{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IGJX3OHREUTU6IABJJT2ILEVHA","short_pith_number":"pith:IGJX3OHR","canonical_record":{"source":{"id":"2006.00387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-30T23:23:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ef3636e08c1cb1c742c1ba902d3be32d9354ac56522be73cb0516651568be0d3","abstract_canon_sha256":"0d77e98606acfc9213d37592e6d9cf17cd252219227b81072a752ec38f4ad071"},"schema_version":"1.0"},"canonical_sha256":"41937db8f125274f20014a67a42c9538141f3a73619d790fc545fab75a7dfce5","source":{"kind":"arxiv","id":"2006.00387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.00387","created_at":"2026-07-05T01:07:00Z"},{"alias_kind":"arxiv_version","alias_value":"2006.00387v1","created_at":"2026-07-05T01:07:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00387","created_at":"2026-07-05T01:07:00Z"},{"alias_kind":"pith_short_12","alias_value":"IGJX3OHREUTU","created_at":"2026-07-05T01:07:00Z"},{"alias_kind":"pith_short_16","alias_value":"IGJX3OHREUTU6IAB","created_at":"2026-07-05T01:07:00Z"},{"alias_kind":"pith_short_8","alias_value":"IGJX3OHR","created_at":"2026-07-05T01:07:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IGJX3OHREUTU6IABJJT2ILEVHA","target":"record","payload":{"canonical_record":{"source":{"id":"2006.00387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-30T23:23:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ef3636e08c1cb1c742c1ba902d3be32d9354ac56522be73cb0516651568be0d3","abstract_canon_sha256":"0d77e98606acfc9213d37592e6d9cf17cd252219227b81072a752ec38f4ad071"},"schema_version":"1.0"},"canonical_sha256":"41937db8f125274f20014a67a42c9538141f3a73619d790fc545fab75a7dfce5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:00.973236Z","signature_b64":"aLONmEIgcktw6Vo5/f67c6Mh85SQ/ekvrcOIXxhwQpD3EGQvZMWAV5EM7H3ehBOF+rxRTuIN5J1LFF+2UHV9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41937db8f125274f20014a67a42c9538141f3a73619d790fc545fab75a7dfce5","last_reissued_at":"2026-07-05T01:07:00.972760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:00.972760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.00387","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":"2026-07-05T01:07:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSNjQQh617sbJ7Gx0pGeCNbVxBY6h0Boq//J+TCb/0FvD+NDdvYuiAdE7bkThw2EkSWRmdbjuz8eDZnGhvJ5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:56:43.728833Z"},"content_sha256":"cf813a7d74a1ace3743bf2663a1a6fbeff44cb8a1c8d5e8c20db899acf12f5f2","schema_version":"1.0","event_id":"sha256:cf813a7d74a1ace3743bf2663a1a6fbeff44cb8a1c8d5e8c20db899acf12f5f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IGJX3OHREUTU6IABJJT2ILEVHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Model Robustness with Adaptive Networks and Improved Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Shafahi, Tom Goldstein, Zheng Xu","submitted_at":"2020-05-30T23:23:56Z","abstract_excerpt":"Adversarial training has proven to be effective in hardening networks against adversarial examples. However, the gained robustness is limited by network capacity and number of training samples. Consequently, to build more robust models, it is common practice to train on widened networks with more parameters. To boost robustness, we propose a conditional normalization module to adapt networks when conditioned on input samples. Our adaptive networks, once adversarially trained, can outperform their non-adaptive counterparts on both clean validation accuracy and robustness. Our method is objectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00387","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/2006.00387/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":"2026-07-05T01:07:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PD7I/z/6acBhVZuB53xlSy7pYZzGcDLS5PBndTvfKV4eaQj4uP9QrVCG9uLmogdMQUY9ADLO9hHNUVMM3XCgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:56:43.729183Z"},"content_sha256":"ef256ae2534377d05136de3b089e56a73e209fbfa78e2648cbe1eb6a78b9ad70","schema_version":"1.0","event_id":"sha256:ef256ae2534377d05136de3b089e56a73e209fbfa78e2648cbe1eb6a78b9ad70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IGJX3OHREUTU6IABJJT2ILEVHA/bundle.json","state_url":"https://pith.science/