{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7JGLV3TJM5ESLK75BHL7BS4O3R","short_pith_number":"pith:7JGLV3TJ","schema_version":"1.0","canonical_sha256":"fa4cbaee69674925abfd09d7f0cb8edc58d5d649b2a8a8f20e6dfd0f3c9c9eab","source":{"kind":"arxiv","id":"2305.12268","version":1},"attestation_state":"computed","paper":{"title":"Patton: Language Model Pretraining on Text-Rich Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Jin, Jiawei Han, Qi Zhu, Wentao Zhang, Xinyang Zhang, Yu Meng, Yu Zhang","submitted_at":"2023-05-20T19:17:10Z","abstract_excerpt":"A real-world text corpus sometimes comprises not only text documents but also semantic links between them (e.g., academic papers in a bibliographic network are linked by citations and co-authorships). Text documents and semantic connections form a text-rich network, which empowers a wide range of downstream tasks such as classification and retrieval. However, pretraining methods for such structures are still lacking, making it difficult to build one generic model that can be adapted to various tasks on text-rich networks. Current pretraining objectives, such as masked language modeling, purely"},"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":"2305.12268","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T19:17:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"badf704ace838d4ef2be7d072ee06b66898f7f440853264be37c0756f25145d5","abstract_canon_sha256":"c014ed53c9c30659322a5aca5af10b34762b2b34fb274a3d16f52ec5f285dec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:08.636477Z","signature_b64":"fuDT+rEdYChivfGy0a9fO8qu/g6XSiOopgyYQwhkYTi9VxwNdmdLTUc5yoKKqccExJOHgH5FdJwvOF53bB4bBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa4cbaee69674925abfd09d7f0cb8edc58d5d649b2a8a8f20e6dfd0f3c9c9eab","last_reissued_at":"2026-07-05T06:12:08.636016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:08.636016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Patton: Language Model Pretraining on Text-Rich Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Jin, Jiawei Han, Qi Zhu, Wentao Zhang, Xinyang Zhang, Yu Meng, Yu Zhang","submitted_at":"2023-05-20T19:17:10Z","abstract_excerpt":"A real-world text corpus sometimes comprises not only text documents but also semantic links between them (e.g., academic papers in a bibliographic network are linked by citations and co-authorships). Text documents and semantic connections form a text-rich network, which empowers a wide range of downstream tasks such as classification and retrieval. However, pretraining methods for such structures are still lacking, making it difficult to build one generic model that can be adapted to various tasks on text-rich networks. Current pretraining objectives, such as masked language modeling, purely"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12268","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/2305.12268/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":"2305.12268","created_at":"2026-07-05T06:12:08.636079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12268v1","created_at":"2026-07-05T06:12:08.636079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12268","created_at":"2026-07-05T06:12:08.636079+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JGLV3TJM5ES","created_at":"2026-07-05T06:12:08.636079+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JGLV3TJM5ESLK75","created_at":"2026-07-05T06:12:08.636079+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JGLV3TJ","created_at":"2026-07-05T06:12:08.636079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30247","citing_title":"OOD-GraphLLM: Graph Large Language Model for Out-of-Distribution Generalized Drug Synergy Prediction","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01410","citing_title":"GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JGLV3TJM5ESLK75BHL7BS4O3R","json":"https://pith.science/pith/7JGLV3TJM5ESLK75BHL7BS4O3R.json","graph_json":"https://pith.science/api/pith-number/7JGLV3TJM5ESLK75BHL7BS4O3R/graph.json","events_json":"https://pith.science/api/pith-number/7JGLV3TJM5ESLK75BHL7BS4O3R/events.json","paper":"https://pith.science/paper/7JGLV3TJ"},"agent_actions":{"view_html":"https://pith.science/pith/7JGLV3TJM5ESLK75BHL7BS4O3R","download_json":"https://pith.science/pith/7JGLV3TJM5ESLK75BHL7BS4O3R.json","view_paper":"https://pith.science/paper/7JGLV3TJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12268&json=true","fetch_graph":"https://pith.science/api/pith-number/7JGLV3TJM5ESLK75BHL7BS4O3R/graph.json","fetch_events":"https://pith.science/api/pith-number/7JGLV3TJM5ESLK75BHL7BS4O3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JGLV3TJM5ESLK75BHL7BS4O3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JGLV3TJM5ESLK75BHL7BS4O3R/action/storage_attestation","attest_author":"https://pith.science/pith/7JGLV3TJM5ESLK75BHL7BS4O3R/action/author_attestation","sign_citation":"https://pith.science/pith/7JGLV3TJM5ESLK75BHL7BS4O3R/action/citation_signature","submit_replication":"https://pith.science/pith/7JGLV3TJM5ESLK75BHL7BS4O3R/action/replication_record"}},"created_at":"2026-07-05T06:12:08.636079+00:00","updated_at":"2026-07-05T06:12:08.636079+00:00"}