{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MA2TW3AZJHEDLYEV6W5CMZUB3F","short_pith_number":"pith:MA2TW3AZ","canonical_record":{"source":{"id":"2109.02868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-07T05:02:59Z","cross_cats_sorted":["cs.LG","cs.SI"],"title_canon_sha256":"b6be4c7a1b6ddf7b0acc4ac747d914cbebfece34b887972faa2abb30b56255ac","abstract_canon_sha256":"c5ee6703ee38659a146efd87b43e20e635efd290819d3cebfbc4656670e554cf"},"schema_version":"1.0"},"canonical_sha256":"60353b6c1949c835e095f5ba266681d954b5e259bdb92f60c7e8bd234e172d12","source":{"kind":"arxiv","id":"2109.02868","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02868","created_at":"2026-07-05T09:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02868v1","created_at":"2026-07-05T09:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02868","created_at":"2026-07-05T09:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"MA2TW3AZJHED","created_at":"2026-07-05T09:52:55Z"},{"alias_kind":"pith_short_16","alias_value":"MA2TW3AZJHEDLYEV","created_at":"2026-07-05T09:52:55Z"},{"alias_kind":"pith_short_8","alias_value":"MA2TW3AZ","created_at":"2026-07-05T09:52:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MA2TW3AZJHEDLYEV6W5CMZUB3F","target":"record","payload":{"canonical_record":{"source":{"id":"2109.02868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-07T05:02:59Z","cross_cats_sorted":["cs.LG","cs.SI"],"title_canon_sha256":"b6be4c7a1b6ddf7b0acc4ac747d914cbebfece34b887972faa2abb30b56255ac","abstract_canon_sha256":"c5ee6703ee38659a146efd87b43e20e635efd290819d3cebfbc4656670e554cf"},"schema_version":"1.0"},"canonical_sha256":"60353b6c1949c835e095f5ba266681d954b5e259bdb92f60c7e8bd234e172d12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:55.063001Z","signature_b64":"AFXT2xFZC22dE95acXqth5DPmUzSlcp8YGp9VInPr2jHuzLZNoa6rA8wYYUdZ82qKUbXy3Hz1SAKNX/J7+HcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60353b6c1949c835e095f5ba266681d954b5e259bdb92f60c7e8bd234e172d12","last_reissued_at":"2026-07-05T09:52:55.062520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:55.062520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.02868","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":"2026-07-05T09:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZqoSdeJM4nB2l4GuUiOKzgY0a046GBcYhRIP7obbBJJ0tRoy6gz3aVbUxgVBsZDFEWa6V+ijf4vVJC7nIoCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:40:33.746499Z"},"content_sha256":"4c9b18c457b7a268efc5e203d7941f12b9db19a1f5ae18e1f2a5b4fb8e018e96","schema_version":"1.0","event_id":"sha256:4c9b18c457b7a268efc5e203d7941f12b9db19a1f5ae18e1f2a5b4fb8e018e96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MA2TW3AZJHEDLYEV6W5CMZUB3F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.AI","authors_text":"Dajiang Liu, Fei Hao, Jiaxing Shang, Linjiang Zheng, Xinjun Cai","submitted_at":"2021-09-07T05:02:59Z","abstract_excerpt":"Many real-world data can be represented as heterogeneous graphs with different types of nodes and connections. Heterogeneous graph neural network model aims to embed nodes or subgraphs into low-dimensional vector space for various downstream tasks such as node classification, link prediction, etc. Although several models were proposed recently, they either only aggregate information from the same type of neighbors, or just indiscriminately treat homogeneous and heterogeneous neighbors in the same way. Based on these observations, we propose a new heterogeneous graph neural network model named "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02868","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/2109.02868/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":"2026-07-05T09:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lRNW5u6zDrZ4pHN4caoQD0RTQU40AI0LFqwgcs3M7sMEvspE4RiwVbuZGE4yQ9bkJh5NzLv94JPom9S23JNEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:40:33.746890Z"},"content_sha256":"47e1c4502196942ddd370033f1d4104a3e8170c66a6305e68fa11e2cedefb312","schema_version":"1.0","event_id":"sha256:47e1c4502196942ddd370033f1d4104a3e8170c66a6305e68fa11e2cedefb312"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MA2TW3AZJHEDLYEV6W5CMZUB3F/bundle.json","state_url":"https://pith.science/pith/MA2TW3AZJHEDLYEV6W5CMZUB3F