{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HA5K5HPTMYEEAFDIZBKKALV7F4","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":"d05e9eb9fe329254b893cce32940cbd0d20317f4d008e6fb94cd1d9cef40df93","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T19:45:21Z","title_canon_sha256":"fa4eac1152efb3ccb6db7d9225663b9e6cbc0d84dff300dc07a62d0736fb1bf6"},"schema_version":"1.0","source":{"id":"2406.12052","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12052","created_at":"2026-07-05T09:53:02Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12052v2","created_at":"2026-07-05T09:53:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12052","created_at":"2026-07-05T09:53:02Z"},{"alias_kind":"pith_short_12","alias_value":"HA5K5HPTMYEE","created_at":"2026-07-05T09:53:02Z"},{"alias_kind":"pith_short_16","alias_value":"HA5K5HPTMYEEAFDI","created_at":"2026-07-05T09:53:02Z"},{"alias_kind":"pith_short_8","alias_value":"HA5K5HPT","created_at":"2026-07-05T09:53:02Z"}],"graph_snapshots":[{"event_id":"sha256:d8553a06929cbcce414b371021d494c9b250ac0ca15e25d05f3d5b64ca8931ef","target":"graph","created_at":"2026-07-05T09:53:02Z","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/2406.12052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representation learning on text-attributed graphs (TAGs), where nodes are represented by textual descriptions, is crucial for textual and relational knowledge systems and recommendation systems. Currently, state-of-the-art embedding methods for TAGs primarily focus on fine-tuning language models (e.g., BERT) using structure-aware training signals. While effective, these methods are tailored for individual TAG and cannot generalize across various graph scenarios. Given the shared textual space, leveraging multiple TAGs for joint fine-tuning, aligning text and graph structure from different aspe","authors_text":"Dongzhe Fan, Ninghao Liu, Qiaoyu Tan, Sirui Ding, Yi Fang","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T19:45:21Z","title":"UniGLM: Training One Unified Language Model for Text-Attributed Graph Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12052","kind":"arxiv","version":2},"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":"sha256:3f1d562a103cbead11eb7b9bad42c4dd429b87ebb8d38cc6e5eacccfa9e9bc10","target":"record","created_at":"2026-07-05T09:53:02Z","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":"d05e9eb9fe329254b893cce32940cbd0d20317f4d008e6fb94cd1d9cef40df93","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T19:45:21Z","title_canon_sha256":"fa4eac1152efb3ccb6db7d9225663b9e6cbc0d84dff300dc07a62d0736fb1bf6"},"schema_version":"1.0","source":{"id":"2406.12052","kind":"arxiv","version":2}},"canonical_sha256":"383aae9df36608401468c854a02ebf2f3313d1344acbb931b7f81ca7c8726853","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"383aae9df36608401468c854a02ebf2f3313d1344acbb931b7f81ca7c8726853","first_computed_at":"2026-07-05T09:53:02.010738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:02.010738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qQclfIn8OmSt7HA0qfroGHOkBXT4zx+K46YUkTRJEdochYEWWdNUhBoexanYKi8aMkvNVtGgD6vMXNn7bV9hAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:02.011146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12052","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f1d562a103cbead11eb7b9bad42c4dd429b87ebb8d38cc6e5eacccfa9e9bc10","sha256:d8553a06929cbcce414b371021d494c9b250ac0ca15e25d05f3d5b64ca8931ef"],"state_sha256":"af965233829875d3e6b1f6cd121cdc81a8390f10452e080236193dafb07d9eab"}