{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VARM5ZUHUAWFD3N27VIQPRYN2F","short_pith_number":"pith:VARM5ZUH","schema_version":"1.0","canonical_sha256":"a822cee687a02c51edbafd5107c70dd154b3f03ac0cc235e25b40d776749f06c","source":{"kind":"arxiv","id":"1905.06214","version":3},"attestation_state":"computed","paper":{"title":"GMNN: Graph Markov Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Tang, Meng Qu, Yoshua Bengio","submitted_at":"2019-05-15T14:39:33Z","abstract_excerpt":"This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutional networks). Statistical relational learning methods can effectively model the dependency of object labels through conditional random fields for collective classification, whereas graph neural networks learn effective object representations for classification through end-to-end t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.06214","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T14:39:33Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"6dba4cf9213d3cdcae0d6334366f24cccb43fcb976e2ba5519baf27a1f1e70a0","abstract_canon_sha256":"326f24b97b062b5d7d0b5dceda552edc04f479e9a981f456c89dcc520fe3fab4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:45.765274Z","signature_b64":"7X3+a5o6P8iS+sChpG78QA8/9bajvfMxo638rZ7QG+DbsVUjh4HQn5VP9UCXjaGGuUpd8fmW3fiCst0u2e1GAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a822cee687a02c51edbafd5107c70dd154b3f03ac0cc235e25b40d776749f06c","last_reissued_at":"2026-07-05T01:21:45.764799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:45.764799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GMNN: Graph Markov Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Tang, Meng Qu, Yoshua Bengio","submitted_at":"2019-05-15T14:39:33Z","abstract_excerpt":"This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutional networks). Statistical relational learning methods can effectively model the dependency of object labels through conditional random fields for collective classification, whereas graph neural networks learn effective object representations for classification through end-to-end t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06214","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/1905.06214/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.06214","created_at":"2026-07-05T01:21:45.764858+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.06214v3","created_at":"2026-07-05T01:21:45.764858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06214","created_at":"2026-07-05T01:21:45.764858+00:00"},{"alias_kind":"pith_short_12","alias_value":"VARM5ZUHUAWF","created_at":"2026-07-05T01:21:45.764858+00:00"},{"alias_kind":"pith_short_16","alias_value":"VARM5ZUHUAWFD3N2","created_at":"2026-07-05T01:21:45.764858+00:00"},{"alias_kind":"pith_short_8","alias_value":"VARM5ZUH","created_at":"2026-07-05T01:21:45.764858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.17641","citing_title":"PTCL: Pseudo-Label Temporal Curriculum Learning for Label-Limited Dynamic Graph","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VARM5ZUHUAWFD3N27VIQPRYN2F","json":"https://pith.science/pith/VARM5ZUHUAWFD3N27VIQPRYN2F.json","graph_json":"https://pith.science/api/pith-number/VARM5ZUHUAWFD3N27VIQPRYN2F/graph.json","events_json":"https://pith.science/api/pith-number/VARM5ZUHUAWFD3N27VIQPRYN2F/events.json","paper":"https://pith.science/paper/VARM5ZUH"},"agent_actions":{"view_html":"https://pith.science/pith/VARM5ZUHUAWFD3N27VIQPRYN2F","download_json":"https://pith.science/pith/VARM5ZUHUAWFD3N27VIQPRYN2F.json","view_paper":"https://pith.science/paper/VARM5ZUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.06214&json=true","fetch_graph":"https://pith.science/api/pith-number/VARM5ZUHUAWFD3N27VIQPRYN2F/graph.json","fetch_events":"https://pith.science/api/pith-number/VARM5ZUHUAWFD3N27VIQPRYN2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VARM5ZUHUAWFD3N27VIQPRYN2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VARM5ZUHUAWFD3N27VIQPRYN2F/action/storage_attestation","attest_author":"https://pith.science/pith/VARM5ZUHUAWFD3N27VIQPRYN2F/action/author_attestation","sign_citation":"https://pith.science/pith/VARM5ZUHUAWFD3N27VIQPRYN2F/action/citation_signature","submit_replication":"https://pith.science/pith/VARM5ZUHUAWFD3N27VIQPRYN2F/action/replication_record"}},"created_at":"2026-07-05T01:21:45.764858+00:00","updated_at":"2026-07-05T01:21:45.764858+00:00"}