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MA2TW3AZJHEDLYEV6W5CMZUB3F/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":"2026-08-03T21:40:33Z","links":{"resolver":"https://pith.science/pith/MA2TW3AZJHEDLYEV6W5CMZUB3F","bundle":"https://pith.science/pith/MA2TW3AZJHEDLYEV6W5CMZUB3F/bundle.json","state":"https://pith.science/pith/MA2TW3AZJHEDLYEV6W5CMZUB3F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MA2TW3AZJHEDLYEV6W5CMZUB3F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MA2TW3AZJHEDLYEV6W5CMZUB3F","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":"c5ee6703ee38659a146efd87b43e20e635efd290819d3cebfbc4656670e554cf","cross_cats_sorted":["cs.LG","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-07T05:02:59Z","title_canon_sha256":"b6be4c7a1b6ddf7b0acc4ac747d914cbebfece34b887972faa2abb30b56255ac"},"schema_version":"1.0","source":{"id":"2109.02868","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02868","created_at":"2026-07-05T09:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02868v1","created_at":"2026-07-05T09:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02868","created_at":"2026-07-05T09:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"MA2TW3AZJHED","created_at":"2026-07-05T09:52:55Z"},{"alias_kind":"pith_short_16","alias_value":"MA2TW3AZJHEDLYEV","created_at":"2026-07-05T09:52:55Z"},{"alias_kind":"pith_short_8","alias_value":"MA2TW3AZ","created_at":"2026-07-05T09:52:55Z"}],"graph_snapshots":[{"event_id":"sha256:47e1c4502196942ddd370033f1d4104a3e8170c66a6305e68fa11e2cedefb312","target":"graph","created_at":"2026-07-05T09:52:55Z","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/2109.02868/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many real-world data can be represented as heterogeneous graphs with different types of nodes and connections. Heterogeneous graph neural network model aims to embed nodes or subgraphs into low-dimensional vector space for various downstream tasks such as node classification, link prediction, etc. Although several models were proposed recently, they either only aggregate information from the same type of neighbors, or just indiscriminately treat homogeneous and heterogeneous neighbors in the same way. Based on these observations, we propose a new heterogeneous graph neural network model named ","authors_text":"Dajiang Liu, Fei Hao, Jiaxing Shang, Linjiang Zheng, Xinjun Cai","cross_cats":["cs.LG","cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-07T05:02:59Z","title":"HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02868","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":"sha256:4c9b18c457b7a268efc5e203d7941f12b9db19a1f5ae18e1f2a5b4fb8e018e96","target":"record","created_at":"2026-07-05T09:52:55Z","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":"c5ee6703ee38659a146efd87b43e20e635efd290819d3cebfbc4656670e554cf","cross_cats_sorted":["cs.LG","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-07T05:02:59Z","title_canon_sha256":"b6be4c7a1b6ddf7b0acc4ac747d914cbebfece34b887972faa2abb30b56255ac"},"schema_version":"1.0","source":{"id":"2109.02868","kind":"arxiv","version":1}},"canonical_sha256":"60353b6c1949c835e095f5ba266681d954b5e259bdb92f60c7e8bd234e172d12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60353b6c1949c835e095f5ba266681d954b5e259bdb92f60c7e8bd234e172d12","first_computed_at":"2026-07-05T09:52:55.062520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:55.062520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AFXT2xFZC22dE95acXqth5DPmUzSlcp8YGp9VInPr2jHuzLZNoa6rA8wYYUdZ82qKUbXy3Hz1SAKNX/J7+HcCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:55.063001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.02868","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c9b18c457b7a268efc5e203d7941f12b9db19a1f5ae18e1f2a5b4fb8e018e96","sha256:47e1c4502196942ddd370033f1d4104a3e8170c66a6305e68fa11e2cedefb312"],"state_sha256":"a5d3d73349eec6bf03aae92a7f7485d59a07046e94de857856d263bde97ea6ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ejnZWmIlWLp8USBEEAnZ1biU1pfhvhB7uVJeq0QYwLzpYM2dujsin1mrOd420Ol2Qy16Cu76zMVAvIRQ0W0FDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:40:33.749728Z","bundle_sha256":"d49cad13e29c5250db9145a1dbf4810e570288ed5c6a0dd8436c05457baf4902"}}