{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VNU3SMRQ5R4LJAOACXHC6JI6SS","short_pith_number":"pith:VNU3SMRQ","canonical_record":{"source":{"id":"1803.10459","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-28T08:37:25Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SI"],"title_canon_sha256":"f43fab92d433658ef6cc48b994a8cc43a1d3e9ca404af588b85789f051bb9417","abstract_canon_sha256":"96991d5134dce294cab010d408cc52d7d2c15cbfee32e2069743cc3c0a014a88"},"schema_version":"1.0"},"canonical_sha256":"ab69b93230ec78b481c015ce2f251e948440e04d1eb19b7d86888365d3a4590e","source":{"kind":"arxiv","id":"1803.10459","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10459","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10459v4","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10459","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"VNU3SMRQ5R4L","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VNU3SMRQ5R4LJAOA","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VNU3SMRQ","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VNU3SMRQ5R4LJAOACXHC6JI6SS","target":"record","payload":{"canonical_record":{"source":{"id":"1803.10459","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-28T08:37:25Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SI"],"title_canon_sha256":"f43fab92d433658ef6cc48b994a8cc43a1d3e9ca404af588b85789f051bb9417","abstract_canon_sha256":"96991d5134dce294cab010d408cc52d7d2c15cbfee32e2069743cc3c0a014a88"},"schema_version":"1.0"},"canonical_sha256":"ab69b93230ec78b481c015ce2f251e948440e04d1eb19b7d86888365d3a4590e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:09.740662Z","signature_b64":"Zah5C+1Kkymb8s/CrDCBxRFWUftbFQz8R2nlpGgRok5hKNbYYlhwhI6xTG5fbHYT1e1xlPXtChrzUJIuq9OtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab69b93230ec78b481c015ce2f251e948440e04d1eb19b7d86888365d3a4590e","last_reissued_at":"2026-05-17T23:46:09.740257Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:09.740257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.10459","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":"2026-05-17T23:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1/5Q9bdGeSOBekeWx0lBt0XuDMbHljDM7I5F/BicYU7SCl3SJIxuQzbkulENnp8YkXrcd3YVYP4rqoXkNVwjAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:54:09.096564Z"},"content_sha256":"b6e653e315e55e1e1407f96a73835984bb3fc6f7a94059b0131f97d705d93840","schema_version":"1.0","event_id":"sha256:b6e653e315e55e1e1407f96a73835984bb3fc6f7a94059b0131f97d705d93840"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VNU3SMRQ5R4LJAOACXHC6JI6SS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graphite: Iterative Generative Modeling of Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.SI"],"primary_cat":"stat.ML","authors_text":"Aaron Zweig, Aditya Grover, Stefano Ermon","submitted_at":"2018-03-28T08:37:25Z","abstract_excerpt":"Graphs are a fundamental abstraction for modeling relational data. However, graphs are discrete and combinatorial in nature, and learning representations suitable for machine learning tasks poses statistical and computational challenges. In this work, we propose Graphite, an algorithmic framework for unsupervised learning of representations over nodes in large graphs using deep latent variable generative models. Our model parameterizes variational autoencoders (VAE) with graph neural networks, and uses a novel iterative graph refinement strategy inspired by low-rank approximations for decoding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10459","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":""},"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":"2026-05-17T23:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XopBDKkjow+woDiZLx+l2pKZx+Qn2lDVUpg1dj25EBOtb6ugdzQI0oGRXO6h80Immovj0uV7sgksKq1JUZlTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:54:09.097250Z"},"content_sha256":"ee7ce2acf8f554e315bbfe9e0ce6e5f15601303dec9434104149a1b0288033b0","schema_version":"1.0","event_id":"sha256:ee7ce2acf8f554e315bbfe9e0ce6e5f15601303dec9434104149a1b0288033b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VNU3SMRQ5R4LJAOACXHC6JI6SS/bundle.json","state