{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2ENDFVPLOUDZSYPEDS44NK2PSI","short_pith_number":"pith:2ENDFVPL","schema_version":"1.0","canonical_sha256":"d11a32d5eb75079961e41cb9c6ab4f920b414234d12c0dd0330f97d5c93e6a56","source":{"kind":"arxiv","id":"2502.08092","version":2},"attestation_state":"computed","paper":{"title":"GCoT: Chain-of-Thought Prompt Learning for Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Zhou, Xingtong Yu, Xinming Zhang, Yuan Fang, Zhongwei Kuai","submitted_at":"2025-02-12T03:33:06Z","abstract_excerpt":"Chain-of-thought (CoT) prompting has achieved remarkable success in natural language processing (NLP). However, its vast potential remains largely unexplored for graphs. This raises an interesting question: How can we design CoT prompting for graphs to guide graph models to learn step by step? On one hand, unlike natural languages, graphs are non-linear and characterized by complex topological structures. On the other hand, many graphs lack textual data, making it difficult to formulate language-based CoT prompting. In this work, we propose the first CoT prompt learning framework for text-free"},"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":"2502.08092","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T03:33:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73bfc95c4965c37d6768e07d95aca24f77a817c6c27f9a861279cb284a1c5e3b","abstract_canon_sha256":"e6543f47f02df28f31521a46c8b9503102a5abf8d5f854fca7e88fbad0a841ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:03.698017Z","signature_b64":"S5GbTsvkzd3BQfrhK5XS2/dF0iftm/x9A8j52JM8Y+FoiYfgUTxCiblBKPylHb80xhiis4ftZWjjanrYQC5vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d11a32d5eb75079961e41cb9c6ab4f920b414234d12c0dd0330f97d5c93e6a56","last_reissued_at":"2026-07-05T11:14:03.697473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:03.697473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GCoT: Chain-of-Thought Prompt Learning for Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Zhou, Xingtong Yu, Xinming Zhang, Yuan Fang, Zhongwei Kuai","submitted_at":"2025-02-12T03:33:06Z","abstract_excerpt":"Chain-of-thought (CoT) prompting has achieved remarkable success in natural language processing (NLP). However, its vast potential remains largely unexplored for graphs. This raises an interesting question: How can we design CoT prompting for graphs to guide graph models to learn step by step? On one hand, unlike natural languages, graphs are non-linear and characterized by complex topological structures. On the other hand, many graphs lack textual data, making it difficult to formulate language-based CoT prompting. In this work, we propose the first CoT prompt learning framework for text-free"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08092","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/2502.08092/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":"2502.08092","created_at":"2026-07-05T11:14:03.697535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08092v2","created_at":"2026-07-05T11:14:03.697535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08092","created_at":"2026-07-05T11:14:03.697535+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ENDFVPLOUDZ","created_at":"2026-07-05T11:14:03.697535+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ENDFVPLOUDZSYPE","created_at":"2026-07-05T11:14:03.697535+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ENDFVPL","created_at":"2026-07-05T11:14:03.697535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.04244","citing_title":"GraphVec: Cross-Domain Graph Vectorization for Graph-Level Representation Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07357","citing_title":"GraphReAct: Reasoning and Acting for Multi-step Graph Inference","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07357","citing_title":"GraphReAct: Reasoning and Acting for Multi-step Graph Inference","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ENDFVPLOUDZSYPEDS44NK2PSI","json":"https://pith.science/pith/2ENDFVPLOUDZSYPEDS44NK2PSI.json","graph_json":"https://pith.science/api/pith-number/2ENDFVPLOUDZSYPEDS44NK2PSI/graph.json","events_json":"https://pith.science/api/pith-number/2ENDFVPLOUDZSYPEDS44NK2PSI/events.json","paper":"https://pith.science/paper/2ENDFVPL"},"agent_actions":{"view_html":"https://pith.science/pith/2ENDFVPLOUDZSYPEDS44NK2PSI","download_json":"https://pith.science/pith/2ENDFVPLOUDZSYPEDS44NK2PSI.json","view_paper":"https://pith.science/paper/2ENDFVPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08092&json=true","fetch_graph":"https://pith.science/api/pith-number/2ENDFVPLOUDZSYPEDS44NK2PSI/graph.json","fetch_events":"https://pith.science/api/pith-number/2ENDFVPLOUDZSYPEDS44NK2PSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ENDFVPLOUDZSYPEDS44NK2PSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ENDFVPLOUDZSYPEDS44NK2PSI/action/storage_attestation","attest_author":"https://pith.science/pith/2ENDFVPLOUDZSYPEDS44NK2PSI/action/author_attestation","sign_citation":"https://pith.science/pith/2ENDFVPLOUDZSYPEDS44NK2PSI/action/citation_signature","submit_replication":"https://pith.science/pith/2ENDFVPLOUDZSYPEDS44NK2PSI/action/replication_record"}},"created_at":"2026-07-05T11:14:03.697535+00:00","updated_at":"2026-07-05T11:14:03.697535+00:00"}