{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z63FTWDVWIYBYT5SKVEITXX7PJ","short_pith_number":"pith:Z63FTWDV","schema_version":"1.0","canonical_sha256":"cfb659d875b2301c4fb2554889deff7a41d4ee3805f49c42fda66e8072fe21d6","source":{"kind":"arxiv","id":"2305.14321","version":2},"attestation_state":"computed","paper":{"title":"ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brandon Roy, Deb Roy, Hang Jiang, Jad Kabbara, Suyash Fulay, William Brannon, Wonjune Kang","submitted_at":"2023-05-23T17:53:30Z","abstract_excerpt":"Learning on text-attributed graphs (TAGs), in which nodes are associated with one or more texts, has been the subject of much recent work. However, most approaches tend to make strong assumptions about the downstream task of interest, are reliant on hand-labeled data, or fail to equally balance the importance of both text and graph representations. In this work, we propose Contrastive Graph-Text pretraining (ConGraT), a general, self-supervised approach for jointly learning separate representations of texts and nodes in a TAG. Our method trains a language model (LM) and a graph neural network "},"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":"2305.14321","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:53:30Z","cross_cats_sorted":[],"title_canon_sha256":"0fa45537a108c38fd33813e6cf2ebe9fba98c01d961771acbb4cb9fe7a171ea0","abstract_canon_sha256":"d6d422c0c53ea77a3fcc01e0b92541df9487f2f76b4aca1296b6631fe8d87fc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:59.028915Z","signature_b64":"V7cfzw+E7iTfmNh3ew24Xrnh8N5UwpN8h0/i8B8fpV4OQIYuQIi2ftfJNfthdPtBIB90DLl+u5TRX/vAuVF3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb659d875b2301c4fb2554889deff7a41d4ee3805f49c42fda66e8072fe21d6","last_reissued_at":"2026-07-05T08:41:59.028125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:59.028125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brandon Roy, Deb Roy, Hang Jiang, Jad Kabbara, Suyash Fulay, William Brannon, Wonjune Kang","submitted_at":"2023-05-23T17:53:30Z","abstract_excerpt":"Learning on text-attributed graphs (TAGs), in which nodes are associated with one or more texts, has been the subject of much recent work. However, most approaches tend to make strong assumptions about the downstream task of interest, are reliant on hand-labeled data, or fail to equally balance the importance of both text and graph representations. In this work, we propose Contrastive Graph-Text pretraining (ConGraT), a general, self-supervised approach for jointly learning separate representations of texts and nodes in a TAG. Our method trains a language model (LM) and a graph neural network "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14321","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/2305.14321/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":"2305.14321","created_at":"2026-07-05T08:41:59.028180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14321v2","created_at":"2026-07-05T08:41:59.028180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14321","created_at":"2026-07-05T08:41:59.028180+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z63FTWDVWIYB","created_at":"2026-07-05T08:41:59.028180+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z63FTWDVWIYBYT5S","created_at":"2026-07-05T08:41:59.028180+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z63FTWDV","created_at":"2026-07-05T08:41:59.028180+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.05779","citing_title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z63FTWDVWIYBYT5SKVEITXX7PJ","json":"https://pith.science/pith/Z63FTWDVWIYBYT5SKVEITXX7PJ.json","graph_json":"https://pith.science/api/pith-number/Z63FTWDVWIYBYT5SKVEITXX7PJ/graph.json","events_json":"https://pith.science/api/pith-number/Z63FTWDVWIYBYT5SKVEITXX7PJ/events.json","paper":"https://pith.science/paper/Z63FTWDV"},"agent_actions":{"view_html":"https://pith.science/pith/Z63FTWDVWIYBYT5SKVEITXX7PJ","download_json":"https://pith.science/pith/Z63FTWDVWIYBYT5SKVEITXX7PJ.json","view_paper":"https://pith.science/paper/Z63FTWDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14321&json=true","fetch_graph":"https://pith.science/api/pith-number/Z63FTWDVWIYBYT5SKVEITXX7PJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z63FTWDVWIYBYT5SKVEITXX7PJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z63FTWDVWIYBYT5SKVEITXX7PJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z63FTWDVWIYBYT5SKVEITXX7PJ/action/storage_attestation","attest_author":"https://pith.science/pith/Z63FTWDVWIYBYT5SKVEITXX7PJ/action/author_attestation","sign_citation":"https://pith.science/pith/Z63FTWDVWIYBYT5SKVEITXX7PJ/action/citation_signature","submit_replication":"https://pith.science/pith/Z63FTWDVWIYBYT5SKVEITXX7PJ/action/replication_record"}},"created_at":"2026-07-05T08:41:59.028180+00:00","updated_at":"2026-07-05T08:41:59.028180+00:00"}