{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XEWSQG7ANNIKIPDPGOGJNNFQBZ","short_pith_number":"pith:XEWSQG7A","canonical_record":{"source":{"id":"2508.14079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T19:38:35Z","cross_cats_sorted":[],"title_canon_sha256":"bc9f50f824e90790d474f58c4726bf91ff8dcaf7d8e9fef559a8d798c6e26f2a","abstract_canon_sha256":"6633065242592bfec00a6d7c7d590d145cda32f6aedd33c1374d60d73c3270f4"},"schema_version":"1.0"},"canonical_sha256":"b92d281be06b50a43c6f338c96b4b00e5996b6c8fd035cc017997fb2b7dccf20","source":{"kind":"arxiv","id":"2508.14079","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14079","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14079v1","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14079","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_12","alias_value":"XEWSQG7ANNIK","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_16","alias_value":"XEWSQG7ANNIKIPDP","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_8","alias_value":"XEWSQG7A","created_at":"2026-07-05T11:56:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XEWSQG7ANNIKIPDPGOGJNNFQBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2508.14079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T19:38:35Z","cross_cats_sorted":[],"title_canon_sha256":"bc9f50f824e90790d474f58c4726bf91ff8dcaf7d8e9fef559a8d798c6e26f2a","abstract_canon_sha256":"6633065242592bfec00a6d7c7d590d145cda32f6aedd33c1374d60d73c3270f4"},"schema_version":"1.0"},"canonical_sha256":"b92d281be06b50a43c6f338c96b4b00e5996b6c8fd035cc017997fb2b7dccf20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:24.628448Z","signature_b64":"QlxTiSiaSPCL5DhpqGtC07JRLn3XCPRSxaHg37A8lADJrr63teHQqTwUvL7gLVqyJYCNBixLqvSKEJg+UqmkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b92d281be06b50a43c6f338c96b4b00e5996b6c8fd035cc017997fb2b7dccf20","last_reissued_at":"2026-07-05T11:56:24.627887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:24.627887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.14079","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":"2026-07-05T11:56:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SX7itcI3I1HdyvUkURTcq6fosxH+zyIHst9bscddWq8uY/CHoKkm5hGOexKZPPmUK3YMauZu8+ntLO607ZFACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T04:47:55.755622Z"},"content_sha256":"98ae2d3e04c255e609e962a54e93adef393898ab90a7f2987e6657d931a7c499","schema_version":"1.0","event_id":"sha256:98ae2d3e04c255e609e962a54e93adef393898ab90a7f2987e6657d931a7c499"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XEWSQG7ANNIKIPDPGOGJNNFQBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Larouche, Audrey Durand, Christian Gagn\\'e, Irina Rish, Jonas Ngnaw\\'e, Maxime Heuillet, Ola Ahmad, Rishika Bhagwatkar, Yann Pequignot","submitted_at":"2025-08-12T19:38:35Z","abstract_excerpt":"Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized loss objectives. Recently, robust fine-tuning has emerged as a more efficient alternative: instead of training from scratch, pretrained models are adapted to maximize predictive performance and robustness. To conduct robust fine-tuning, practitioners design an optimization strategy that includes the model update protocol (e.g., full or partial) and the special"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14079","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/2508.14079/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":"2026-07-05T11:56:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EYKeGY/97FIFq73duShNiOgIlJ2seV5WYYJP5hjXK3A9yRhxOyhSvNKGVoOB1r+MBqvv1zGHY9soHm1dJ2YaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T04:47:55.756002Z"},"content_sha256":"c7dd3b379bd4e65188e979b8ffff8b32552cdd2789cf26294c68fea8faee6595","schema_version":"1.0","event_id":"sha256:c7dd3b379bd4e65188e979b8ffff8b32552cdd2789cf26294c68fea8faee6595"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XEWSQG7ANNIKIPDPGOGJNNFQBZ/bundle.json","state_url":"https://pith.science/