{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CHOUCUD55D6C7F7WBNKIYPVEEX","short_pith_number":"pith:CHOUCUD5","canonical_record":{"source":{"id":"2506.06157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2025-06-06T15:21:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6131f0a9f79c694ad9d03801b9ad3dd83e4bbe823b662a3e8c966766b636018f","abstract_canon_sha256":"4fae03e243746f560a9c5b51778d55a5234fe08ea41d23c9af8f26e89e1bbd23"},"schema_version":"1.0"},"canonical_sha256":"11dd41507de8fc2f97f60b548c3ea425f3266fd8fa1339e2c64ac37d5991ed01","source":{"kind":"arxiv","id":"2506.06157","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06157","created_at":"2026-07-05T11:45:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06157v2","created_at":"2026-07-05T11:45:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06157","created_at":"2026-07-05T11:45:36Z"},{"alias_kind":"pith_short_12","alias_value":"CHOUCUD55D6C","created_at":"2026-07-05T11:45:36Z"},{"alias_kind":"pith_short_16","alias_value":"CHOUCUD55D6C7F7W","created_at":"2026-07-05T11:45:36Z"},{"alias_kind":"pith_short_8","alias_value":"CHOUCUD5","created_at":"2026-07-05T11:45:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CHOUCUD55D6C7F7WBNKIYPVEEX","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2025-06-06T15:21:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6131f0a9f79c694ad9d03801b9ad3dd83e4bbe823b662a3e8c966766b636018f","abstract_canon_sha256":"4fae03e243746f560a9c5b51778d55a5234fe08ea41d23c9af8f26e89e1bbd23"},"schema_version":"1.0"},"canonical_sha256":"11dd41507de8fc2f97f60b548c3ea425f3266fd8fa1339e2c64ac37d5991ed01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:36.276771Z","signature_b64":"GFrv+tnPFr6BMA5XeXAnq2N+q5X0lxQ4veaQ/SmrYB4mcmkdBjg/hbz7WZ+Y+LpgRvbHN8IBIrJNcMB4wC6KAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11dd41507de8fc2f97f60b548c3ea425f3266fd8fa1339e2c64ac37d5991ed01","last_reissued_at":"2026-07-05T11:45:36.276255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:36.276255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06157","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:45:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PWsCGmE5qsCH2TD77Nyp6GnARDvc9jb0x7QybB5BB2zyK60ffwpfP7FywhiyG4Kifu+m95FmMFBwX9k+3441Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:43:45.182906Z"},"content_sha256":"5856c689ef43119eb5dc665154012c34466ecb599d191946fb87ada510f53857","schema_version":"1.0","event_id":"sha256:5856c689ef43119eb5dc665154012c34466ecb599d191946fb87ada510f53857"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CHOUCUD55D6C7F7WBNKIYPVEEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Masked Language Models are Good Heterogeneous Graph Generalizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SI","authors_text":"Cheng Yang, Chuan Shi, Jinyu Yang, Liangwei Yang, Muhan Zhang, Shanyuan Cui, Zeyuan Guo, Zhiqiang Zhang","submitted_at":"2025-06-06T15:21:24Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) excel at capturing structural and semantic information in heterogeneous graphs (HGs), while struggling to generalize across domains and tasks. With the rapid advancement of large language models (LLMs), a recent study explored the integration of HGNNs with LLMs for generalizable heterogeneous graph learning. However, this approach typically encodes structural information as HG tokens using HGNNs, and disparities in embedding spaces between HGNNs and LLMs have been shown to bias the LLM's comprehension of HGs. Moreover, since these HG tokens are often"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06157","kind":"arxiv","version":2},"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/2506.06157/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":"2026-07-05T11:45:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IaVEcuCY6TFyLhBi/upO+orQX54J/NDdJxi0PSPP8brL4Z+PUxEm7qD+RFbCen0+Ja7EJbyvgmhwBUSekFLTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:43:45.183415Z"},"content_sha256":"47443aebf012414afa63f17c524afb290ef646587576c0aecb3b4c27673e4297","schema_version":"1.0","event_id":"sha256:47443aebf012414afa63f17c524afb290ef646587576c0aecb3b4c27673e4297"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CHOUCUD55D6C7F7WBNKIYPVEEX/bundle.json","state_url":"https://pith.science/pith/CHOUCUD55D6C7F7WBNKIYPVEEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CHOUCUD55D6C7F7WBNKIYPVEEX/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":"2026-08-06T12:43:45Z","links":{"resolver":"https://pith.science/pith/CHOUCUD55D6C7F7WBNKIYPVEEX","bundle":"https://pith.science/pith/CHOUCUD55D6C7F7WBNKIYPVEEX/bundle.json","state":"https://pith.science/pith/CHOUCUD55D6C7F7WBNKIYPVEEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CHOUCUD55D6C7F7WBNKIYPVEEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CHOUCUD55D6C7F7WBNKIYPVEEX","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":"4fae03e243746f560a9c5b51778d55a5234fe08ea41d23c9af8f26e89e1bbd23","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2025-06-06T15:21:24Z","title_canon_sha256":"6131f0a9f79c694ad9d03801b9ad3dd83e4bbe823b662a3e8c966766b636018f"},"schema_version":"1.0","source":{"id":"2506.06157","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06157","created_at":"2026-07-05T11:45:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06157v2","created_at":"2026-07-05T11:45:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06157","created_at":"2026-07-05T11:45:36Z"},{"alias_kind":"pith_short_12","alias_value":"CHOUCUD55D6C","created_at":"2026-07-05T11:45:36Z"},{"alias_kind":"pith_short_16","alias_value":"CHOUCUD55D6C7F7W","created_at":"2026-07-05T11:45:36Z"},{"alias_kind":"pith_short_8","alias_value":"CHOUCUD5","created_at":"2026-07-05T11:45:36Z"}],"graph_snapshots":[{"event_id":"sha256:47443aebf012414afa63f17c524afb290ef646587576c0aecb3b4c27673e4297","target":"graph","created_at":"2026-07-05T11:45:36Z","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/2506.06157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) excel at capturing structural and semantic information in heterogeneous graphs (HGs), while struggling to generalize across domains and tasks. With the rapid advancement of large language models (LLMs), a recent study explored the integration of HGNNs with LLMs for generalizable heterogeneous graph learning. However, this approach typically encodes structural information as HG tokens using HGNNs, and disparities in embedding spaces between HGNNs and LLMs have been shown to bias the LLM's comprehension of HGs. Moreover, since these HG tokens are often","authors_text":"Cheng Yang, Chuan Shi, Jinyu Yang, Liangwei Yang, Muhan Zhang, Shanyuan Cui, Zeyuan Guo, Zhiqiang Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06157","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":"sha256:5856c689ef43119eb5dc665154012c34466ecb599d191946fb87ada510f53857","target":"record","created_at":"2026-07-05T11:45:36Z","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":"4fae03e243746f560a9c5b51778d55a5234fe08ea41d23c9af8f26e89e1bbd23","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2025-06-06T15:21:24Z","title_canon_sha256":"6131f0a9f79c694ad9d03801b9ad3dd83e4bbe823b662a3e8c966766b636018f"},"schema_version":"1.0","source":{"id":"2506.06157","kind":"arxiv","version":2}},"canonical_sha256":"11dd41507de8fc2f97f60b548c3ea425f3266fd8fa1339e2c64ac37d5991ed01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11dd41507de8fc2f97f60b548c3ea425f3266fd8fa1339e2c64ac37d5991ed01","first_computed_at":"2026-07-05T11:45:36.276255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:36.276255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GFrv+tnPFr6BMA5XeXAnq2N+q5X0lxQ4veaQ/SmrYB4mcmkdBjg/hbz7WZ+Y+LpgRvbHN8IBIrJNcMB4wC6KAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:36.276771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06157","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5856c689ef43119eb5dc665154012c34466ecb599d191946fb87ada510f53857","sha256:47443aebf012414afa63f17c524afb290ef646587576c0aecb3b4c27673e4297"],"state_sha256":"1d8a398105d00695cd4b58cada95907e760ab1c4ac2a57dce3b0042c966ee086"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"llTBqEcwoQgEFpkVNtRO3zMflykc5QJS8ZeYMq6z3oi07CeAozp3t7DIUNf2kDsRfSuywbObhvs2r2O9XeZOCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:43:45.187780Z","bundle_sha256":"747ff55281a49517ccf8497cfe21b0859bdf36212c8f1ce204ed59b17397e1a9"}}