{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DMJRNC7SWWVUC3SZ3QCODECGLW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0f954bf1d626b921d06282558907b697861d4e537b8b2967da4388812e028bab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-13T06:29:25Z","title_canon_sha256":"d4af35edf78c869cb4f4250e2e48f44092dec50c2c30ba7fb3250e07ac5841db"},"schema_version":"1.0","source":{"id":"2505.08265","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08265","created_at":"2026-07-05T11:19:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08265v3","created_at":"2026-07-05T11:19:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08265","created_at":"2026-07-05T11:19:26Z"},{"alias_kind":"pith_short_12","alias_value":"DMJRNC7SWWVU","created_at":"2026-07-05T11:19:26Z"},{"alias_kind":"pith_short_16","alias_value":"DMJRNC7SWWVUC3SZ","created_at":"2026-07-05T11:19:26Z"},{"alias_kind":"pith_short_8","alias_value":"DMJRNC7S","created_at":"2026-07-05T11:19:26Z"}],"graph_snapshots":[{"event_id":"sha256:e2699f0eb0ce3454a70c46dc1d8fee3c471f4b6fc136b485114c4158d4d4934a","target":"graph","created_at":"2026-07-05T11:19:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.08265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of large language models (LLMs) as feature enhancers to optimize node representations, which are then used as inputs for graph neural networks (GNNs), has shown significant potential in graph representation learning. However, the fundamental properties of this approach remain underexplored. To address this issue, we propose conducting a more in-depth analysis of this issue based on the interchange intervention method. First, we construct a synthetic graph dataset with controllable causal relationships, enabling precise manipulation of semantic relationships and causal modeling to provi","authors_text":"Changwen Zheng, Fengge Wu, Hang Gao, Huaping Liu, Junsuo Zhao, Wenxuan Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-13T06:29:25Z","title":"LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08265","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:53a66cb04c96d7d4f7f24a9df861f538dbcc402d17a3af14b2639405130dfa45","target":"record","created_at":"2026-07-05T11:19:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0f954bf1d626b921d06282558907b697861d4e537b8b2967da4388812e028bab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-13T06:29:25Z","title_canon_sha256":"d4af35edf78c869cb4f4250e2e48f44092dec50c2c30ba7fb3250e07ac5841db"},"schema_version":"1.0","source":{"id":"2505.08265","kind":"arxiv","version":3}},"canonical_sha256":"1b13168bf2b5ab416e59dc04e190465d937daa904880e7ff402dc7533b5a7c29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b13168bf2b5ab416e59dc04e190465d937daa904880e7ff402dc7533b5a7c29","first_computed_at":"2026-07-05T11:19:26.890674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:26.890674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QORvl5E/NutdL0XBPH/76+7lGpYdm+PFfwYfrrTA/KMMCx+lrnBhQGj6eSxF+k7MR/L7hKOao4z5mgcM1fG/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:26.891189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08265","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53a66cb04c96d7d4f7f24a9df861f538dbcc402d17a3af14b2639405130dfa45","sha256:e2699f0eb0ce3454a70c46dc1d8fee3c471f4b6fc136b485114c4158d4d4934a"],"state_sha256":"911d752e4cb57d1188057909df1d21441a8ebda761120cfc7e5f619ca2517a1c"}