{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2KGVLOBNVIODGRMMLWCOYUV6HR","short_pith_number":"pith:2KGVLOBN","schema_version":"1.0","canonical_sha256":"d28d55b82daa1c33458c5d84ec52be3c57b8e6d6dee89008b40ae2a2471bde2a","source":{"kind":"arxiv","id":"2203.16162","version":2},"attestation_state":"computed","paper":{"title":"AdaGrid: Adaptive Grid Search for Link Prediction Training Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Jiaxuan You, Jure Leskovec, Mohammadreza Banaei, R\\'emi Lebret, Tim Po\\v{s}tuvan","submitted_at":"2022-03-30T09:24:17Z","abstract_excerpt":"One of the most important factors that contribute to the success of a machine learning model is a good training objective. Training objective crucially influences the model's performance and generalization capabilities. This paper specifically focuses on graph neural network training objective for link prediction, which has not been explored in the existing literature. Here, the training objective includes, among others, a negative sampling strategy, and various hyperparameters, such as edge message ratio which controls how training edges are used. Commonly, these hyperparameters are fine-tune"},"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":"2203.16162","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-30T09:24:17Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"c09d10e6650cddd026c159655b484207728b3782149ce018040e1e02c191b2cb","abstract_canon_sha256":"52a3eb1182427065e5748064e4bc80202024aa667180f7141c7191c2c0a7e12f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:11.979423Z","signature_b64":"O2ximIpHup5X566UB4Baqyj7GbQCSsoPgKX+9+fdXXy9xbkKa5iRYuN1in/lZRwdwLAXbDjlWC952jCD/+/BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d28d55b82daa1c33458c5d84ec52be3c57b8e6d6dee89008b40ae2a2471bde2a","last_reissued_at":"2026-07-05T04:21:11.978920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:11.978920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaGrid: Adaptive Grid Search for Link Prediction Training Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Jiaxuan You, Jure Leskovec, Mohammadreza Banaei, R\\'emi Lebret, Tim Po\\v{s}tuvan","submitted_at":"2022-03-30T09:24:17Z","abstract_excerpt":"One of the most important factors that contribute to the success of a machine learning model is a good training objective. Training objective crucially influences the model's performance and generalization capabilities. This paper specifically focuses on graph neural network training objective for link prediction, which has not been explored in the existing literature. Here, the training objective includes, among others, a negative sampling strategy, and various hyperparameters, such as edge message ratio which controls how training edges are used. Commonly, these hyperparameters are fine-tune"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16162","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/2203.16162/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":"2203.16162","created_at":"2026-07-05T04:21:11.978991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16162v2","created_at":"2026-07-05T04:21:11.978991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16162","created_at":"2026-07-05T04:21:11.978991+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KGVLOBNVIOD","created_at":"2026-07-05T04:21:11.978991+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KGVLOBNVIODGRMM","created_at":"2026-07-05T04:21:11.978991+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KGVLOBN","created_at":"2026-07-05T04:21:11.978991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21124","citing_title":"Quantum Adaptive Search: A Hybrid Quantum-Classical Algorithm for Global Optimization of Multivariate Functions","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KGVLOBNVIODGRMMLWCOYUV6HR","json":"https://pith.science/pith/2KGVLOBNVIODGRMMLWCOYUV6HR.json","graph_json":"https://pith.science/api/pith-number/2KGVLOBNVIODGRMMLWCOYUV6HR/graph.json","events_json":"https://pith.science/api/pith-number/2KGVLOBNVIODGRMMLWCOYUV6HR/events.json","paper":"https://pith.science/paper/2KGVLOBN"},"agent_actions":{"view_html":"https://pith.science/pith/2KGVLOBNVIODGRMMLWCOYUV6HR","download_json":"https://pith.science/pith/2KGVLOBNVIODGRMMLWCOYUV6HR.json","view_paper":"https://pith.science/paper/2KGVLOBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16162&json=true","fetch_graph":"https://pith.science/api/pith-number/2KGVLOBNVIODGRMMLWCOYUV6HR/graph.json","fetch_events":"https://pith.science/api/pith-number/2KGVLOBNVIODGRMMLWCOYUV6HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KGVLOBNVIODGRMMLWCOYUV6HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KGVLOBNVIODGRMMLWCOYUV6HR/action/storage_attestation","attest_author":"https://pith.science/pith/2KGVLOBNVIODGRMMLWCOYUV6HR/action/author_attestation","sign_citation":"https://pith.science/pith/2KGVLOBNVIODGRMMLWCOYUV6HR/action/citation_signature","submit_replication":"https://pith.science/pith/2KGVLOBNVIODGRMMLWCOYUV6HR/action/replication_record"}},"created_at":"2026-07-05T04:21:11.978991+00:00","updated_at":"2026-07-05T04:21:11.978991+00:00"}