{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2XER6LFBELSRMPMJVCX6O4DPAL","short_pith_number":"pith:2XER6LFB","canonical_record":{"source":{"id":"2206.10781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-22T00:23:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"85db636904ddad86cb11d95cdd90e91dae858e76f0a10f3a2cb1644f2f3b76c2","abstract_canon_sha256":"e4322e026b2b788014fe2e663a93d973a69a78d6a9fe0035c8a52f11efd326fa"},"schema_version":"1.0"},"canonical_sha256":"d5c91f2ca122e5163d89a8afe7706f02ea4446b9b331ea909f96e04518b7824b","source":{"kind":"arxiv","id":"2206.10781","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.10781","created_at":"2026-07-05T04:33:55Z"},{"alias_kind":"arxiv_version","alias_value":"2206.10781v1","created_at":"2026-07-05T04:33:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10781","created_at":"2026-07-05T04:33:55Z"},{"alias_kind":"pith_short_12","alias_value":"2XER6LFBELSR","created_at":"2026-07-05T04:33:55Z"},{"alias_kind":"pith_short_16","alias_value":"2XER6LFBELSRMPMJ","created_at":"2026-07-05T04:33:55Z"},{"alias_kind":"pith_short_8","alias_value":"2XER6LFB","created_at":"2026-07-05T04:33:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2XER6LFBELSRMPMJVCX6O4DPAL","target":"record","payload":{"canonical_record":{"source":{"id":"2206.10781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-22T00:23:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"85db636904ddad86cb11d95cdd90e91dae858e76f0a10f3a2cb1644f2f3b76c2","abstract_canon_sha256":"e4322e026b2b788014fe2e663a93d973a69a78d6a9fe0035c8a52f11efd326fa"},"schema_version":"1.0"},"canonical_sha256":"d5c91f2ca122e5163d89a8afe7706f02ea4446b9b331ea909f96e04518b7824b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:55.376650Z","signature_b64":"MG6n84Clpu2KaKi4Qj5QUj3U2ReC44mZFxQSJa+PMVIt0113B/t5Mf+NCNhMrN3MLk3ZTHB6nbCwA18rTCdHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5c91f2ca122e5163d89a8afe7706f02ea4446b9b331ea909f96e04518b7824b","last_reissued_at":"2026-07-05T04:33:55.376198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:55.376198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.10781","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":"2026-07-05T04:33:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0YCiwiqxydx3cHiCsigqDJZgsErRarxs13LnkiaX99rUmzp6T240NFm5/RxIXtUSBSvl1+g6G8hx+l2K53NvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:43:58.339995Z"},"content_sha256":"88512bcd3b6a9bb4f45ac287d05b1bf288ae7fd3d489208f2753d8d590a9d966","schema_version":"1.0","event_id":"sha256:88512bcd3b6a9bb4f45ac287d05b1bf288ae7fd3d489208f2753d8d590a9d966"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2XER6LFBELSRMPMJVCX6O4DPAL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient and effective training of language and graph neural network models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Belinda Zeng, Da Zheng, George Karypis, Houyu Zhang, Jun Ma, Trishul Chilimbi, Vassilis N. Ioannidis, Xiang Song, Yi Xu","submitted_at":"2022-06-22T00:23:37Z","abstract_excerpt":"Can we combine heterogenous graph structure with text to learn high-quality semantic and behavioural representations? Graph neural networks (GNN)s encode numerical node attributes and graph structure to achieve impressive performance in a variety of supervised learning tasks. Current GNN approaches are challenged by textual features, which typically need to be encoded to a numerical vector before provided to the GNN that may incur some information loss. In this paper, we put forth an efficient and effective framework termed language model GNN (LM-GNN) to jointly train large-scale language mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10781","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/2206.10781/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":"2026-07-05T04:33:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afkSS5+h+K/lmAxZhIbNq6ulOki+sygG72NU4ZpcqhrDebPj86Kmf7025+XX99mqHrnOejXGTMZ0s+lbBeq1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:43:58.340392Z"},"content_sha256":"f6c43063d58a2e716382630730367a8fee051555d1958d258a67be825b62ef8e","schema_version":"1.0","event_id":"sha256:f6c43063d58a2e716382630730367a8fee051555d1958d258a67be825b62ef8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2XER6LFBELSRMPMJVCX6O4DPAL/bundle.json","state_url":"https://pith.science