{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4J27JLYXRTUUA72VVEZRUGKQ3O","short_pith_number":"pith:4J27JLYX","schema_version":"1.0","canonical_sha256":"e275f4af178ce9407f55a9331a1950db84d30505f4dc63e737c6a3020efbc42a","source":{"kind":"arxiv","id":"2606.22429","version":1},"attestation_state":"computed","paper":{"title":"Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junshu Sun, Qingming Huang, Shuhui Wang, Wanxing Chang","submitted_at":"2026-06-21T10:40:33Z","abstract_excerpt":"Graph neural networks (GNNs) tightly couple their input-output parameters to dataset-specific feature spaces and target sets, exhibiting limited transferability across different datasets. In contrast, language models (LMs) generalize flexibly via a unified input-output interface, motivating recent attempts to adapt LMs to graph tasks. However, existing methods struggle to encode whole-graph information, leading to potential information loss and suboptimal graph understanding. In this work, we propose a novel weight-level information injection paradigm for adapting LMs to graph tasks. This para"},"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":"2606.22429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T10:40:33Z","cross_cats_sorted":[],"title_canon_sha256":"2cde713e317c00cee8d5d3f4c64d7163adbb921fc7483391e65d9b8dee1ea26c","abstract_canon_sha256":"90260ea47f435862b765452e22b03293ab95d88ff4d17d6d5aacad6f8fa432d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:38.237005Z","signature_b64":"OJlwg6l36l+dAiBwqZk8u15v3wbIZzKJ8Hnx9VhVcH4L3C8jnsvslj2mMg+X+mNR757gw+pvWs3fYI6oYS3TBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e275f4af178ce9407f55a9331a1950db84d30505f4dc63e737c6a3020efbc42a","last_reissued_at":"2026-06-23T02:13:38.236589Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:38.236589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junshu Sun, Qingming Huang, Shuhui Wang, Wanxing Chang","submitted_at":"2026-06-21T10:40:33Z","abstract_excerpt":"Graph neural networks (GNNs) tightly couple their input-output parameters to dataset-specific feature spaces and target sets, exhibiting limited transferability across different datasets. In contrast, language models (LMs) generalize flexibly via a unified input-output interface, motivating recent attempts to adapt LMs to graph tasks. However, existing methods struggle to encode whole-graph information, leading to potential information loss and suboptimal graph understanding. In this work, we propose a novel weight-level information injection paradigm for adapting LMs to graph tasks. This para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22429","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/2606.22429/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":"2606.22429","created_at":"2026-06-23T02:13:38.236652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22429v1","created_at":"2026-06-23T02:13:38.236652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22429","created_at":"2026-06-23T02:13:38.236652+00:00"},{"alias_kind":"pith_short_12","alias_value":"4J27JLYXRTUU","created_at":"2026-06-23T02:13:38.236652+00:00"},{"alias_kind":"pith_short_16","alias_value":"4J27JLYXRTUUA72V","created_at":"2026-06-23T02:13:38.236652+00:00"},{"alias_kind":"pith_short_8","alias_value":"4J27JLYX","created_at":"2026-06-23T02:13:38.236652+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/4J27JLYXRTUUA72VVEZRUGKQ3O","json":"https://pith.science/pith/4J27JLYXRTUUA72VVEZRUGKQ3O.json","graph_json":"https://pith.science/api/pith-number/4J27JLYXRTUUA72VVEZRUGKQ3O/graph.json","events_json":"https://pith.science/api/pith-number/4J27JLYXRTUUA72VVEZRUGKQ3O/events.json","paper":"https://pith.science/paper/4J27JLYX"},"agent_actions":{"view_html":"https://pith.science/pith/4J27JLYXRTUUA72VVEZRUGKQ3O","download_json":"https://pith.science/pith/4J27JLYXRTUUA72VVEZRUGKQ3O.json","view_paper":"https://pith.science/paper/4J27JLYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22429&json=true","fetch_graph":"https://pith.science/api/pith-number/4J27JLYXRTUUA72VVEZRUGKQ3O/graph.json","fetch_events":"https://pith.science/api/pith-number/4J27JLYXRTUUA72VVEZRUGKQ3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4J27JLYXRTUUA72VVEZRUGKQ3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4J27JLYXRTUUA72VVEZRUGKQ3O/action/storage_attestation","attest_author":"https://pith.science/pith/4J27JLYXRTUUA72VVEZRUGKQ3O/action/author_attestation","sign_citation":"https://pith.science/pith/4J27JLYXRTUUA72VVEZRUGKQ3O/action/citation_signature","submit_replication":"https://pith.science/pith/4J27JLYXRTUUA72VVEZRUGKQ3O/action/replication_record"}},"created_at":"2026-06-23T02:13:38.236652+00:00","updated_at":"2026-06-23T02:13:38.236652+00:00"}