{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T3ZSKG37FXAYYO2WQK5D6FNVBR","short_pith_number":"pith:T3ZSKG37","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"},"canonical_sha256":"9ef3251b7f2dc18c3b5682ba3f15b50c480c2595dea7815d0b0f5a3d3b8638f9","source":{"kind":"arxiv","id":"2406.19092","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19092","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19092v1","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19092","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"pith_short_12","alias_value":"T3ZSKG37FXAY","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"pith_short_16","alias_value":"T3ZSKG37FXAYYO2W","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"pith_short_8","alias_value":"T3ZSKG37","created_at":"2026-07-05T08:37:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T3ZSKG37FXAYYO2WQK5D6FNVBR","target":"record","payload":{"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"},"canonical_sha256":"9ef3251b7f2dc18c3b5682ba3f15b50c480c2595dea7815d0b0f5a3d3b8638f9","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"},"source_kind":"arxiv","source_id":"2406.19092","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y3qkb3HUfAQJwXOjmNWcDRcGpwA6y4MS2TsN6u3hmQJ/DM8fxPSXDvhtrXnypWwajakV3cB4cfur7e00TykxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:37:19.330668Z"},"content_sha256":"1d81d159b2ce021a38c49d594b52c6a99cc3583e047fcd1e71a26aa66e3673ca","schema_version":"1.0","event_id":"sha256:1d81d159b2ce021a38c49d594b52c6a99cc3583e047fcd1e71a26aa66e3673ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T3ZSKG37FXAYYO2WQK5D6FNVBR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Ipv3t/HgVz8uBHaTT+bGv4k8suTOchta1mWbLR+Novr2uogPcZoEIhuPrPhME+REeBvDm1PVrHQ8Ju1lGmRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:37:19.331564Z"},"content_sha256":"e10feef3611a0c77db8cd8573e61a326448e9d9090318f94855f86c4d611cec6","schema_version":"1.0","event_id":"sha256:e10feef3611a0c77db8cd8573e61a326448e9d9090318f94855f86c4d611cec6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/bundle.json","state_url":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T11:37:19Z","links":{"resolver":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR","bundle":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/bundle.json","state":"https://pith.science/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T3ZSKG37FXAYYO2WQK5D6FNVBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T3ZSKG37FXAYYO2WQK5D6FNVBR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"43ed020498b37ce3e4df8be69d77d391da5b10b0fdaae51cd16be684417c6e85","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-27T11:17:13Z","title_canon_sha256":"39365e50b43214edfc6f9356f2593e5433f86c5164e089a22c77d25c2e8fe0c8"},"schema_version":"1.0","source":{"id":"2406.19092","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19092","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19092v1","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19092","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"pith_short_12","alias_value":"T3ZSKG37FXAY","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"pith_short_16","alias_value":"T3ZSKG37FXAYYO2W","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"pith_short_8","alias_value":"T3ZSKG37","created_at":"2026-07-05T08:37:30Z"}],"graph_snapshots":[{"event_id":"sha256:e10feef3611a0c77db8cd8573e61a326448e9d9090318f94855f86c4d611cec6","target":"graph","created_at":"2026-07-05T08:37:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.19092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arnab Sharma, Axel-Cyrille Ngonga Ngomo, Caglar Demir","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-27T11:17:13Z","title":"Adaptive Stochastic Weight Averaging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19092","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1d81d159b2ce021a38c49d594b52c6a99cc3583e047fcd1e71a26aa66e3673ca","target":"record","created_at":"2026-07-05T08:37:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"43ed020498b37ce3e4df8be69d77d391da5b10b0fdaae51cd16be684417c6e85","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-27T11:17:13Z","title_canon_sha256":"39365e50b43214edfc6f9356f2593e5433f86c5164e089a22c77d25c2e8fe0c8"},"schema_version":"1.0","source":{"id":"2406.19092","kind":"arxiv","version":1}},"canonical_sha256":"9ef3251b7f2dc18c3b5682ba3f15b50c480c2595dea7815d0b0f5a3d3b8638f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ef3251b7f2dc18c3b5682ba3f15b50c480c2595dea7815d0b0f5a3d3b8638f9","first_computed_at":"2026-07-05T08:37:30.006015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:30.006015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eMVOIdwQxtMEnGmtsY3y4aqb27V+s2FH2QG4Lhk/+4G7AQDRlkLGtW7db6p8qGpV6H/ArelPT35Ptg8QlBJpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:30.006589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19092","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d81d159b2ce021a38c49d594b52c6a99cc3583e047fcd1e71a26aa66e3673ca","sha256:e10feef3611a0c77db8cd8573e61a326448e9d9090318f94855f86c4d611cec6"],"state_sha256":"0483c6cc5ab8f59b3c82d795cb2461882cf3d19a54ed6cacedca93363659da83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R57qhFa5d4HlUvPaUGRea7YIQJ1hpNqaoT4YdRiTUPd9uSTkpoFrxfQ/Z0x389zP/ujlH2ZPQKerztQeG1ZaAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:37:19.338123Z","bundle_sha256":"15b7c38bc4a360448008c2e18950e44680e2699f390c4a1c1cc248242d743c3e"}}