{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:O35HMEEELTGJSRANITSCQM5DWD","short_pith_number":"pith:O35HMEEE","canonical_record":{"source":{"id":"2312.09020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T15:08:27Z","cross_cats_sorted":[],"title_canon_sha256":"9dac32e4550d9fe1655d628f76e4efc39e136f8ebb9c4f8eacf1f22100f4d39f","abstract_canon_sha256":"5f84968827aa452a23222bfc02f0206d50161089d4483e144435c8db362150a6"},"schema_version":"1.0"},"canonical_sha256":"76fa7610845ccc99440d44e42833a3b0d27dcac21db6bf70aedfd08305bc1a97","source":{"kind":"arxiv","id":"2312.09020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09020","created_at":"2026-07-05T07:24:13Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09020v1","created_at":"2026-07-05T07:24:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09020","created_at":"2026-07-05T07:24:13Z"},{"alias_kind":"pith_short_12","alias_value":"O35HMEEELTGJ","created_at":"2026-07-05T07:24:13Z"},{"alias_kind":"pith_short_16","alias_value":"O35HMEEELTGJSRAN","created_at":"2026-07-05T07:24:13Z"},{"alias_kind":"pith_short_8","alias_value":"O35HMEEE","created_at":"2026-07-05T07:24:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:O35HMEEELTGJSRANITSCQM5DWD","target":"record","payload":{"canonical_record":{"source":{"id":"2312.09020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T15:08:27Z","cross_cats_sorted":[],"title_canon_sha256":"9dac32e4550d9fe1655d628f76e4efc39e136f8ebb9c4f8eacf1f22100f4d39f","abstract_canon_sha256":"5f84968827aa452a23222bfc02f0206d50161089d4483e144435c8db362150a6"},"schema_version":"1.0"},"canonical_sha256":"76fa7610845ccc99440d44e42833a3b0d27dcac21db6bf70aedfd08305bc1a97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:13.096872Z","signature_b64":"SvCRhobowglDrXkhpvH+gwm0UGGnJChc8utLGRpCpj7/pmxWJWFVDKDASSKlAGPAEc8G6m0/+L8jqnR/MyFaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76fa7610845ccc99440d44e42833a3b0d27dcac21db6bf70aedfd08305bc1a97","last_reissued_at":"2026-07-05T07:24:13.096380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:13.096380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.09020","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":"2026-07-05T07:24:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jMs3vFf3EwpanbnkvknCspmMLqv9fFJpaIkDqhCd2tlmRk/JhHELjOTHXCkCrxJpX34gYjxaATu9ls6QtUfKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:51:31.067489Z"},"content_sha256":"4efb982eb03fb172c03c30b4f8bc74ae2214ff575d963a3a4fd2172c8dd2511f","schema_version":"1.0","event_id":"sha256:4efb982eb03fb172c03c30b4f8bc74ae2214ff575d963a3a4fd2172c8dd2511f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:O35HMEEELTGJSRANITSCQM5DWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Transferability for Randomized Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huishuai Zhang, Kai Qiu, Stephen Lin, Zhirong Wu","submitted_at":"2023-12-14T15:08:27Z","abstract_excerpt":"Training foundation models on extensive datasets and then finetuning them on specific tasks has emerged as the mainstream approach in artificial intelligence. However, the model robustness, which is a critical aspect for safety, is often optimized for each specific task rather than at the pretraining stage. In this paper, we propose a method for pretraining certifiably robust models that can be readily finetuned for adaptation to a particular task. A key challenge is dealing with the compromise between semantic learning and robustness. We address this with a simple yet highly effective strateg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09020","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/2312.09020/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":"2026-07-05T07:24:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j2LNhcTYaDp5OPzqwvO5MR1vPv8QtlAEJGgwfFXDmyodDGBwoG+WiOaLxFHKMgLB2fKUTgrb7c7uWfmX6qjVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:51:31.068045Z"},"content_sha256":"29ca96c6d211c3c37227859572356d6764683b18af9ae57a9872d85a5914714d","schema_version":"1.0","event_id":"sha256:29ca96c6d211c3c37227859572356d6764683b18af9ae57a9872d85a5914714d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O35HMEEELTGJSRANITSCQM5DWD/bundle.json","state_url":"https://pith.science