{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6OUR5AALF5WESPLWICBBL4T6LH","short_pith_number":"pith:6OUR5AAL","schema_version":"1.0","canonical_sha256":"f3a91e800b2f6c493d76408215f27e59cbf21c803c1e8183ffe7aa4ec874e5bc","source":{"kind":"arxiv","id":"2008.05000","version":3},"attestation_state":"computed","paper":{"title":"Degree-Quant: Quantization-Aware Training for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Javier Fernandez-Marques, Nicholas D. Lane, Shyam A. Tailor","submitted_at":"2020-08-11T20:53:50Z","abstract_excerpt":"Graph neural networks (GNNs) have demonstrated strong performance on a wide variety of tasks due to their ability to model non-uniform structured data. Despite their promise, there exists little research exploring methods to make them more efficient at inference time. In this work, we explore the viability of training quantized GNNs, enabling the usage of low precision integer arithmetic during inference. We identify the sources of error that uniquely arise when attempting to quantize GNNs, and propose an architecturally-agnostic method, Degree-Quant, to improve performance over existing quant"},"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":"2008.05000","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-11T20:53:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6e4f4afd8e1d1020a30d9b0ce344faba5a022d5208e482a07b52daa268b30ba9","abstract_canon_sha256":"5f33293505614539ab7d38619af92d16d6158f7f139433232e1946b1f1af7fce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:56.835777Z","signature_b64":"IyDXN4aMQcs1t63FDuQ7R8UUKHMXwCYdT/cjJLEbD5IcI5zofvWXxQ0O/tp+UYiMkh+2+unwZE1qHDKb37dGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3a91e800b2f6c493d76408215f27e59cbf21c803c1e8183ffe7aa4ec874e5bc","last_reissued_at":"2026-07-05T02:22:56.835334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:56.835334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Degree-Quant: Quantization-Aware Training for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Javier Fernandez-Marques, Nicholas D. Lane, Shyam A. Tailor","submitted_at":"2020-08-11T20:53:50Z","abstract_excerpt":"Graph neural networks (GNNs) have demonstrated strong performance on a wide variety of tasks due to their ability to model non-uniform structured data. Despite their promise, there exists little research exploring methods to make them more efficient at inference time. In this work, we explore the viability of training quantized GNNs, enabling the usage of low precision integer arithmetic during inference. We identify the sources of error that uniquely arise when attempting to quantize GNNs, and propose an architecturally-agnostic method, Degree-Quant, to improve performance over existing quant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05000","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/2008.05000/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":"2008.05000","created_at":"2026-07-05T02:22:56.835395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.05000v3","created_at":"2026-07-05T02:22:56.835395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05000","created_at":"2026-07-05T02:22:56.835395+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OUR5AALF5WE","created_at":"2026-07-05T02:22:56.835395+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OUR5AALF5WESPLW","created_at":"2026-07-05T02:22:56.835395+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OUR5AAL","created_at":"2026-07-05T02:22:56.835395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20796","citing_title":"FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OUR5AALF5WESPLWICBBL4T6LH","json":"https://pith.science/pith/6OUR5AALF5WESPLWICBBL4T6LH.json","graph_json":"https://pith.science/api/pith-number/6OUR5AALF5WESPLWICBBL4T6LH/graph.json","events_json":"https://pith.science/api/pith-number/6OUR5AALF5WESPLWICBBL4T6LH/events.json","paper":"https://pith.science/paper/6OUR5AAL"},"agent_actions":{"view_html":"https://pith.science/pith/6OUR5AALF5WESPLWICBBL4T6LH","download_json":"https://pith.science/pith/6OUR5AALF5WESPLWICBBL4T6LH.json","view_paper":"https://pith.science/paper/6OUR5AAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.05000&json=true","fetch_graph":"https://pith.science/api/pith-number/6OUR5AALF5WESPLWICBBL4T6LH/graph.json","fetch_events":"https://pith.science/api/pith-number/6OUR5AALF5WESPLWICBBL4T6LH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OUR5AALF5WESPLWICBBL4T6LH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OUR5AALF5WESPLWICBBL4T6LH/action/storage_attestation","attest_author":"https://pith.science/pith/6OUR5AALF5WESPLWICBBL4T6LH/action/author_attestation","sign_citation":"https://pith.science/pith/6OUR5AALF5WESPLWICBBL4T6LH/action/citation_signature","submit_replication":"https://pith.science/pith/6OUR5AALF5WESPLWICBBL4T6LH/action/replication_record"}},"created_at":"2026-07-05T02:22:56.835395+00:00","updated_at":"2026-07-05T02:22:56.835395+00:00"}