowledge is first acquired and then reinforced through practice. Inspired"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13037","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/2508.13037/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":"2508.13037","created_at":"2026-07-05T11:55:31.247020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13037v1","created_at":"2026-07-05T11:55:31.247020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13037","created_at":"2026-07-05T11:55:31.247020+00:00"},{"alias_kind":"pith_short_12","alias_value":"N5EMFOU6PROK","created_at":"2026-07-05T11:55:31.247020+00:00"},{"alias_kind":"pith_short_16","alias_value":"N5EMFOU6PROKT6KD","created_at":"2026-07-05T11:55:31.247020+00:00"},{"alias_kind":"pith_short_8","alias_value":"N5EMFOU6","created_at":"2026-07-05T11:55:31.247020+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/N5EMFOU6PROKT6KDAZ3FHDUSIF","json":"https://pith.science/pith/N5EMFOU6PROKT6KDAZ3FHDUSIF.json","graph_json":"https://pith.science/api/pith-number/N5EMFOU6PROKT6KDAZ3FHDUSIF/graph.json","events_json":"https://pith.science/api/pith-number/N5EMFOU6PROKT6KDAZ3FHDUSIF/events.json","paper":"https://pith.science/paper/N5EMFOU6"},"agent_actions":{"view_html":"https://pith.science/pith/N5EMFOU6PROKT6KDAZ3FHDUSIF","download_json":"https://pith.science/pith/N5EMFOU6PROKT6KDAZ3FHDUSIF.json","view_paper":"https://pith.science/paper/N5EMFOU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13037&json=true","fetch_graph":"https://pith.science/api/pith-number/N5EMFOU6PROKT6KDAZ3FHDUSIF/graph.json","fetch_events":"https://pith.science/api/pith-number/N5EMFOU6PROKT6KDAZ3FHDUSIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N5EMFOU6PROKT6KDAZ3FHDUSIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N5EMFOU6PROKT6KDAZ3FHDUSIF/action/storage_attestation","attest_author":"https://pith.science/pith/N5EMFOU6PROKT6KDAZ3FHDUSIF/action/author_attestation","sign_citation":"https://pith.science/pith/N5EMFOU6PROKT6KDAZ3FHDUSIF/action/citation_signature","submit_replication":"https://pith.science/pith/N5EMFOU6PROKT6KDAZ3FHDUSIF/action/replication_record"}},"created_at":"2026-07-05T11:55:31.247020+00:00","updated_at":"2026-07-05T11:55:31.247020+00:00"}