{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:34Z4W3VYT36ITYWF47ZTLUPKMF","short_pith_number":"pith:34Z4W3VY","canonical_record":{"source":{"id":"1904.09671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-21T22:45:04Z","cross_cats_sorted":["cs.IR","cs.SI","stat.ML"],"title_canon_sha256":"6e1c78bea17abcdfd0fdefb7f98042b14f51f35f0de5c85018a7639e53db926d","abstract_canon_sha256":"92e4db654df3469a5a30b763dafa8a84a33eb3f6aaeeaad0caf95d3d2fd1ecd1"},"schema_version":"1.0"},"canonical_sha256":"df33cb6eb89efc89e2c5e7f335d1ea615b78feb14c53af58ddd0bfac338a776f","source":{"kind":"arxiv","id":"1904.09671","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09671","created_at":"2026-05-17T23:48:03Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09671v1","created_at":"2026-05-17T23:48:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09671","created_at":"2026-05-17T23:48:03Z"},{"alias_kind":"pith_short_12","alias_value":"34Z4W3VYT36I","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"34Z4W3VYT36ITYWF","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"34Z4W3VY","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:34Z4W3VYT36ITYWF47ZTLUPKMF","target":"record","payload":{"canonical_record":{"source":{"id":"1904.09671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-21T22:45:04Z","cross_cats_sorted":["cs.IR","cs.SI","stat.ML"],"title_canon_sha256":"6e1c78bea17abcdfd0fdefb7f98042b14f51f35f0de5c85018a7639e53db926d","abstract_canon_sha256":"92e4db654df3469a5a30b763dafa8a84a33eb3f6aaeeaad0caf95d3d2fd1ecd1"},"schema_version":"1.0"},"canonical_sha256":"df33cb6eb89efc89e2c5e7f335d1ea615b78feb14c53af58ddd0bfac338a776f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:03.678446Z","signature_b64":"hn/iIJWt3BRNvnRuU+UgKl7qQhy5gtCakJbEIZf/oMv29R6Isk0McBxxuOsSXJzC8HnlMyWLAI0kgs87prBOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df33cb6eb89efc89e2c5e7f335d1ea615b78feb14c53af58ddd0bfac338a776f","last_reissued_at":"2026-05-17T23:48:03.677712Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:03.677712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.09671","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":"2026-05-17T23:48:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a01xaOliw8CUGD6cgi+pjVnZm5zuq7vYW+p3QybjLKAGGwDLGtcjNAiFu/Yd4C7Bf49hO2mEs75K3JiczEAnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:25:33.535750Z"},"content_sha256":"ae2ee35e2e24b7496b8b798e01b403320a54d95a7d6aa85a65d297a774a7e133","schema_version":"1.0","event_id":"sha256:ae2ee35e2e24b7496b8b798e01b403320a54d95a7d6aa85a65d297a774a7e133"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:34Z4W3VYT36ITYWF47ZTLUPKMF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DDGK: Learning Graph Representations for Deep Divergence Graph Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bryan Perozzi, Dustin Zelle, Rami Al-Rfou","submitted_at":"2019-04-21T22:45:04Z","abstract_excerpt":"Can neural networks learn to compare graphs without feature engineering? In this paper, we show that it is possible to learn representations for graph similarity with neither domain knowledge nor supervision (i.e.\\ feature engineering or labeled graphs). We propose Deep Divergence Graph Kernels, an unsupervised method for learning representations over graphs that encodes a relaxed notion of graph isomorphism. Our method consists of three parts. First, we learn an encoder for each anchor graph to capture its structure. Second, for each pair of graphs, we train a cross-graph attention network wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09671","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":""},"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":"2026-05-17T23:48:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IMbxTO881EsGNhuV1jSESL52vrVmRAusODqQwTqc4gyjsdAXmU6KXFFOHijUDMv2+50ZxYvPmKJwmCgDcSXCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:25:33.536126Z"},"content_sha256":"53bd6a96d5c101fe22753f47e04dfaa938ef7618a0333554a6d90c2b654daa7c","schema_version":"1.0","event_id":"sha256:53bd6a96d5c101fe22753f47e04dfaa938ef7618a0333554a6d90c2b654daa7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/34Z4W3VYT36ITYWF47ZTLUPKMF/bundle.json","state_url":"https://pith.science/pith/34Z4W3VYT