{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EM3EQMDRIQ327HG2IKS57S23PO","short_pith_number":"pith:EM3EQMDR","canonical_record":{"source":{"id":"2203.02018","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T21:00:23Z","cross_cats_sorted":[],"title_canon_sha256":"b78165c899e9d11c43eb02cb62e919fdc68ddfe9edff2669e932ebb507ad68d5","abstract_canon_sha256":"804e5d7c109e5955a00e92b4bcbae2e8f05138d7433fd7ed3bd38e23eb305cd5"},"schema_version":"1.0"},"canonical_sha256":"23364830714437af9cda42a5dfcb5b7b93f026e2132c909cf88bbb9277de59ad","source":{"kind":"arxiv","id":"2203.02018","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02018","created_at":"2026-07-05T05:06:10Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02018v4","created_at":"2026-07-05T05:06:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02018","created_at":"2026-07-05T05:06:10Z"},{"alias_kind":"pith_short_12","alias_value":"EM3EQMDRIQ32","created_at":"2026-07-05T05:06:10Z"},{"alias_kind":"pith_short_16","alias_value":"EM3EQMDRIQ327HG2","created_at":"2026-07-05T05:06:10Z"},{"alias_kind":"pith_short_8","alias_value":"EM3EQMDR","created_at":"2026-07-05T05:06:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EM3EQMDRIQ327HG2IKS57S23PO","target":"record","payload":{"canonical_record":{"source":{"id":"2203.02018","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T21:00:23Z","cross_cats_sorted":[],"title_canon_sha256":"b78165c899e9d11c43eb02cb62e919fdc68ddfe9edff2669e932ebb507ad68d5","abstract_canon_sha256":"804e5d7c109e5955a00e92b4bcbae2e8f05138d7433fd7ed3bd38e23eb305cd5"},"schema_version":"1.0"},"canonical_sha256":"23364830714437af9cda42a5dfcb5b7b93f026e2132c909cf88bbb9277de59ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:10.308811Z","signature_b64":"5spyFUFCJqxD3moUVrU5AG341d1VY5VEMg/riV4LnsYdYcmI7t4KG5MqqGciuNobQn9YUR4MPX6pegyUbAAuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23364830714437af9cda42a5dfcb5b7b93f026e2132c909cf88bbb9277de59ad","last_reissued_at":"2026-07-05T05:06:10.308312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:10.308312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.02018","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:06:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bT7X07ch0OsNkf5mXHKIyOvWjqG/D0pJHjfxa9EJ///Lqx59nidwX7DcgpaaoEABApgvGvoplTMCvI0n61nPAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:30:31.288140Z"},"content_sha256":"d9d00770162e5aaadfe3c6ec6c1bcb183f0fe540952384cb41a5b9e3805923ff","schema_version":"1.0","event_id":"sha256:d9d00770162e5aaadfe3c6ec6c1bcb183f0fe540952384cb41a5b9e3805923ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EM3EQMDRIQ327HG2IKS57S23PO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bryan Perozzi, Dustin Zelle, John Palowitch, Minji Yoon, Ruslan Salakhutdinov, Ziniu Hu","submitted_at":"2022-03-03T21:00:23Z","abstract_excerpt":"Data continuously emitted from industrial ecosystems such as social or e-commerce platforms are commonly represented as heterogeneous graphs (HG) composed of multiple node/edge types. State-of-the-art graph learning methods for HGs known as heterogeneous graph neural networks (HGNNs) are applied to learn deep context-informed node representations. However, many HG datasets from industrial applications suffer from label imbalance between node types. As there is no direct way to learn using labels rooted at different node types, HGNNs have been applied to only a few node types with abundant labe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02018","kind":"arxiv","version":4},"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/2203.02018/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":"2026-07-05T05:06:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jrAVOuf65fLe5eBh+kIipZWmudGRjkJ2SJu7S9mAoLZV1H/DWrq9Ou9QZRo8lGJ11hW9g0g67bKpqH7pwtrtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:30:31.289034Z"},"content_sha256":"b101fc59a4c695783e4f5c6527a0d304f5c1ce138c1147c19a5dcd7561804f37","schema_version":"1.0","event_id":"sha256:b101fc59a4c695783e4f5c6527a0d304f5c1ce138c1147c19a5dcd7561804f37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EM3EQMDRIQ327HG2IKS57S23PO/bundle.json","state_url":"https://pith.science/pith/EM3EQMDRIQ327HG2IKS57S23PO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EM3EQMDRIQ327HG2IKS57S23PO/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":"2026-08-11T01:30:31Z","links":{"resolver":"https://pith.science/pith/EM3EQMDRIQ327HG2IKS57S23PO","bundle":"https://pith.science/pith/EM3EQMDRIQ327HG2IKS57S23PO/bundle.json","state":"https://pith.science/pith/EM3EQMDRIQ327HG2IKS57S23PO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EM3EQMDRIQ327HG2IKS57S23PO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EM3EQMDRIQ327HG2IKS57S23PO","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":"804e5d7c109e5955a00e92b4bcbae2e8f05138d7433fd7ed3bd38e23eb305cd5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T21:00:23Z","title_canon_sha256":"b78165c899e9d11c43eb02cb62e919fdc68ddfe9edff2669e932ebb507ad68d5"},"schema_version":"1.0","source":{"id":"2203.02018","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02018","created_at":"2026-07-05T05:06:10Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02018v4","created_at":"2026-07-05T05:06:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02018","created_at":"2026-07-05T05:06:10Z"},{"alias_kind":"pith_short_12","alias_value":"EM3EQMDRIQ32","created_at":"2026-07-05T05:06:10Z"},{"alias_kind":"pith_short_16","alias_value":"EM3EQMDRIQ327HG2","created_at":"2026-07-05T05:06:10Z"},{"alias_kind":"pith_short_8","alias_value":"EM3EQMDR","created_at":"2026-07-05T05:06:10Z"}],"graph_snapshots":[{"event_id":"sha256:b101fc59a4c695783e4f5c6527a0d304f5c1ce138c1147c19a5dcd7561804f37","target":"graph","created_at":"2026-07-05T05:06:10Z","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/2203.02018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data continuously emitted from industrial ecosystems such as social or e-commerce platforms are commonly represented as heterogeneous graphs (HG) composed of multiple node/edge types. State-of-the-art graph learning methods for HGs known as heterogeneous graph neural networks (HGNNs) are applied to learn deep context-informed node representations. However, many HG datasets from industrial applications suffer from label imbalance between node types. As there is no direct way to learn using labels rooted at different node types, HGNNs have been applied to only a few node types with abundant labe","authors_text":"Bryan Perozzi, Dustin Zelle, John Palowitch, Minji Yoon, Ruslan Salakhutdinov, Ziniu Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T21:00:23Z","title":"Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02018","kind":"arxiv","version":4},"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:d9d00770162e5aaadfe3c6ec6c1bcb183f0fe540952384cb41a5b9e3805923ff","target":"record","created_at":"2026-07-05T05:06:10Z","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":"804e5d7c109e5955a00e92b4bcbae2e8f05138d7433fd7ed3bd38e23eb305cd5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T21:00:23Z","title_canon_sha256":"b78165c899e9d11c43eb02cb62e919fdc68ddfe9edff2669e932ebb507ad68d5"},"schema_version":"1.0","source":{"id":"2203.02018","kind":"arxiv","version":4}},"canonical_sha256":"23364830714437af9cda42a5dfcb5b7b93f026e2132c909cf88bbb9277de59ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23364830714437af9cda42a5dfcb5b7b93f026e2132c909cf88bbb9277de59ad","first_computed_at":"2026-07-05T05:06:10.308312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:10.308312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5spyFUFCJqxD3moUVrU5AG341d1VY5VEMg/riV4LnsYdYcmI7t4KG5MqqGciuNobQn9YUR4MPX6pegyUbAAuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:10.308811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02018","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9d00770162e5aaadfe3c6ec6c1bcb183f0fe540952384cb41a5b9e3805923ff","sha256:b101fc59a4c695783e4f5c6527a0d304f5c1ce138c1147c19a5dcd7561804f37"],"state_sha256":"12e0e341031a672c290d77f311f191221e828b5174a0fbc4df4cf1e535d739f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SQ0ftKZGoNWaGFeK6jyngGXijVbXESWbxbow1NwJLnMs5MXDpv6Z6fxev3uec7FtZrnS8l8dRDIykPGhVcY6AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:30:31.294909Z","bundle_sha256":"2848da4ee7dfca23ea0e3e3d68c9f722b9990f0467e4b305c29443b00621d1b2"}}