{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T3ZSKG37FXAYYO2WQK5D6FNVBR","short_pith_number":"pith:T3ZSKG37","schema_version":"1.0","canonical_sha256":"9ef3251b7f2dc18c3b5682ba3f15b50c480c2595dea7815d0b0f5a3d3b8638f9","source":{"kind":"arxiv","id":"2406.19092","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Stochastic Weight Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arnab Sharma, Axel-Cyrille Ngonga Ngomo, Caglar Demir","submitted_at":"2024-06-27T11:17:13Z","abstract_excerpt":"Ensemble models often improve generalization performances in challenging tasks. Yet, traditional techniques based on prediction averaging incur three well-known disadvantages: the computational overhead of training multiple models, increased latency, and memory requirements at test time. To address these issues, the Stochastic Weight Averaging (SWA) technique maintains a running average of model parameters from a specific epoch onward. Despite its potential benefits, maintaining a running average of parameters can hinder generalization, as an underlying running model begins to overfit. Convers"},"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":"2406.19092","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-27T11:17:13Z","cross_cats_sorted":[],"title_canon_sha256":"39365e50b43214edfc6f9356f2593e5433f86c5164e089a22c77d25c2e8fe0c8","abstract_canon_sha256":"43ed020498b37ce3e4df8be69d77d391da5b10b0fdaae51cd16be684417c6e85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:30.006589Z","signature_b64":"eMVOIdwQxtMEnGmtsY3y4aqb27V+s2FH2QG4Lhk/+4G7AQDRlkLGtW7db6p8qGpV6H/ArelPT35Ptg8QlBJpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ef3251b7f2dc18c3b5682ba3f15b50c480c2595dea7815d0b0f5a3d3b8638f9","last_reissued_at":"2026-07-05T08:37:30.006015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:30.006015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Stochastic Weight Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arnab Sharma, Axel-Cyrille Ngonga Ngomo, Caglar Demir","submitted_at":"2024-06-27T11:17:13Z","abstract_excerpt":"Ensemble models often improve generalization performances in challenging tasks. Yet, traditional techniques based on prediction averaging incur three well-known disadvantages: the computational overhead of training multiple models, increased latency, and memory requirements at test time. To address these issues, the Stochastic Weight Averaging (SWA) technique maintains a running average of model parameters from a specific epoch onward. Despite its potential benefits, maintaining a running average of parameters can hinder generalization, as an underlying running model begins to overfit. Convers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19092","kind":"arxiv","version":1},"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/2406.19092/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":"2406.19092","created_at":"2026-07-05T08:37:30.006095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19092v1","created_at":"2026-07-05T08:37:30.006095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19092","created_at":"2026-07-05T08:37:30.006095+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3ZSKG37FXAY","created_at":"2026-07-05T08:37:30.006095+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3ZSKG37FXAYYO2W","created_at":"2026-07-05T08:37:30.006095+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3ZSKG37","created_at":"2026-07-05T08:37:30.006095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.23104","citing_title":"DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR","json":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR.json","graph_json":"https://pith.science/api/pith-number/T3ZSKG37FXAYYO2WQK5D6FNVBR/graph.json","events_json":"https://pith.science/api/pith-number/T3ZSKG37FXAYYO2WQK5D6FNVBR/events.json","paper":"https://pith.science/paper/T3ZSKG37"},"agent_actions":{"view_html":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR","download_json":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR.json","view_paper":"https://pith.science/paper/T3ZSKG37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19092&json=true","fetch_graph":"https://pith.science/api/pith-number/T3ZSKG37FXAYYO2WQK5D6FNVBR/graph.json","fetch_events":"https://pith.science/api/pith-number/T3ZSKG37FXAYYO2WQK5D6FNVBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/action/storage_attestation","attest_author":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/action/author_attestation","sign_citation":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/action/citation_signature","submit_replication":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/action/replication_record"}},"created_at":"2026-07-05T08:37:30.006095+00:00","updated_at":"2026-07-05T08:37:30.006095+00:00"}