_url":"https://pith.science/pith/VNU3SMRQ5R4LJAOACXHC6JI6SS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VNU3SMRQ5R4LJAOACXHC6JI6SS/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":"2026-05-27T13:54:09Z","links":{"resolver":"https://pith.science/pith/VNU3SMRQ5R4LJAOACXHC6JI6SS","bundle":"https://pith.science/pith/VNU3SMRQ5R4LJAOACXHC6JI6SS/bundle.json","state":"https://pith.science/pith/VNU3SMRQ5R4LJAOACXHC6JI6SS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VNU3SMRQ5R4LJAOACXHC6JI6SS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VNU3SMRQ5R4LJAOACXHC6JI6SS","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":"96991d5134dce294cab010d408cc52d7d2c15cbfee32e2069743cc3c0a014a88","cross_cats_sorted":["cs.LG","cs.NE","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-28T08:37:25Z","title_canon_sha256":"f43fab92d433658ef6cc48b994a8cc43a1d3e9ca404af588b85789f051bb9417"},"schema_version":"1.0","source":{"id":"1803.10459","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10459","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10459v4","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10459","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"VNU3SMRQ5R4L","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VNU3SMRQ5R4LJAOA","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VNU3SMRQ","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:ee7ce2acf8f554e315bbfe9e0ce6e5f15601303dec9434104149a1b0288033b0","target":"graph","created_at":"2026-05-17T23:46:09Z","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":"Graphs are a fundamental abstraction for modeling relational data. However, graphs are discrete and combinatorial in nature, and learning representations suitable for machine learning tasks poses statistical and computational challenges. In this work, we propose Graphite, an algorithmic framework for unsupervised learning of representations over nodes in large graphs using deep latent variable generative models. Our model parameterizes variational autoencoders (VAE) with graph neural networks, and uses a novel iterative graph refinement strategy inspired by low-rank approximations for decoding","authors_text":"Aaron Zweig, Aditya Grover, Stefano Ermon","cross_cats":["cs.LG","cs.NE","cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-28T08:37:25Z","title":"Graphite: Iterative Generative Modeling of Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10459","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:b6e653e315e55e1e1407f96a73835984bb3fc6f7a94059b0131f97d705d93840","target":"record","created_at":"2026-05-17T23:46:09Z","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":"96991d5134dce294cab010d408cc52d7d2c15cbfee32e2069743cc3c0a014a88","cross_cats_sorted":["cs.LG","cs.NE","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-28T08:37:25Z","title_canon_sha256":"f43fab92d433658ef6cc48b994a8cc43a1d3e9ca404af588b85789f051bb9417"},"schema_version":"1.0","source":{"id":"1803.10459","kind":"arxiv","version":4}},"canonical_sha256":"ab69b93230ec78b481c015ce2f251e948440e04d1eb19b7d86888365d3a4590e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab69b93230ec78b481c015ce2f251e948440e04d1eb19b7d86888365d3a4590e","first_computed_at":"2026-05-17T23:46:09.740257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:09.740257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zah5C+1Kkymb8s/CrDCBxRFWUftbFQz8R2nlpGgRok5hKNbYYlhwhI6xTG5fbHYT1e1xlPXtChrzUJIuq9OtDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:09.740662Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.10459","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6e653e315e55e1e1407f96a73835984bb3fc6f7a94059b0131f97d705d93840","sha256:ee7ce2acf8f554e315bbfe9e0ce6e5f15601303dec9434104149a1b0288033b0"],"state_sha256":"c956dc6eca75340f2affacecda1daf9f6f2f9933e81d29e4c30277ffd9bc951c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DzSzMTjl6H6qcyV2VR+koHXcCaCuxWzxsyTN0UBWSDrwQtYotHpKrNMfxEAlIvZwQD62CWvhPqIEdT7N/8TjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:54:09.100932Z","bundle_sha256":"825ad29de624a7ef39b83029519d2ca0e2303c1dd8f5ce65e6a770ff26dc209d"}}