pith/IGJX3OHREUTU6IABJJT2ILEVHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IGJX3OHREUTU6IABJJT2ILEVHA/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":"2026-08-21T08:56:43Z","links":{"resolver":"https://pith.science/pith/IGJX3OHREUTU6IABJJT2ILEVHA","bundle":"https://pith.science/pith/IGJX3OHREUTU6IABJJT2ILEVHA/bundle.json","state":"https://pith.science/pith/IGJX3OHREUTU6IABJJT2ILEVHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IGJX3OHREUTU6IABJJT2ILEVHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IGJX3OHREUTU6IABJJT2ILEVHA","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":"0d77e98606acfc9213d37592e6d9cf17cd252219227b81072a752ec38f4ad071","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-30T23:23:56Z","title_canon_sha256":"ef3636e08c1cb1c742c1ba902d3be32d9354ac56522be73cb0516651568be0d3"},"schema_version":"1.0","source":{"id":"2006.00387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.00387","created_at":"2026-07-05T01:07:00Z"},{"alias_kind":"arxiv_version","alias_value":"2006.00387v1","created_at":"2026-07-05T01:07:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00387","created_at":"2026-07-05T01:07:00Z"},{"alias_kind":"pith_short_12","alias_value":"IGJX3OHREUTU","created_at":"2026-07-05T01:07:00Z"},{"alias_kind":"pith_short_16","alias_value":"IGJX3OHREUTU6IAB","created_at":"2026-07-05T01:07:00Z"},{"alias_kind":"pith_short_8","alias_value":"IGJX3OHR","created_at":"2026-07-05T01:07:00Z"}],"graph_snapshots":[{"event_id":"sha256:ef256ae2534377d05136de3b089e56a73e209fbfa78e2648cbe1eb6a78b9ad70","target":"graph","created_at":"2026-07-05T01:07:00Z","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/2006.00387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial training has proven to be effective in hardening networks against adversarial examples. However, the gained robustness is limited by network capacity and number of training samples. Consequently, to build more robust models, it is common practice to train on widened networks with more parameters. To boost robustness, we propose a conditional normalization module to adapt networks when conditioned on input samples. Our adaptive networks, once adversarially trained, can outperform their non-adaptive counterparts on both clean validation accuracy and robustness. Our method is objectiv","authors_text":"Ali Shafahi, Tom Goldstein, Zheng Xu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-30T23:23:56Z","title":"Exploring Model Robustness with Adaptive Networks and Improved Adversarial Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00387","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:cf813a7d74a1ace3743bf2663a1a6fbeff44cb8a1c8d5e8c20db899acf12f5f2","target":"record","created_at":"2026-07-05T01:07:00Z","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":"0d77e98606acfc9213d37592e6d9cf17cd252219227b81072a752ec38f4ad071","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-30T23:23:56Z","title_canon_sha256":"ef3636e08c1cb1c742c1ba902d3be32d9354ac56522be73cb0516651568be0d3"},"schema_version":"1.0","source":{"id":"2006.00387","kind":"arxiv","version":1}},"canonical_sha256":"41937db8f125274f20014a67a42c9538141f3a73619d790fc545fab75a7dfce5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41937db8f125274f20014a67a42c9538141f3a73619d790fc545fab75a7dfce5","first_computed_at":"2026-07-05T01:07:00.972760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:00.972760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aLONmEIgcktw6Vo5/f67c6Mh85SQ/ekvrcOIXxhwQpD3EGQvZMWAV5EM7H3ehBOF+rxRTuIN5J1LFF+2UHV9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:00.973236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.00387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf813a7d74a1ace3743bf2663a1a6fbeff44cb8a1c8d5e8c20db899acf12f5f2","sha256:ef256ae2534377d05136de3b089e56a73e209fbfa78e2648cbe1eb6a78b9ad70"],"state_sha256":"43d3d2ad7eaf1fc0f7ea79d8fe31e7fe8286d8cacbe5b2dbad5a4afae071c7bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OntmFjG2+vKsNlGl0Nj8yIoOvkkuH1ZmeSklg/Cxkr5/f75q8pDNlh/dceu6hvr8DVqB8T1XtMUcOOG1eJcPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T08:56:43.733282Z","bundle_sha256":"4f2680f281d3a9eb90a24759884a391c62fc20716bc74d93b065febbcccb78fa"}}