{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KFCC6XREQHWTKOE26RYXBFLOAB","short_pith_number":"pith:KFCC6XRE","schema_version":"1.0","canonical_sha256":"51442f5e2481ed35389af47170956e0041093690eefdb4784b6854db0c66ca1c","source":{"kind":"arxiv","id":"2505.06321","version":2},"attestation_state":"computed","paper":{"title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changwen Zheng, Chenhao Zhang, Fengge Wu, Hang Gao, Huaping Liu, Junsuo Zhao, Tie Wang","submitted_at":"2025-05-09T02:51:22Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success across various domains. However, they still face significant challenges, including high computational costs for training and limitations in solving complex reasoning problems. Although existing methods have extended the reasoning capabilities of LLMs through structured paradigms, these approaches often rely on task-specific prompts and predefined reasoning processes, which constrain their flexibility and generalizability. To address these limitations, we propose a novel framework that leverages graph learning to enable more flexible"},"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":"2505.06321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T02:51:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b23999ed8edf0c66d6fa59f82da32eb805695fda70c832c1f27884e4e14974a9","abstract_canon_sha256":"9c797d76f92e614fda483894fc0d10a3388ac32ec88635ca77b329863a2207d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:22.271250Z","signature_b64":"76RCCGW+uavnOF7RKq6JAZmzydkxdMVqVZroT4MrvdGuYenfxU8g7it5YJttveR+NvYUmJUlz6JWp1nPuszvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51442f5e2481ed35389af47170956e0041093690eefdb4784b6854db0c66ca1c","last_reissued_at":"2026-07-05T11:04:22.270730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:22.270730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changwen Zheng, Chenhao Zhang, Fengge Wu, Hang Gao, Huaping Liu, Junsuo Zhao, Tie Wang","submitted_at":"2025-05-09T02:51:22Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success across various domains. However, they still face significant challenges, including high computational costs for training and limitations in solving complex reasoning problems. Although existing methods have extended the reasoning capabilities of LLMs through structured paradigms, these approaches often rely on task-specific prompts and predefined reasoning processes, which constrain their flexibility and generalizability. To address these limitations, we propose a novel framework that leverages graph learning to enable more flexible"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06321","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/2505.06321/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":"2505.06321","created_at":"2026-07-05T11:04:22.270798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06321v2","created_at":"2026-07-05T11:04:22.270798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06321","created_at":"2026-07-05T11:04:22.270798+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFCC6XREQHWT","created_at":"2026-07-05T11:04:22.270798+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFCC6XREQHWTKOE2","created_at":"2026-07-05T11:04:22.270798+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFCC6XRE","created_at":"2026-07-05T11:04:22.270798+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/KFCC6XREQHWTKOE26RYXBFLOAB","json":"https://pith.science/pith/KFCC6XREQHWTKOE26RYXBFLOAB.json","graph_json":"https://pith.science/api/pith-number/KFCC6XREQHWTKOE26RYXBFLOAB/graph.json","events_json":"https://pith.science/api/pith-number/KFCC6XREQHWTKOE26RYXBFLOAB/events.json","paper":"https://pith.science/paper/KFCC6XRE"},"agent_actions":{"view_html":"https://pith.science/pith/KFCC6XREQHWTKOE26RYXBFLOAB","download_json":"https://pith.science/pith/KFCC6XREQHWTKOE26RYXBFLOAB.json","view_paper":"https://pith.science/paper/KFCC6XRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06321&json=true","fetch_graph":"https://pith.science/api/pith-number/KFCC6XREQHWTKOE26RYXBFLOAB/graph.json","fetch_events":"https://pith.science/api/pith-number/KFCC6XREQHWTKOE26RYXBFLOAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFCC6XREQHWTKOE26RYXBFLOAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFCC6XREQHWTKOE26RYXBFLOAB/action/storage_attestation","attest_author":"https://pith.science/pith/KFCC6XREQHWTKOE26RYXBFLOAB/action/author_attestation","sign_citation":"https://pith.science/pith/KFCC6XREQHWTKOE26RYXBFLOAB/action/citation_signature","submit_replication":"https://pith.science/pith/KFCC6XREQHWTKOE26RYXBFLOAB/action/replication_record"}},"created_at":"2026-07-05T11:04:22.270798+00:00","updated_at":"2026-07-05T11:04:22.270798+00:00"}