{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O2X4DYO7RIMHUPCEEJKUJOM4NQ","short_pith_number":"pith:O2X4DYO7","schema_version":"1.0","canonical_sha256":"76afc1e1df8a187a3c44225544b99c6c35dfefa89671c52552ae509df98a7a46","source":{"kind":"arxiv","id":"2606.11583","version":1},"attestation_state":"computed","paper":{"title":"Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hanlin Gu, Lixin Fan, Yi Yang, Zhuoyi Peng","submitted_at":"2026-06-10T02:15:56Z","abstract_excerpt":"Text-attributed graphs (TAGs) underlie real-world applications such as citation networks, social media, and e-commerce. Few-shot graph learning on TAGs is hard: with only a handful of labels per class and the rest of the graph unannotated, neither GNNs nor LLMs can learn well on their own. GNNs read topology and fail on cold nodes; LLMs read text and fail on text-ambiguous nodes. Existing LLM-GNN methods all follow the same recipe: designate one model as the golden teacher and use its outputs (e.g., features or pseudo-labels) to supervise the other. We argue this golden-teacher assumption brea"},"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":"2606.11583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T02:15:56Z","cross_cats_sorted":[],"title_canon_sha256":"59e68e9593573e0d6f0647d6b1a6929b3cf9bc9f7cd2a2c22ce73d60bc496bf1","abstract_canon_sha256":"f67454e785716242f2efbeeba5995f0b6f5ee167a5c24be4462bf87347c9cff3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:57.479160Z","signature_b64":"cb14EfrRXLD/oyVRT3NlTIxVlyYohKk7iv/mjK5LVoangU4wYv3SQleewMh8toOrjEvUBPi0tIo+fsJ3pg0tDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76afc1e1df8a187a3c44225544b99c6c35dfefa89671c52552ae509df98a7a46","last_reissued_at":"2026-06-11T01:09:57.478324Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:57.478324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hanlin Gu, Lixin Fan, Yi Yang, Zhuoyi Peng","submitted_at":"2026-06-10T02:15:56Z","abstract_excerpt":"Text-attributed graphs (TAGs) underlie real-world applications such as citation networks, social media, and e-commerce. Few-shot graph learning on TAGs is hard: with only a handful of labels per class and the rest of the graph unannotated, neither GNNs nor LLMs can learn well on their own. GNNs read topology and fail on cold nodes; LLMs read text and fail on text-ambiguous nodes. Existing LLM-GNN methods all follow the same recipe: designate one model as the golden teacher and use its outputs (e.g., features or pseudo-labels) to supervise the other. We argue this golden-teacher assumption brea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11583","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/2606.11583/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":"2606.11583","created_at":"2026-06-11T01:09:57.478454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11583v1","created_at":"2026-06-11T01:09:57.478454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11583","created_at":"2026-06-11T01:09:57.478454+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2X4DYO7RIMH","created_at":"2026-06-11T01:09:57.478454+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2X4DYO7RIMHUPCE","created_at":"2026-06-11T01:09:57.478454+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2X4DYO7","created_at":"2026-06-11T01:09:57.478454+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/O2X4DYO7RIMHUPCEEJKUJOM4NQ","json":"https://pith.science/pith/O2X4DYO7RIMHUPCEEJKUJOM4NQ.json","graph_json":"https://pith.science/api/pith-number/O2X4DYO7RIMHUPCEEJKUJOM4NQ/graph.json","events_json":"https://pith.science/api/pith-number/O2X4DYO7RIMHUPCEEJKUJOM4NQ/events.json","paper":"https://pith.science/paper/O2X4DYO7"},"agent_actions":{"view_html":"https://pith.science/pith/O2X4DYO7RIMHUPCEEJKUJOM4NQ","download_json":"https://pith.science/pith/O2X4DYO7RIMHUPCEEJKUJOM4NQ.json","view_paper":"https://pith.science/paper/O2X4DYO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11583&json=true","fetch_graph":"https://pith.science/api/pith-number/O2X4DYO7RIMHUPCEEJKUJOM4NQ/graph.json","fetch_events":"https://pith.science/api/pith-number/O2X4DYO7RIMHUPCEEJKUJOM4NQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2X4DYO7RIMHUPCEEJKUJOM4NQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2X4DYO7RIMHUPCEEJKUJOM4NQ/action/storage_attestation","attest_author":"https://pith.science/pith/O2X4DYO7RIMHUPCEEJKUJOM4NQ/action/author_attestation","sign_citation":"https://pith.science/pith/O2X4DYO7RIMHUPCEEJKUJOM4NQ/action/citation_signature","submit_replication":"https://pith.science/pith/O2X4DYO7RIMHUPCEEJKUJOM4NQ/action/replication_record"}},"created_at":"2026-06-11T01:09:57.478454+00:00","updated_at":"2026-06-11T01:09:57.478454+00:00"}