{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6DBNBFRVBHJK355EVZMWDOCFDJ","short_pith_number":"pith:6DBNBFRV","schema_version":"1.0","canonical_sha256":"f0c2d0963509d2adf7a4ae5961b8451a4766ee73df0bf99a6059809e74ee90f8","source":{"kind":"arxiv","id":"2407.15431","version":1},"attestation_state":"computed","paper":{"title":"Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SI","authors_text":"Beining Yang, Chenhui Zhang, Evgeny Kharlamov, Huanjing Zhao, Jie Tang, Junyu Ren, Shu Zhao, Yukuo Cen, Yuxiao Dong","submitted_at":"2024-07-22T07:24:21Z","abstract_excerpt":"The text-attributed graph (TAG) is one kind of important real-world graph-structured data with each node associated with raw texts. For TAGs, traditional few-shot node classification methods directly conduct training on the pre-processed node features and do not consider the raw texts. The performance is highly dependent on the choice of the feature pre-processing method. In this paper, we propose P2TAG, a framework designed for few-shot node classification on TAGs with graph pre-training and prompting. P2TAG first pre-trains the language model (LM) and graph neural network (GNN) on TAGs with "},"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":"2407.15431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2024-07-22T07:24:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"05dcb940e90208eecb739ecfd58d676b4707b27b85df9e40eabbaa9beec0c8d8","abstract_canon_sha256":"c6b5521a5dd0327a3adce4a808d2ed43cda9a3e0a581028686038d37e809eb6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:43.776066Z","signature_b64":"5CaEL4svJ+EFJxy9/CSOqbaHVPf3UM4WK8cWWW+kZE7Y33/kxWHoaIJ5+Y61ZCgQvPkGMwWzMAsTuqq8FmZ3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0c2d0963509d2adf7a4ae5961b8451a4766ee73df0bf99a6059809e74ee90f8","last_reissued_at":"2026-07-05T08:46:43.775597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:43.775597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SI","authors_text":"Beining Yang, Chenhui Zhang, Evgeny Kharlamov, Huanjing Zhao, Jie Tang, Junyu Ren, Shu Zhao, Yukuo Cen, Yuxiao Dong","submitted_at":"2024-07-22T07:24:21Z","abstract_excerpt":"The text-attributed graph (TAG) is one kind of important real-world graph-structured data with each node associated with raw texts. For TAGs, traditional few-shot node classification methods directly conduct training on the pre-processed node features and do not consider the raw texts. The performance is highly dependent on the choice of the feature pre-processing method. In this paper, we propose P2TAG, a framework designed for few-shot node classification on TAGs with graph pre-training and prompting. P2TAG first pre-trains the language model (LM) and graph neural network (GNN) on TAGs with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15431","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/2407.15431/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":"2407.15431","created_at":"2026-07-05T08:46:43.775652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15431v1","created_at":"2026-07-05T08:46:43.775652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15431","created_at":"2026-07-05T08:46:43.775652+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DBNBFRVBHJK","created_at":"2026-07-05T08:46:43.775652+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DBNBFRVBHJK355E","created_at":"2026-07-05T08:46:43.775652+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DBNBFRV","created_at":"2026-07-05T08:46:43.775652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.08168","citing_title":"Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DBNBFRVBHJK355EVZMWDOCFDJ","json":"https://pith.science/pith/6DBNBFRVBHJK355EVZMWDOCFDJ.json","graph_json":"https://pith.science/api/pith-number/6DBNBFRVBHJK355EVZMWDOCFDJ/graph.json","events_json":"https://pith.science/api/pith-number/6DBNBFRVBHJK355EVZMWDOCFDJ/events.json","paper":"https://pith.science/paper/6DBNBFRV"},"agent_actions":{"view_html":"https://pith.science/pith/6DBNBFRVBHJK355EVZMWDOCFDJ","download_json":"https://pith.science/pith/6DBNBFRVBHJK355EVZMWDOCFDJ.json","view_paper":"https://pith.science/paper/6DBNBFRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15431&json=true","fetch_graph":"https://pith.science/api/pith-number/6DBNBFRVBHJK355EVZMWDOCFDJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6DBNBFRVBHJK355EVZMWDOCFDJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DBNBFRVBHJK355EVZMWDOCFDJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DBNBFRVBHJK355EVZMWDOCFDJ/action/storage_attestation","attest_author":"https://pith.science/pith/6DBNBFRVBHJK355EVZMWDOCFDJ/action/author_attestation","sign_citation":"https://pith.science/pith/6DBNBFRVBHJK355EVZMWDOCFDJ/action/citation_signature","submit_replication":"https://pith.science/pith/6DBNBFRVBHJK355EVZMWDOCFDJ/action/replication_record"}},"created_at":"2026-07-05T08:46:43.775652+00:00","updated_at":"2026-07-05T08:46:43.775652+00:00"}