/pith/O35HMEEELTGJSRANITSCQM5DWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O35HMEEELTGJSRANITSCQM5DWD/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":"2026-08-05T06:51:31Z","links":{"resolver":"https://pith.science/pith/O35HMEEELTGJSRANITSCQM5DWD","bundle":"https://pith.science/pith/O35HMEEELTGJSRANITSCQM5DWD/bundle.json","state":"https://pith.science/pith/O35HMEEELTGJSRANITSCQM5DWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O35HMEEELTGJSRANITSCQM5DWD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:O35HMEEELTGJSRANITSCQM5DWD","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":"5f84968827aa452a23222bfc02f0206d50161089d4483e144435c8db362150a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T15:08:27Z","title_canon_sha256":"9dac32e4550d9fe1655d628f76e4efc39e136f8ebb9c4f8eacf1f22100f4d39f"},"schema_version":"1.0","source":{"id":"2312.09020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09020","created_at":"2026-07-05T07:24:13Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09020v1","created_at":"2026-07-05T07:24:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09020","created_at":"2026-07-05T07:24:13Z"},{"alias_kind":"pith_short_12","alias_value":"O35HMEEELTGJ","created_at":"2026-07-05T07:24:13Z"},{"alias_kind":"pith_short_16","alias_value":"O35HMEEELTGJSRAN","created_at":"2026-07-05T07:24:13Z"},{"alias_kind":"pith_short_8","alias_value":"O35HMEEE","created_at":"2026-07-05T07:24:13Z"}],"graph_snapshots":[{"event_id":"sha256:29ca96c6d211c3c37227859572356d6764683b18af9ae57a9872d85a5914714d","target":"graph","created_at":"2026-07-05T07:24:13Z","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/2312.09020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training foundation models on extensive datasets and then finetuning them on specific tasks has emerged as the mainstream approach in artificial intelligence. However, the model robustness, which is a critical aspect for safety, is often optimized for each specific task rather than at the pretraining stage. In this paper, we propose a method for pretraining certifiably robust models that can be readily finetuned for adaptation to a particular task. A key challenge is dealing with the compromise between semantic learning and robustness. We address this with a simple yet highly effective strateg","authors_text":"Huishuai Zhang, Kai Qiu, Stephen Lin, Zhirong Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T15:08:27Z","title":"Exploring Transferability for Randomized Smoothing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09020","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":"sha256:4efb982eb03fb172c03c30b4f8bc74ae2214ff575d963a3a4fd2172c8dd2511f","target":"record","created_at":"2026-07-05T07:24:13Z","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":"5f84968827aa452a23222bfc02f0206d50161089d4483e144435c8db362150a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T15:08:27Z","title_canon_sha256":"9dac32e4550d9fe1655d628f76e4efc39e136f8ebb9c4f8eacf1f22100f4d39f"},"schema_version":"1.0","source":{"id":"2312.09020","kind":"arxiv","version":1}},"canonical_sha256":"76fa7610845ccc99440d44e42833a3b0d27dcac21db6bf70aedfd08305bc1a97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76fa7610845ccc99440d44e42833a3b0d27dcac21db6bf70aedfd08305bc1a97","first_computed_at":"2026-07-05T07:24:13.096380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:13.096380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SvCRhobowglDrXkhpvH+gwm0UGGnJChc8utLGRpCpj7/pmxWJWFVDKDASSKlAGPAEc8G6m0/+L8jqnR/MyFaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:13.096872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.09020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4efb982eb03fb172c03c30b4f8bc74ae2214ff575d963a3a4fd2172c8dd2511f","sha256:29ca96c6d211c3c37227859572356d6764683b18af9ae57a9872d85a5914714d"],"state_sha256":"d82d7d6ade69b2ac7cf6f6af7cccbe62a9502a440efed26209ed8068d5a1e1bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AkEr+/7vHvquUHOEVMDAnY62VrtD4xaO9adm6pk2m8o8zXzsP0uonG6uGa6Y4CxfQ0e1xpi60a2C1sjgwsJ0AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:51:31.071294Z","bundle_sha256":"6b3595f341675e11088fa256ea90c8d60692152d3ac3759296fbcfe571bcf65a"}}