{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K7VJJ7LB243KXD4MQ5CIMKFDNT","short_pith_number":"pith:K7VJJ7LB","schema_version":"1.0","canonical_sha256":"57ea94fd61d736ab8f8c87448628a36cf37656c6a145810d27e7a5fc0fd008bc","source":{"kind":"arxiv","id":"2606.01873","version":1},"attestation_state":"computed","paper":{"title":"G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianxin Li, Mufan Zhao, Ruijie Wang, Wenbo Zhang, Yibo Ding, Yuhan Wang, Yutong Ye","submitted_at":"2026-06-01T08:19:47Z","abstract_excerpt":"LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning. While effective on individual downstream tasks, we observe severe catastrophic forgetting when such models are sequentially fine-tuned on streaming tasks. Although parameter-efficient fine-tuning alleviates forgetting to some extent, it remains insufficient to resolve task interference and ineffective knowledge transfer. In this work, we study graph continual learning for LLM-as-Aligner models on "},"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":"2606.01873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T08:19:47Z","cross_cats_sorted":[],"title_canon_sha256":"4da4bf86f65e379e1532fd19f53871d920a35aff41e2ad44f4885303c76ef57d","abstract_canon_sha256":"c0b3ea85abea9da9473a04afb36c7a8c5b50dc25ee90effaf5e3fd3ccb8e7943"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:59.232234Z","signature_b64":"GIt07srwcLRfins3KI3i0RKFfd9T554eJTpxP3y+f0rOB8bYOXuq2jjwJ0Bt3Okb2XOXeO7i2MNaLipVbDCtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57ea94fd61d736ab8f8c87448628a36cf37656c6a145810d27e7a5fc0fd008bc","last_reissued_at":"2026-06-02T02:04:59.231832Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:59.231832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianxin Li, Mufan Zhao, Ruijie Wang, Wenbo Zhang, Yibo Ding, Yuhan Wang, Yutong Ye","submitted_at":"2026-06-01T08:19:47Z","abstract_excerpt":"LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning. While effective on individual downstream tasks, we observe severe catastrophic forgetting when such models are sequentially fine-tuned on streaming tasks. Although parameter-efficient fine-tuning alleviates forgetting to some extent, it remains insufficient to resolve task interference and ineffective knowledge transfer. In this work, we study graph continual learning for LLM-as-Aligner models on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01873","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/2606.01873/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":"2606.01873","created_at":"2026-06-02T02:04:59.231897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01873v1","created_at":"2026-06-02T02:04:59.231897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01873","created_at":"2026-06-02T02:04:59.231897+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7VJJ7LB243K","created_at":"2026-06-02T02:04:59.231897+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7VJJ7LB243KXD4M","created_at":"2026-06-02T02:04:59.231897+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7VJJ7LB","created_at":"2026-06-02T02:04:59.231897+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/K7VJJ7LB243KXD4MQ5CIMKFDNT","json":"https://pith.science/pith/K7VJJ7LB243KXD4MQ5CIMKFDNT.json","graph_json":"https://pith.science/api/pith-number/K7VJJ7LB243KXD4MQ5CIMKFDNT/graph.json","events_json":"https://pith.science/api/pith-number/K7VJJ7LB243KXD4MQ5CIMKFDNT/events.json","paper":"https://pith.science/paper/K7VJJ7LB"},"agent_actions":{"view_html":"https://pith.science/pith/K7VJJ7LB243KXD4MQ5CIMKFDNT","download_json":"https://pith.science/pith/K7VJJ7LB243KXD4MQ5CIMKFDNT.json","view_paper":"https://pith.science/paper/K7VJJ7LB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01873&json=true","fetch_graph":"https://pith.science/api/pith-number/K7VJJ7LB243KXD4MQ5CIMKFDNT/graph.json","fetch_events":"https://pith.science/api/pith-number/K7VJJ7LB243KXD4MQ5CIMKFDNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7VJJ7LB243KXD4MQ5CIMKFDNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7VJJ7LB243KXD4MQ5CIMKFDNT/action/storage_attestation","attest_author":"https://pith.science/pith/K7VJJ7LB243KXD4MQ5CIMKFDNT/action/author_attestation","sign_citation":"https://pith.science/pith/K7VJJ7LB243KXD4MQ5CIMKFDNT/action/citation_signature","submit_replication":"https://pith.science/pith/K7VJJ7LB243KXD4MQ5CIMKFDNT/action/replication_record"}},"created_at":"2026-06-02T02:04:59.231897+00:00","updated_at":"2026-06-02T02:04:59.231897+00:00"}