{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:F2CHWT34IKRXBLBSSUOIBQODZW","short_pith_number":"pith:F2CHWT34","canonical_record":{"source":{"id":"1706.07845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2017-06-23T19:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"309a9d4e49a69c017580847ac4ef986860f34d70a9a3b029ee166419cd2895f8","abstract_canon_sha256":"bc59221df9f30b3461979fd43a22e22e0999f7cbed3ab3117b13a867a090503a"},"schema_version":"1.0"},"canonical_sha256":"2e847b4f7c42a370ac32951c80c1c3cd8f9cd9c612b6c8859c2596b6e48c3e4f","source":{"kind":"arxiv","id":"1706.07845","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.07845","created_at":"2026-05-18T00:30:28Z"},{"alias_kind":"arxiv_version","alias_value":"1706.07845v2","created_at":"2026-05-18T00:30:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.07845","created_at":"2026-05-18T00:30:28Z"},{"alias_kind":"pith_short_12","alias_value":"F2CHWT34IKRX","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"F2CHWT34IKRXBLBS","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"F2CHWT34","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:F2CHWT34IKRXBLBSSUOIBQODZW","target":"record","payload":{"canonical_record":{"source":{"id":"1706.07845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2017-06-23T19:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"309a9d4e49a69c017580847ac4ef986860f34d70a9a3b029ee166419cd2895f8","abstract_canon_sha256":"bc59221df9f30b3461979fd43a22e22e0999f7cbed3ab3117b13a867a090503a"},"schema_version":"1.0"},"canonical_sha256":"2e847b4f7c42a370ac32951c80c1c3cd8f9cd9c612b6c8859c2596b6e48c3e4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:28.054389Z","signature_b64":"oWyyRt/r30aET4tJcA9CKYHp+DyMM8TrCBFgwld25BXi/BL1y8pQvLpghaFGAMlRYKC1DULT/7yKrKvfoXJYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e847b4f7c42a370ac32951c80c1c3cd8f9cd9c612b6c8859c2596b6e48c3e4f","last_reissued_at":"2026-05-18T00:30:28.053633Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:28.053633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.07845","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5aHDccWaE8AdbifQGp7HKVGh6KD4KB831N1S6fRrczy6Edz6ESQYnrUaYkjQcuQ4EwSLAuB7dKlf2tgBXLl7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:30:56.538444Z"},"content_sha256":"dd7e19b0687389f5c48c03182cc77f8d7c4329f58713a8172d1acc66e3f5027d","schema_version":"1.0","event_id":"sha256:dd7e19b0687389f5c48c03182cc77f8d7c4329f58713a8172d1acc66e3f5027d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:F2CHWT34IKRXBLBSSUOIBQODZW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HARP: Hierarchical Representation Learning for Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SI","authors_text":"Bryan Perozzi, Haochen Chen, Steven Skiena, Yifan Hu","submitted_at":"2017-06-23T19:27:13Z","abstract_excerpt":"We present HARP, a novel method for learning low dimensional embeddings of a graph's nodes which preserves higher-order structural features. Our proposed method achieves this by compressing the input graph prior to embedding it, effectively avoiding troublesome embedding configurations (i.e. local minima) which can pose problems to non-convex optimization. HARP works by finding a smaller graph which approximates the global structure of its input. This simplified graph is used to learn a set of initial representations, which serve as good initializations for learning representations in the orig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.07845","kind":"arxiv","version":2},"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":"2026-05-18T00:30:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FYiTDHRpfhajh8k12GuiRYsC7o3Zj1/N5H6W4Tk1/deCoqMvb5Jxi2eR8eMF+HFleTUttvHBYhW/3mvVLLZ8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:30:56.539151Z"},"content_sha256":"66b247630879e2171843a3280c4ea427e955b825200251e3454b541c483ccaa1","schema_version":"1.0","event_id":"sha256:66b247630879e2171843a3280c4ea427e955b825200251e3454b541c483ccaa1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F2CHWT34IKRXBLBSSUOIBQODZW/bundle.json","state_url":"https://pith.science/pith/F2CHWT34IKRXBLBSSUOIBQODZW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F2CHWT34IKRXBLBSSUOIBQODZW/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":"2026-05-25T18:30:56Z","links":{"resolver":"https://pith.science/pith/F2CHWT34IKRXBLBSSUOIBQODZW","bundle":"https://pith.science/pith/F2CHWT34IKRXBLBSSUOIBQODZW/bundle.json","state":"https://pith.science/pith/F2CHWT34IKRXBLBSSUOIBQODZW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F2CHWT34IKRXBLBSSUOIBQODZW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:F2CHWT34IKRXBLBSSUOIBQODZW","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":"bc59221df9f30b3461979fd43a22e22e0999f7cbed3ab3117b13a867a090503a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2017-06-23T19:27:13Z","title_canon_sha256":"309a9d4e49a69c017580847ac4ef986860f34d70a9a3b029ee166419cd2895f8"},"schema_version":"1.0","source":{"id":"1706.07845","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.07845","created_at":"2026-05-18T00:30:28Z"},{"alias_kind":"arxiv_version","alias_value":"1706.07845v2","created_at":"2026-05-18T00:30:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.07845","created_at":"2026-05-18T00:30:28Z"},{"alias_kind":"pith_short_12","alias_value":"F2CHWT34IKRX","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"F2CHWT34IKRXBLBS","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"F2CHWT34","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:66b247630879e2171843a3280c4ea427e955b825200251e3454b541c483ccaa1","target":"graph","created_at":"2026-05-18T00:30:28Z","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":"We present HARP, a novel method for learning low dimensional embeddings of a graph's nodes which preserves higher-order structural features. Our proposed method achieves this by compressing the input graph prior to embedding it, effectively avoiding troublesome embedding configurations (i.e. local minima) which can pose problems to non-convex optimization. HARP works by finding a smaller graph which approximates the global structure of its input. This simplified graph is used to learn a set of initial representations, which serve as good initializations for learning representations in the orig","authors_text":"Bryan Perozzi, Haochen Chen, Steven Skiena, Yifan Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2017-06-23T19:27:13Z","title":"HARP: Hierarchical Representation Learning for Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.07845","kind":"arxiv","version":2},"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:dd7e19b0687389f5c48c03182cc77f8d7c4329f58713a8172d1acc66e3f5027d","target":"record","created_at":"2026-05-18T00:30:28Z","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":"bc59221df9f30b3461979fd43a22e22e0999f7cbed3ab3117b13a867a090503a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2017-06-23T19:27:13Z","title_canon_sha256":"309a9d4e49a69c017580847ac4ef986860f34d70a9a3b029ee166419cd2895f8"},"schema_version":"1.0","source":{"id":"1706.07845","kind":"arxiv","version":2}},"canonical_sha256":"2e847b4f7c42a370ac32951c80c1c3cd8f9cd9c612b6c8859c2596b6e48c3e4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e847b4f7c42a370ac32951c80c1c3cd8f9cd9c612b6c8859c2596b6e48c3e4f","first_computed_at":"2026-05-18T00:30:28.053633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:28.053633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oWyyRt/r30aET4tJcA9CKYHp+DyMM8TrCBFgwld25BXi/BL1y8pQvLpghaFGAMlRYKC1DULT/7yKrKvfoXJYBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:28.054389Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.07845","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd7e19b0687389f5c48c03182cc77f8d7c4329f58713a8172d1acc66e3f5027d","sha256:66b247630879e2171843a3280c4ea427e955b825200251e3454b541c483ccaa1"],"state_sha256":"033d8450dc307e8219de8f0b13b0e9eab9eae7ee6d8fa74ada53ce8c63d2718e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BA2p05XF8copzTUs2iKXiba46ZsQq7e18oQaTFzwESm55bQLZeH2/esCFpudDkjVsofJwYP852opOJHzFg86BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:30:56.543155Z","bundle_sha256":"cf79c64bb62b3830f825ef1be255a80c169b5254f4cad26bc36eef3852ceec5d"}}