/pith/2XER6LFBELSRMPMJVCX6O4DPAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2XER6LFBELSRMPMJVCX6O4DPAL/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":"2026-07-06T12:43:58Z","links":{"resolver":"https://pith.science/pith/2XER6LFBELSRMPMJVCX6O4DPAL","bundle":"https://pith.science/pith/2XER6LFBELSRMPMJVCX6O4DPAL/bundle.json","state":"https://pith.science/pith/2XER6LFBELSRMPMJVCX6O4DPAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2XER6LFBELSRMPMJVCX6O4DPAL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2XER6LFBELSRMPMJVCX6O4DPAL","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":"e4322e026b2b788014fe2e663a93d973a69a78d6a9fe0035c8a52f11efd326fa","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-22T00:23:37Z","title_canon_sha256":"85db636904ddad86cb11d95cdd90e91dae858e76f0a10f3a2cb1644f2f3b76c2"},"schema_version":"1.0","source":{"id":"2206.10781","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.10781","created_at":"2026-07-05T04:33:55Z"},{"alias_kind":"arxiv_version","alias_value":"2206.10781v1","created_at":"2026-07-05T04:33:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10781","created_at":"2026-07-05T04:33:55Z"},{"alias_kind":"pith_short_12","alias_value":"2XER6LFBELSR","created_at":"2026-07-05T04:33:55Z"},{"alias_kind":"pith_short_16","alias_value":"2XER6LFBELSRMPMJ","created_at":"2026-07-05T04:33:55Z"},{"alias_kind":"pith_short_8","alias_value":"2XER6LFB","created_at":"2026-07-05T04:33:55Z"}],"graph_snapshots":[{"event_id":"sha256:f6c43063d58a2e716382630730367a8fee051555d1958d258a67be825b62ef8e","target":"graph","created_at":"2026-07-05T04:33:55Z","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/2206.10781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can we combine heterogenous graph structure with text to learn high-quality semantic and behavioural representations? Graph neural networks (GNN)s encode numerical node attributes and graph structure to achieve impressive performance in a variety of supervised learning tasks. Current GNN approaches are challenged by textual features, which typically need to be encoded to a numerical vector before provided to the GNN that may incur some information loss. In this paper, we put forth an efficient and effective framework termed language model GNN (LM-GNN) to jointly train large-scale language mode","authors_text":"Belinda Zeng, Da Zheng, George Karypis, Houyu Zhang, Jun Ma, Trishul Chilimbi, Vassilis N. Ioannidis, Xiang Song, Yi Xu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-22T00:23:37Z","title":"Efficient and effective training of language and graph neural network models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10781","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":"sha256:88512bcd3b6a9bb4f45ac287d05b1bf288ae7fd3d489208f2753d8d590a9d966","target":"record","created_at":"2026-07-05T04:33:55Z","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":"e4322e026b2b788014fe2e663a93d973a69a78d6a9fe0035c8a52f11efd326fa","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-22T00:23:37Z","title_canon_sha256":"85db636904ddad86cb11d95cdd90e91dae858e76f0a10f3a2cb1644f2f3b76c2"},"schema_version":"1.0","source":{"id":"2206.10781","kind":"arxiv","version":1}},"canonical_sha256":"d5c91f2ca122e5163d89a8afe7706f02ea4446b9b331ea909f96e04518b7824b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5c91f2ca122e5163d89a8afe7706f02ea4446b9b331ea909f96e04518b7824b","first_computed_at":"2026-07-05T04:33:55.376198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:55.376198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MG6n84Clpu2KaKi4Qj5QUj3U2ReC44mZFxQSJa+PMVIt0113B/t5Mf+NCNhMrN3MLk3ZTHB6nbCwA18rTCdHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:55.376650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.10781","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88512bcd3b6a9bb4f45ac287d05b1bf288ae7fd3d489208f2753d8d590a9d966","sha256:f6c43063d58a2e716382630730367a8fee051555d1958d258a67be825b62ef8e"],"state_sha256":"8ee27f392685d4f2e7b5d8a1706601586c9333985367192c83f55741c4c3e259"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kWcoBGUOYK05Y0sZqIDxgAWiNpb4Vx35XfTLtK7O6QFIiq0Tk2NEo79frhI2Ou7VfJ3sKtGR7VBP4s3/ORa/Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:43:58.342417Z","bundle_sha256":"736cb5720f7c45e5856a7dcd911970fcf7d7331ecde8b8fc58eddc751d87344d"}}