{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:H4O72NSB3HGCX5ZZIXTO5H6XNQ","short_pith_number":"pith:H4O72NSB","schema_version":"1.0","canonical_sha256":"3f1dfd3641d9cc2bf73945e6ee9fd76c21985d6bbfcfb12f57e4cea7ea33d8da","source":{"kind":"arxiv","id":"2103.03036","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Graph Structure Learning: Progress and Opportunities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Carl Yang, Jieyu Zhang, Jinghao Zhang, Qiang Liu, Shu Wu, Weizhi Xu, Yanqiao Zhu, Yuanqi Du","submitted_at":"2021-03-04T13:49:25Z","abstract_excerpt":"Graphs are widely used to describe real-world objects and their interactions. Graph Neural Networks (GNNs) as a de facto model for analyzing graphstructured data, are highly sensitive to the quality of the given graph structures. Therefore, noisy or incomplete graphs often lead to unsatisfactory representations and prevent us from fully understanding the mechanism underlying the system. In pursuit of an optimal graph structure for downstream tasks, recent studies have sparked an effort around the central theme of Graph Structure Learning (GSL), which aims to jointly learn an optimized graph st"},"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":"2103.03036","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T13:49:25Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"3f877af6f4fc8e48cab256ec9086adebffd5293a5efc41f37c4458b357715f12","abstract_canon_sha256":"fb856b0d5e851427009b08e876cc9ffe9f91c6178b1b8fdcd4a3609075880ba4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:45.976293Z","signature_b64":"6eZMn4Xm+u4VXatD8SNHKwjHQfCuQ4YJsuiRXiGQzbPvu9CJgkfEq59d9R+A0IIDZ5rBxyyB7WQ6N5NDPZ2xAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f1dfd3641d9cc2bf73945e6ee9fd76c21985d6bbfcfb12f57e4cea7ea33d8da","last_reissued_at":"2026-07-05T03:56:45.975813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:45.975813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Graph Structure Learning: Progress and Opportunities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Carl Yang, Jieyu Zhang, Jinghao Zhang, Qiang Liu, Shu Wu, Weizhi Xu, Yanqiao Zhu, Yuanqi Du","submitted_at":"2021-03-04T13:49:25Z","abstract_excerpt":"Graphs are widely used to describe real-world objects and their interactions. Graph Neural Networks (GNNs) as a de facto model for analyzing graphstructured data, are highly sensitive to the quality of the given graph structures. Therefore, noisy or incomplete graphs often lead to unsatisfactory representations and prevent us from fully understanding the mechanism underlying the system. In pursuit of an optimal graph structure for downstream tasks, recent studies have sparked an effort around the central theme of Graph Structure Learning (GSL), which aims to jointly learn an optimized graph st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03036","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.03036/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":"2103.03036","created_at":"2026-07-05T03:56:45.975870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.03036v2","created_at":"2026-07-05T03:56:45.975870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03036","created_at":"2026-07-05T03:56:45.975870+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4O72NSB3HGC","created_at":"2026-07-05T03:56:45.975870+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4O72NSB3HGCX5ZZ","created_at":"2026-07-05T03:56:45.975870+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4O72NSB","created_at":"2026-07-05T03:56:45.975870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17782","citing_title":"Blind Recovery of Latent Domains via Unsupervised Symmetry Discovery","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07191","citing_title":"Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Driving","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21475","citing_title":"Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18316","citing_title":"Dynamic Elliptical Graph Factor Models via Riemannian Optimization with Geodesic Temporal Regularization","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08952","citing_title":"When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H4O72NSB3HGCX5ZZIXTO5H6XNQ","json":"https://pith.science/pith/H4O72NSB3HGCX5ZZIXTO5H6XNQ.json","graph_json":"https://pith.science/api/pith-number/H4O72NSB3HGCX5ZZIXTO5H6XNQ/graph.json","events_json":"https://pith.science/api/pith-number/H4O72NSB3HGCX5ZZIXTO5H6XNQ/events.json","paper":"https://pith.science/paper/H4O72NSB"},"agent_actions":{"view_html":"https://pith.science/pith/H4O72NSB3HGCX5ZZIXTO5H6XNQ","download_json":"https://pith.science/pith/H4O72NSB3HGCX5ZZIXTO5H6XNQ.json","view_paper":"https://pith.science/paper/H4O72NSB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.03036&json=true","fetch_graph":"https://pith.science/api/pith-number/H4O72NSB3HGCX5ZZIXTO5H6XNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/H4O72NSB3HGCX5ZZIXTO5H6XNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4O72NSB3HGCX5ZZIXTO5H6XNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4O72NSB3HGCX5ZZIXTO5H6XNQ/action/storage_attestation","attest_author":"https://pith.science/pith/H4O72NSB3HGCX5ZZIXTO5H6XNQ/action/author_attestation","sign_citation":"https://pith.science/pith/H4O72NSB3HGCX5ZZIXTO5H6XNQ/action/citation_signature","submit_replication":"https://pith.science/pith/H4O72NSB3HGCX5ZZIXTO5H6XNQ/action/replication_record"}},"created_at":"2026-07-05T03:56:45.975870+00:00","updated_at":"2026-07-05T03:56:45.975870+00:00"}