{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PKGHZ6HPZAPUP3Q2GBKN6MFRGZ","short_pith_number":"pith:PKGHZ6HP","canonical_record":{"source":{"id":"2003.08420","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-18T18:21:48Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"52404db3b1639f70ccc7e5841c2683d8d72f4731aff3532f817e39ab55f1a158","abstract_canon_sha256":"aed1d4b77d508a90a9b5599ed55eaf1581c973c0810b8639b18b492722db016e"},"schema_version":"1.0"},"canonical_sha256":"7a8c7cf8efc81f47ee1a3054df30b1364ed8c46dd3898bd5b03857f527429786","source":{"kind":"arxiv","id":"2003.08420","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.08420","created_at":"2026-07-05T01:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"2003.08420v3","created_at":"2026-07-05T01:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08420","created_at":"2026-07-05T01:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"PKGHZ6HPZAPU","created_at":"2026-07-05T01:23:11Z"},{"alias_kind":"pith_short_16","alias_value":"PKGHZ6HPZAPUP3Q2","created_at":"2026-07-05T01:23:11Z"},{"alias_kind":"pith_short_8","alias_value":"PKGHZ6HP","created_at":"2026-07-05T01:23:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PKGHZ6HPZAPUP3Q2GBKN6MFRGZ","target":"record","payload":{"canonical_record":{"source":{"id":"2003.08420","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-18T18:21:48Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"52404db3b1639f70ccc7e5841c2683d8d72f4731aff3532f817e39ab55f1a158","abstract_canon_sha256":"aed1d4b77d508a90a9b5599ed55eaf1581c973c0810b8639b18b492722db016e"},"schema_version":"1.0"},"canonical_sha256":"7a8c7cf8efc81f47ee1a3054df30b1364ed8c46dd3898bd5b03857f527429786","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:11.517528Z","signature_b64":"4I7dJXaTwUc5FoNRjvheVWWNRjyv6BSfQc+0fSfISVDRqO4RQNnQrIhUn54WwUl4NcAtGhYa6LI9fTmPr1cjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a8c7cf8efc81f47ee1a3054df30b1364ed8c46dd3898bd5b03857f527429786","last_reissued_at":"2026-07-05T01:23:11.516987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:11.516987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.08420","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:23:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqhnfRdMlITSOWc6nsym1f7OR4JR2O56WIpPe1wzbJY678A9dnTI1EiXkl02Mw0+R/IE8XImjIhaK2JYSGy8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:15:14.213231Z"},"content_sha256":"01ca7bab6c264a769135dabf15152cc2ad74268e62b41942447fceba2ab4f923","schema_version":"1.0","event_id":"sha256:01ca7bab6c264a769135dabf15152cc2ad74268e62b41942447fceba2ab4f923"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PKGHZ6HPZAPUP3Q2GBKN6MFRGZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fei Ding, Ilya Safro, Justin Sybrandt, Xiaohong Zhang","submitted_at":"2020-03-18T18:21:48Z","abstract_excerpt":"Graph representation learning based on graph neural networks (GNNs) can greatly improve the performance of downstream tasks, such as node and graph classification. However, the general GNN models do not aggregate node information in a hierarchical manner, and can miss key higher-order structural features of many graphs. The hierarchical aggregation also enables the graph representations to be explainable. In addition, supervised graph representation learning requires labeled data, which is expensive and error-prone. To address these issues, we present an unsupervised graph representation learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08420","kind":"arxiv","version":3},"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/2003.08420/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":"2026-07-05T01:23:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wFfPeIOqbRwSVuLCR4geEMqGyWXaiDhOp6spTdeE6p4AnFBg47vR0g8j36yknxUd4YhiMMYC7a/AmysDfNTDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:15:14.213739Z"},"content_sha256":"8b8fcb7dbef8ed3b3fd5cbd07a11af383e2074526bb1c0206d672249c22bb10a","schema_version":"1.0","event_id":"sha256:8b8fcb7dbef8ed3b3fd5cbd07a11af383e2074526bb1c0206d672249c22bb10a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PKGHZ6HPZAPUP3Q2GBKN6MFRGZ/bundle.json","state_url":"https://pith.science/pith/PKGHZ6HPZAPUP3Q2GBKN6MFRGZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PKGHZ6HPZAPUP3Q2GBKN6MFRGZ/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":"2026-08-15T22:15:14Z","links":{"resolver":"https://pith.science/pith/PKGHZ6HPZAPUP3Q2GBKN6MFRGZ","bundle":"https://pith.science/pith/PKGHZ6HPZAPUP3Q2GBKN6MFRGZ/bundle.json","state":"https://pith.science/pith/PKGHZ6HPZAPUP3Q2GBKN6MFRGZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PKGHZ6HPZAPUP3Q2GBKN6MFRGZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PKGHZ6HPZAPUP3Q2GBKN6MFRGZ","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":"aed1d4b77d508a90a9b5599ed55eaf1581c973c0810b8639b18b492722db016e","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-18T18:21:48Z","title_canon_sha256":"52404db3b1639f70ccc7e5841c2683d8d72f4731aff3532f817e39ab55f1a158"},"schema_version":"1.0","source":{"id":"2003.08420","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.08420","created_at":"2026-07-05T01:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"2003.08420v3","created_at":"2026-07-05T01:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08420","created_at":"2026-07-05T01:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"PKGHZ6HPZAPU","created_at":"2026-07-05T01:23:11Z"},{"alias_kind":"pith_short_16","alias_value":"PKGHZ6HPZAPUP3Q2","created_at":"2026-07-05T01:23:11Z"},{"alias_kind":"pith_short_8","alias_value":"PKGHZ6HP","created_at":"2026-07-05T01:23:11Z"}],"graph_snapshots":[{"event_id":"sha256:8b8fcb7dbef8ed3b3fd5cbd07a11af383e2074526bb1c0206d672249c22bb10a","target":"graph","created_at":"2026-07-05T01:23:11Z","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/2003.08420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph representation learning based on graph neural networks (GNNs) can greatly improve the performance of downstream tasks, such as node and graph classification. However, the general GNN models do not aggregate node information in a hierarchical manner, and can miss key higher-order structural features of many graphs. The hierarchical aggregation also enables the graph representations to be explainable. In addition, supervised graph representation learning requires labeled data, which is expensive and error-prone. To address these issues, we present an unsupervised graph representation learn","authors_text":"Fei Ding, Ilya Safro, Justin Sybrandt, Xiaohong Zhang","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-18T18:21:48Z","title":"Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08420","kind":"arxiv","version":3},"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":"sha256:01ca7bab6c264a769135dabf15152cc2ad74268e62b41942447fceba2ab4f923","target":"record","created_at":"2026-07-05T01:23:11Z","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":"aed1d4b77d508a90a9b5599ed55eaf1581c973c0810b8639b18b492722db016e","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-18T18:21:48Z","title_canon_sha256":"52404db3b1639f70ccc7e5841c2683d8d72f4731aff3532f817e39ab55f1a158"},"schema_version":"1.0","source":{"id":"2003.08420","kind":"arxiv","version":3}},"canonical_sha256":"7a8c7cf8efc81f47ee1a3054df30b1364ed8c46dd3898bd5b03857f527429786","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a8c7cf8efc81f47ee1a3054df30b1364ed8c46dd3898bd5b03857f527429786","first_computed_at":"2026-07-05T01:23:11.516987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:23:11.516987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4I7dJXaTwUc5FoNRjvheVWWNRjyv6BSfQc+0fSfISVDRqO4RQNnQrIhUn54WwUl4NcAtGhYa6LI9fTmPr1cjAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:23:11.517528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.08420","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01ca7bab6c264a769135dabf15152cc2ad74268e62b41942447fceba2ab4f923","sha256:8b8fcb7dbef8ed3b3fd5cbd07a11af383e2074526bb1c0206d672249c22bb10a"],"state_sha256":"61f654dc0af0bc1591009b1e164bcb0b779e284f62e49a1c298401cee24c1b24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AUw+MNRBGEEzJoGuyYnYDN3rLl9b52JkHOL/4aJlnhbKrRiiTTPd98yefVdqM909lHdq2Xji7kB7IL6oS9nkAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T22:15:14.218180Z","bundle_sha256":"9f53ac530823391212928edd339b819816d1f8da784a368f14ad020778501bf5"}}