{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NXAYRGZYVRXRXOYPAYNSHXQNOX","short_pith_number":"pith:NXAYRGZY","canonical_record":{"source":{"id":"2105.09111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-19T13:15:03Z","cross_cats_sorted":[],"title_canon_sha256":"b035b0cdbbb6f12ee5d1ae6a5966234e14157c9fb54b498de30fab71f7681dca","abstract_canon_sha256":"827824319413b940b7e35f7a92a337e59713d951aafb01b3ad8b1b94f89a9d63"},"schema_version":"1.0"},"canonical_sha256":"6dc1889b38ac6f1bbb0f061b23de0d75cca522bf256d96330fa017d12d24280e","source":{"kind":"arxiv","id":"2105.09111","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.09111","created_at":"2026-07-05T02:41:37Z"},{"alias_kind":"arxiv_version","alias_value":"2105.09111v1","created_at":"2026-07-05T02:41:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09111","created_at":"2026-07-05T02:41:37Z"},{"alias_kind":"pith_short_12","alias_value":"NXAYRGZYVRXR","created_at":"2026-07-05T02:41:37Z"},{"alias_kind":"pith_short_16","alias_value":"NXAYRGZYVRXRXOYP","created_at":"2026-07-05T02:41:37Z"},{"alias_kind":"pith_short_8","alias_value":"NXAYRGZY","created_at":"2026-07-05T02:41:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NXAYRGZYVRXRXOYPAYNSHXQNOX","target":"record","payload":{"canonical_record":{"source":{"id":"2105.09111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-19T13:15:03Z","cross_cats_sorted":[],"title_canon_sha256":"b035b0cdbbb6f12ee5d1ae6a5966234e14157c9fb54b498de30fab71f7681dca","abstract_canon_sha256":"827824319413b940b7e35f7a92a337e59713d951aafb01b3ad8b1b94f89a9d63"},"schema_version":"1.0"},"canonical_sha256":"6dc1889b38ac6f1bbb0f061b23de0d75cca522bf256d96330fa017d12d24280e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:37.532729Z","signature_b64":"Sd6/2RU750jk0ClNJNZ7Z3tgkTjqM+M05M1VwYOVdHFSTHK1StQVNJjEJXCx5M4a13aVcvbhnma5v1639l+2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dc1889b38ac6f1bbb0f061b23de0d75cca522bf256d96330fa017d12d24280e","last_reissued_at":"2026-07-05T02:41:37.532278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:37.532278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.09111","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":"2026-07-05T02:41:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HVojgb16Rnpqutl8PEoPmBa42IEBcSSviyPokyWSgD50ZNvmulgpRf928tymHz15fJfXFFUZJRnuDWhitwW3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:07:10.262161Z"},"content_sha256":"1d8b772d5dd6550dd47610fa25ec7865504888b31dd217c70dbf7891b8003c4e","schema_version":"1.0","event_id":"sha256:1d8b772d5dd6550dd47610fa25ec7865504888b31dd217c70dbf7891b8003c4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NXAYRGZYVRXRXOYPAYNSHXQNOX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuan Shi, Hui Han, Nian Liu, Xiao Wang","submitted_at":"2021-05-19T13:15:03Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follow a semi-supervised learning manner, which notably limits their wide use in reality since labels are usually scarce in real applications. Recently, contrastive learning, a self-supervised method, becomes one of the most exciting learning paradigms and shows great potential when there are no labels. In this paper, we study the problem of self-supervised HGNNs and propose a novel co-contrastive learning mechanism for H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09111","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/2105.09111/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":"2026-07-05T02:41:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mGP1rX9qQYaD3Ak/iO6BQ5GIV1aQWyuCEjzEg7Fuy/VJHRWd8tN2VqylRn9mtyQmFscy9neRFSvfSRTHW3KoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:07:10.262647Z"},"content_sha256":"acf2eab34bdd62d2f9129a2a5b4b3e56d39b22c01f8146cb798a2ab3717976aa","schema_version":"1.0","event_id":"sha256:acf2eab34bdd62d2f9129a2a5b4b3e56d39b22c01f8146cb798a2ab3717976aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NXAYRGZYVRXRXOYPAYNSHXQNOX/bundle.json","state_url":"https://pith.science/pith/NXAYRGZYVRXRXOYPAYNSHXQNOX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NXAYRGZYVRXRXOYPAYNSHXQNOX/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":"2026-08-06T16:07:10Z","links":{"resolver":"https://pith.science/pith/NXAYRGZYVRXRXOYPAYNSHXQNOX","bundle":"https://pith.science/pith/NXAYRGZYVRXRXOYPAYNSHXQNOX/bundle.json","state":"https://pith.science/pith/NXAYRGZYVRXRXOYPAYNSHXQNOX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NXAYRGZYVRXRXOYPAYNSHXQNOX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NXAYRGZYVRXRXOYPAYNSHXQNOX","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":"827824319413b940b7e35f7a92a337e59713d951aafb01b3ad8b1b94f89a9d63","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-19T13:15:03Z","title_canon_sha256":"b035b0cdbbb6f12ee5d1ae6a5966234e14157c9fb54b498de30fab71f7681dca"},"schema_version":"1.0","source":{"id":"2105.09111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.09111","created_at":"2026-07-05T02:41:37Z"},{"alias_kind":"arxiv_version","alias_value":"2105.09111v1","created_at":"2026-07-05T02:41:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09111","created_at":"2026-07-05T02:41:37Z"},{"alias_kind":"pith_short_12","alias_value":"NXAYRGZYVRXR","created_at":"2026-07-05T02:41:37Z"},{"alias_kind":"pith_short_16","alias_value":"NXAYRGZYVRXRXOYP","created_at":"2026-07-05T02:41:37Z"},{"alias_kind":"pith_short_8","alias_value":"NXAYRGZY","created_at":"2026-07-05T02:41:37Z"}],"graph_snapshots":[{"event_id":"sha256:acf2eab34bdd62d2f9129a2a5b4b3e56d39b22c01f8146cb798a2ab3717976aa","target":"graph","created_at":"2026-07-05T02:41:37Z","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/2105.09111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follow a semi-supervised learning manner, which notably limits their wide use in reality since labels are usually scarce in real applications. Recently, contrastive learning, a self-supervised method, becomes one of the most exciting learning paradigms and shows great potential when there are no labels. In this paper, we study the problem of self-supervised HGNNs and propose a novel co-contrastive learning mechanism for H","authors_text":"Chuan Shi, Hui Han, Nian Liu, Xiao Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-19T13:15:03Z","title":"Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09111","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":"sha256:1d8b772d5dd6550dd47610fa25ec7865504888b31dd217c70dbf7891b8003c4e","target":"record","created_at":"2026-07-05T02:41:37Z","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":"827824319413b940b7e35f7a92a337e59713d951aafb01b3ad8b1b94f89a9d63","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-19T13:15:03Z","title_canon_sha256":"b035b0cdbbb6f12ee5d1ae6a5966234e14157c9fb54b498de30fab71f7681dca"},"schema_version":"1.0","source":{"id":"2105.09111","kind":"arxiv","version":1}},"canonical_sha256":"6dc1889b38ac6f1bbb0f061b23de0d75cca522bf256d96330fa017d12d24280e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dc1889b38ac6f1bbb0f061b23de0d75cca522bf256d96330fa017d12d24280e","first_computed_at":"2026-07-05T02:41:37.532278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:41:37.532278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sd6/2RU750jk0ClNJNZ7Z3tgkTjqM+M05M1VwYOVdHFSTHK1StQVNJjEJXCx5M4a13aVcvbhnma5v1639l+2Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:41:37.532729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.09111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d8b772d5dd6550dd47610fa25ec7865504888b31dd217c70dbf7891b8003c4e","sha256:acf2eab34bdd62d2f9129a2a5b4b3e56d39b22c01f8146cb798a2ab3717976aa"],"state_sha256":"9730c2de444199612066385579737e53524656ce351f3722b101679e56a175d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NylrLeIurT1fvuIir0315CfuLrPAzd5yp3icxPNQUR5dZ8XoVxpuUNhcMiw8ysoV0lIuEo/94UcO4WUMg764CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:07:10.267029Z","bundle_sha256":"be83abd66ced8ccf3eba490794fd26abc83312f8dd864d288794a48d09fe9e25"}}