{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LMUYR4GTOJBPK7UKQXUBSDQ23M","short_pith_number":"pith:LMUYR4GT","canonical_record":{"source":{"id":"2306.02592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T04:46:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ee554db43bfddaf36a88237317092db4ff3650470e251affcb2202cc2d4d4652","abstract_canon_sha256":"b942cb4ab9018b2b263ae089572ac9548098a5316bb1e1f7328c37bbdd3c1e34"},"schema_version":"1.0"},"canonical_sha256":"5b2988f0d37242f57e8a85e8190e1adb0237d17b19f6dd0a42383e85ade60d4d","source":{"kind":"arxiv","id":"2306.02592","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02592","created_at":"2026-07-05T06:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02592v1","created_at":"2026-07-05T06:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02592","created_at":"2026-07-05T06:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"LMUYR4GTOJBP","created_at":"2026-07-05T06:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"LMUYR4GTOJBPK7UK","created_at":"2026-07-05T06:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"LMUYR4GT","created_at":"2026-07-05T06:17:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LMUYR4GTOJBPK7UKQXUBSDQ23M","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T04:46:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ee554db43bfddaf36a88237317092db4ff3650470e251affcb2202cc2d4d4652","abstract_canon_sha256":"b942cb4ab9018b2b263ae089572ac9548098a5316bb1e1f7328c37bbdd3c1e34"},"schema_version":"1.0"},"canonical_sha256":"5b2988f0d37242f57e8a85e8190e1adb0237d17b19f6dd0a42383e85ade60d4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:19.134577Z","signature_b64":"eyyY3901GOL+aBdaNe1nmk615UUSsfERPosnmNv2ySxdBty2gKJkGJZiLSP3thPjHeza8uwdTNqcUtZ1utozAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b2988f0d37242f57e8a85e8190e1adb0237d17b19f6dd0a42383e85ade60d4d","last_reissued_at":"2026-07-05T06:17:19.134087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:19.134087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02592","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Nl3/jimuA9jp6mscyK6Q10EwW/nxSOeLsuBBYvvzUCDnp8rlrfTKydWGYqsutnVTsgEAd+emqtRsQ4jl8LtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:05:50.056000Z"},"content_sha256":"b87418ac81c4b558cbabd31c33477102815805980d166acdb7decb9ca9d62009","schema_version":"1.0","event_id":"sha256:b87418ac81c4b558cbabd31c33477102815805980d166acdb7decb9ca9d62009"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LMUYR4GTOJBPK7UKQXUBSDQ23M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Belinda Zeng, Carl Yang, Da Zheng, Han Xie, Houyu Zhang, Jun Ma, Qing Ping, Sheng Wang, Trishul Chilimbi, Vassilis N. Ioannidis, Xiang Song, Yi Xu","submitted_at":"2023-06-05T04:46:44Z","abstract_excerpt":"Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the hope of benefiting downstream graph applications, which has also been explored by several recent studies. However, no existing study has ever investigated the pre-training of text plus graph models on large heterogeneous graphs with abundant textual information (a.k.a. large graph corpora) and then fine-tuning the model on different related downstream applic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02592","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/2306.02592/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b8a6B5wfVUdZlmncrR5GOvlrKLSeWZr1Wjeli9EPsHGJeLOqh1nA57ZWAdBwN1Vea9637CW4OROrlOof/G40Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:05:50.056604Z"},"content_sha256":"acea481d55607f63630e7684f49070f381d46543c2a9dbedeff7f5394562145c","schema_version":"1.0","event_id":"sha256:acea481d55607f63630e7684f49070f381d46543c2a9dbedeff7f5394562145c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LMUYR4GTOJBPK7UKQXUBSDQ23M/bundle.json","state_url":"https://pith.science/pith/LMUYR4GTOJBPK7UKQXUBSDQ23M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LMUYR4GTOJBPK7UKQXUBSDQ23M/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T08:05:50Z","links":{"resolver":"https://pith.science/pith/LMUYR4GTOJBPK7UKQXUBSDQ23M","bundle":"https://pith.science/pith/LMUYR4GTOJBPK7UKQXUBSDQ23M/bundle.json","state":"https://pith.science/pith/LMUYR4GTOJBPK7UKQXUBSDQ23M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LMUYR4GTOJBPK7UKQXUBSDQ23M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LMUYR4GTOJBPK7UKQXUBSDQ23M","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":"b942cb4ab9018b2b263ae089572ac9548098a5316bb1e1f7328c37bbdd3c1e34","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T04:46:44Z","title_canon_sha256":"ee554db43bfddaf36a88237317092db4ff3650470e251affcb2202cc2d4d4652"},"schema_version":"1.0","source":{"id":"2306.02592","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02592","created_at":"2026-07-05T06:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02592v1","created_at":"2026-07-05T06:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02592","created_at":"2026-07-05T06:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"LMUYR4GTOJBP","created_at":"2026-07-05T06:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"LMUYR4GTOJBPK7UK","created_at":"2026-07-05T06:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"LMUYR4GT","created_at":"2026-07-05T06:17:19Z"}],"graph_snapshots":[{"event_id":"sha256:acea481d55607f63630e7684f49070f381d46543c2a9dbedeff7f5394562145c","target":"graph","created_at":"2026-07-05T06:17:19Z","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/2306.02592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the hope of benefiting downstream graph applications, which has also been explored by several recent studies. However, no existing study has ever investigated the pre-training of text plus graph models on large heterogeneous graphs with abundant textual information (a.k.a. large graph corpora) and then fine-tuning the model on different related downstream applic","authors_text":"Belinda Zeng, Carl Yang, Da Zheng, Han Xie, Houyu Zhang, Jun Ma, Qing Ping, Sheng Wang, Trishul Chilimbi, Vassilis N. Ioannidis, Xiang Song, Yi Xu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T04:46:44Z","title":"Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02592","kind":"arxiv","version":1},"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:b87418ac81c4b558cbabd31c33477102815805980d166acdb7decb9ca9d62009","target":"record","created_at":"2026-07-05T06:17:19Z","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":"b942cb4ab9018b2b263ae089572ac9548098a5316bb1e1f7328c37bbdd3c1e34","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T04:46:44Z","title_canon_sha256":"ee554db43bfddaf36a88237317092db4ff3650470e251affcb2202cc2d4d4652"},"schema_version":"1.0","source":{"id":"2306.02592","kind":"arxiv","version":1}},"canonical_sha256":"5b2988f0d37242f57e8a85e8190e1adb0237d17b19f6dd0a42383e85ade60d4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b2988f0d37242f57e8a85e8190e1adb0237d17b19f6dd0a42383e85ade60d4d","first_computed_at":"2026-07-05T06:17:19.134087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:19.134087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eyyY3901GOL+aBdaNe1nmk615UUSsfERPosnmNv2ySxdBty2gKJkGJZiLSP3thPjHeza8uwdTNqcUtZ1utozAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:19.134577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02592","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b87418ac81c4b558cbabd31c33477102815805980d166acdb7decb9ca9d62009","sha256:acea481d55607f63630e7684f49070f381d46543c2a9dbedeff7f5394562145c"],"state_sha256":"6daa3c0e5405e967ddcde2d4082f25ca71b70626d1f3e727a7c2c037fb5d41e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YWaBvaVpNVxDZN/AW/Vi4/ma5lK8WXBKmcn0/yBgqX1xqUlzUh/K5hcbpDqlBXxwIJ+QTC3PkuZLMobMm9jsDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:05:50.059393Z","bundle_sha256":"04f4406d07debebc8835442071e545ed240a4d1a696958b5fa947fb0fb98b31e"}}