{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CUA3P5OQXZ435IQUDISJABQRCA","short_pith_number":"pith:CUA3P5OQ","canonical_record":{"source":{"id":"2501.08361","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T10:04:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"22d1c36cd69e87250d91408d2da0e9e5c0fa841a6d327963d2f03606eea5e7d7","abstract_canon_sha256":"63f5314d3097acc8d328b28695c034132288a0c55c3212eab77da1504d789dab"},"schema_version":"1.0"},"canonical_sha256":"1501b7f5d0be79bea2141a249006111006a1972ccce3e743d447b61d2bde7f5d","source":{"kind":"arxiv","id":"2501.08361","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08361","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08361v1","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08361","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"CUA3P5OQXZ43","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"CUA3P5OQXZ435IQU","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"CUA3P5OQ","created_at":"2026-07-05T10:01:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CUA3P5OQXZ435IQUDISJABQRCA","target":"record","payload":{"canonical_record":{"source":{"id":"2501.08361","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T10:04:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"22d1c36cd69e87250d91408d2da0e9e5c0fa841a6d327963d2f03606eea5e7d7","abstract_canon_sha256":"63f5314d3097acc8d328b28695c034132288a0c55c3212eab77da1504d789dab"},"schema_version":"1.0"},"canonical_sha256":"1501b7f5d0be79bea2141a249006111006a1972ccce3e743d447b61d2bde7f5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:01.638519Z","signature_b64":"B+vg9OUmGH/s8yWbPt19L9VyBaB4f4JES7apWjHH4JG4cvx1XzvUpvcxnVVn/3ZV1LYTjKhKiNhzR35m++c8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1501b7f5d0be79bea2141a249006111006a1972ccce3e743d447b61d2bde7f5d","last_reissued_at":"2026-07-05T10:01:01.638146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:01.638146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.08361","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":"2026-07-05T10:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Owr69qTi6UpflKy0Y8SH5w6O067N3uFAYajXx25H7kn4cXcuiDRIZ5JLjBJvu7lL72fay/zvbA2icygU+zE9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:29:49.443970Z"},"content_sha256":"70f2f1f9bcef25a80033f3b8766d0096022ae12cc9e8fdf4f598464c9cd6ebfb","schema_version":"1.0","event_id":"sha256:70f2f1f9bcef25a80033f3b8766d0096022ae12cc9e8fdf4f598464c9cd6ebfb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CUA3P5OQXZ435IQUDISJABQRCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weight Averaging for Out-of-Distribution Generalization and Few-Shot Domain Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Shijian Xu","submitted_at":"2025-01-14T10:04:05Z","abstract_excerpt":"Empirical risk minimization (ERM) is not robust to changes in the distribution of data. When the distribution of test data is different from that of training data, the problem is known as out-of-distribution generalization. Recently, two techniques have been developed for addressing out-of-distribution generalization in computer vision: weight averaging (WA) and sharpness-aware minimization (SAM). WA involves training multiple models with different hyperparameters and then averaging the weights of these models, which can significantly improve out-of-distribution generalization performance. SAM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08361","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/2501.08361/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":"2026-07-05T10:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bxp+Y0v2MpuxwoHxnThCh4scxBwyCCyOPeTOML6C3OV15wWz+1Wqm9tX4CcthrXENSnYh2r3NSOL3nFFOeimBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:29:49.444557Z"},"content_sha256":"472d644c5d4e2e28cb3433476cb979bf70099889a3a5b902cace7ae6d55ce348","schema_version":"1.0","event_id":"sha256:472d644c5d4e2e28cb3433476cb979bf70099889a3a5b902cace7ae6d55ce348"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CUA3P5OQXZ435IQUDISJABQRCA/bundle.json","state_url":"https://pith.science/pith/CUA3P5OQXZ435IQUDISJABQRCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CUA3P5OQXZ435IQUDISJABQRCA/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":"2026-08-12T05:29:49Z","links":{"resolver":"https://pith.science/pith/CUA3P5OQXZ435IQUDISJABQRCA","bundle":"https://pith.science/pith/CUA3P5OQXZ435IQUDISJABQRCA/bundle.json","state":"https://pith.science/pith/CUA3P5OQXZ435IQUDISJABQRCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CUA3P5OQXZ435IQUDISJABQRCA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CUA3P5OQXZ435IQUDISJABQRCA","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":"63f5314d3097acc8d328b28695c034132288a0c55c3212eab77da1504d789dab","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T10:04:05Z","title_canon_sha256":"22d1c36cd69e87250d91408d2da0e9e5c0fa841a6d327963d2f03606eea5e7d7"},"schema_version":"1.0","source":{"id":"2501.08361","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08361","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08361v1","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08361","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"CUA3P5OQXZ43","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"CUA3P5OQXZ435IQU","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"CUA3P5OQ","created_at":"2026-07-05T10:01:01Z"}],"graph_snapshots":[{"event_id":"sha256:472d644c5d4e2e28cb3433476cb979bf70099889a3a5b902cace7ae6d55ce348","target":"graph","created_at":"2026-07-05T10:01:01Z","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/2501.08361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Empirical risk minimization (ERM) is not robust to changes in the distribution of data. When the distribution of test data is different from that of training data, the problem is known as out-of-distribution generalization. Recently, two techniques have been developed for addressing out-of-distribution generalization in computer vision: weight averaging (WA) and sharpness-aware minimization (SAM). WA involves training multiple models with different hyperparameters and then averaging the weights of these models, which can significantly improve out-of-distribution generalization performance. SAM","authors_text":"Shijian Xu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T10:04:05Z","title":"Weight Averaging for Out-of-Distribution Generalization and Few-Shot Domain Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08361","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":"sha256:70f2f1f9bcef25a80033f3b8766d0096022ae12cc9e8fdf4f598464c9cd6ebfb","target":"record","created_at":"2026-07-05T10:01:01Z","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":"63f5314d3097acc8d328b28695c034132288a0c55c3212eab77da1504d789dab","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T10:04:05Z","title_canon_sha256":"22d1c36cd69e87250d91408d2da0e9e5c0fa841a6d327963d2f03606eea5e7d7"},"schema_version":"1.0","source":{"id":"2501.08361","kind":"arxiv","version":1}},"canonical_sha256":"1501b7f5d0be79bea2141a249006111006a1972ccce3e743d447b61d2bde7f5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1501b7f5d0be79bea2141a249006111006a1972ccce3e743d447b61d2bde7f5d","first_computed_at":"2026-07-05T10:01:01.638146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:01.638146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B+vg9OUmGH/s8yWbPt19L9VyBaB4f4JES7apWjHH4JG4cvx1XzvUpvcxnVVn/3ZV1LYTjKhKiNhzR35m++c8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:01.638519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08361","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70f2f1f9bcef25a80033f3b8766d0096022ae12cc9e8fdf4f598464c9cd6ebfb","sha256:472d644c5d4e2e28cb3433476cb979bf70099889a3a5b902cace7ae6d55ce348"],"state_sha256":"8bc69d72df49f6bbd540e5a91bb0d00f847da0900b7c099b6f8eb8b5037ca124"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9vRT2OKAW2kCG4A0Ipi9fSJb6SlzfrA5kPsWtxU+03h3gp2DHVixSVfB2ViDz0IqipsOYSQNJE/EQBQ3z/ZsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T05:29:49.448592Z","bundle_sha256":"0655049b9359aa9fab8bce2857515d6787d075bc1b0cff117d562637d17de63e"}}