pith/XEWSQG7ANNIKIPDPGOGJNNFQBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XEWSQG7ANNIKIPDPGOGJNNFQBZ/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":"2026-07-10T04:47:55Z","links":{"resolver":"https://pith.science/pith/XEWSQG7ANNIKIPDPGOGJNNFQBZ","bundle":"https://pith.science/pith/XEWSQG7ANNIKIPDPGOGJNNFQBZ/bundle.json","state":"https://pith.science/pith/XEWSQG7ANNIKIPDPGOGJNNFQBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XEWSQG7ANNIKIPDPGOGJNNFQBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XEWSQG7ANNIKIPDPGOGJNNFQBZ","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":"6633065242592bfec00a6d7c7d590d145cda32f6aedd33c1374d60d73c3270f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T19:38:35Z","title_canon_sha256":"bc9f50f824e90790d474f58c4726bf91ff8dcaf7d8e9fef559a8d798c6e26f2a"},"schema_version":"1.0","source":{"id":"2508.14079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14079","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14079v1","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14079","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_12","alias_value":"XEWSQG7ANNIK","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_16","alias_value":"XEWSQG7ANNIKIPDP","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_8","alias_value":"XEWSQG7A","created_at":"2026-07-05T11:56:24Z"}],"graph_snapshots":[{"event_id":"sha256:c7dd3b379bd4e65188e979b8ffff8b32552cdd2789cf26294c68fea8faee6595","target":"graph","created_at":"2026-07-05T11:56:24Z","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/2508.14079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized loss objectives. Recently, robust fine-tuning has emerged as a more efficient alternative: instead of training from scratch, pretrained models are adapted to maximize predictive performance and robustness. To conduct robust fine-tuning, practitioners design an optimization strategy that includes the model update protocol (e.g., full or partial) and the special","authors_text":"Alexandre Larouche, Audrey Durand, Christian Gagn\\'e, Irina Rish, Jonas Ngnaw\\'e, Maxime Heuillet, Ola Ahmad, Rishika Bhagwatkar, Yann Pequignot","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T19:38:35Z","title":"A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14079","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":"sha256:98ae2d3e04c255e609e962a54e93adef393898ab90a7f2987e6657d931a7c499","target":"record","created_at":"2026-07-05T11:56:24Z","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":"6633065242592bfec00a6d7c7d590d145cda32f6aedd33c1374d60d73c3270f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T19:38:35Z","title_canon_sha256":"bc9f50f824e90790d474f58c4726bf91ff8dcaf7d8e9fef559a8d798c6e26f2a"},"schema_version":"1.0","source":{"id":"2508.14079","kind":"arxiv","version":1}},"canonical_sha256":"b92d281be06b50a43c6f338c96b4b00e5996b6c8fd035cc017997fb2b7dccf20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b92d281be06b50a43c6f338c96b4b00e5996b6c8fd035cc017997fb2b7dccf20","first_computed_at":"2026-07-05T11:56:24.627887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:24.627887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QlxTiSiaSPCL5DhpqGtC07JRLn3XCPRSxaHg37A8lADJrr63teHQqTwUvL7gLVqyJYCNBixLqvSKEJg+UqmkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:24.628448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.14079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98ae2d3e04c255e609e962a54e93adef393898ab90a7f2987e6657d931a7c499","sha256:c7dd3b379bd4e65188e979b8ffff8b32552cdd2789cf26294c68fea8faee6595"],"state_sha256":"af5851f8f5ac6ff0f23047a20740371d855a12ea7b332286fcc610f77d459479"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+2XX2t7z0GzTEDh/O2DZqui5QUoYsfFzSAvcH4SOsVdOEXWYvnTJJYL9/3i71eB4dAzuZiOaubmh6KEstMP3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T04:47:55.758047Z","bundle_sha256":"0e03c7be044526e074168e41a12e126a209923d0c7d59479f5a2496ad73f6670"}}