36ITYWF47ZTLUPKMF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/34Z4W3VYT36ITYWF47ZTLUPKMF/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":"2026-05-25T20:25:33Z","links":{"resolver":"https://pith.science/pith/34Z4W3VYT36ITYWF47ZTLUPKMF","bundle":"https://pith.science/pith/34Z4W3VYT36ITYWF47ZTLUPKMF/bundle.json","state":"https://pith.science/pith/34Z4W3VYT36ITYWF47ZTLUPKMF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/34Z4W3VYT36ITYWF47ZTLUPKMF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:34Z4W3VYT36ITYWF47ZTLUPKMF","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":"92e4db654df3469a5a30b763dafa8a84a33eb3f6aaeeaad0caf95d3d2fd1ecd1","cross_cats_sorted":["cs.IR","cs.SI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-21T22:45:04Z","title_canon_sha256":"6e1c78bea17abcdfd0fdefb7f98042b14f51f35f0de5c85018a7639e53db926d"},"schema_version":"1.0","source":{"id":"1904.09671","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09671","created_at":"2026-05-17T23:48:03Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09671v1","created_at":"2026-05-17T23:48:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09671","created_at":"2026-05-17T23:48:03Z"},{"alias_kind":"pith_short_12","alias_value":"34Z4W3VYT36I","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"34Z4W3VYT36ITYWF","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"34Z4W3VY","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:53bd6a96d5c101fe22753f47e04dfaa938ef7618a0333554a6d90c2b654daa7c","target":"graph","created_at":"2026-05-17T23:48:03Z","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"},"paper":{"abstract_excerpt":"Can neural networks learn to compare graphs without feature engineering? In this paper, we show that it is possible to learn representations for graph similarity with neither domain knowledge nor supervision (i.e.\\ feature engineering or labeled graphs). We propose Deep Divergence Graph Kernels, an unsupervised method for learning representations over graphs that encodes a relaxed notion of graph isomorphism. Our method consists of three parts. First, we learn an encoder for each anchor graph to capture its structure. Second, for each pair of graphs, we train a cross-graph attention network wh","authors_text":"Bryan Perozzi, Dustin Zelle, Rami Al-Rfou","cross_cats":["cs.IR","cs.SI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-21T22:45:04Z","title":"DDGK: Learning Graph Representations for Deep Divergence Graph Kernels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09671","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:ae2ee35e2e24b7496b8b798e01b403320a54d95a7d6aa85a65d297a774a7e133","target":"record","created_at":"2026-05-17T23:48:03Z","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":"92e4db654df3469a5a30b763dafa8a84a33eb3f6aaeeaad0caf95d3d2fd1ecd1","cross_cats_sorted":["cs.IR","cs.SI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-21T22:45:04Z","title_canon_sha256":"6e1c78bea17abcdfd0fdefb7f98042b14f51f35f0de5c85018a7639e53db926d"},"schema_version":"1.0","source":{"id":"1904.09671","kind":"arxiv","version":1}},"canonical_sha256":"df33cb6eb89efc89e2c5e7f335d1ea615b78feb14c53af58ddd0bfac338a776f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df33cb6eb89efc89e2c5e7f335d1ea615b78feb14c53af58ddd0bfac338a776f","first_computed_at":"2026-05-17T23:48:03.677712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:03.677712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hn/iIJWt3BRNvnRuU+UgKl7qQhy5gtCakJbEIZf/oMv29R6Isk0McBxxuOsSXJzC8HnlMyWLAI0kgs87prBOBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:03.678446Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.09671","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae2ee35e2e24b7496b8b798e01b403320a54d95a7d6aa85a65d297a774a7e133","sha256:53bd6a96d5c101fe22753f47e04dfaa938ef7618a0333554a6d90c2b654daa7c"],"state_sha256":"0c4905ea303835c657e21b6024d9b37cceb765172a08dd7e72bb33cee750847f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ible8Tdc6O4MKfuFT9a7yI6kijbHOjW8zZGKUYh7gjKNcm8r+BafxEih6tjhkFZZHuxO/lNYlPbvy5Zy+gfmAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:25:33.538915Z","bundle_sha256":"cdd5363cc84fadf30ace1875fa21623718bbfc146d908b475eeed00f90b4f2cc"}}