{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LWQNCE6AUDKEIYOOY3E374DDRN","short_pith_number":"pith:LWQNCE6A","canonical_record":{"source":{"id":"2209.07735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-16T06:25:06Z","cross_cats_sorted":[],"title_canon_sha256":"6bf411e4d6cd1aa395d12e579a4d1bd3b221478486e88cc3239ff232e3e0ea33","abstract_canon_sha256":"571f7778ed1f18e13c490226dfd9f0d583d494ba07d275498782f51a91b83f36"},"schema_version":"1.0"},"canonical_sha256":"5da0d113c0a0d44461cec6c9bff0638b5496290d937111da2e07b9270b149115","source":{"kind":"arxiv","id":"2209.07735","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.07735","created_at":"2026-07-05T04:58:09Z"},{"alias_kind":"arxiv_version","alias_value":"2209.07735v1","created_at":"2026-07-05T04:58:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07735","created_at":"2026-07-05T04:58:09Z"},{"alias_kind":"pith_short_12","alias_value":"LWQNCE6AUDKE","created_at":"2026-07-05T04:58:09Z"},{"alias_kind":"pith_short_16","alias_value":"LWQNCE6AUDKEIYOO","created_at":"2026-07-05T04:58:09Z"},{"alias_kind":"pith_short_8","alias_value":"LWQNCE6A","created_at":"2026-07-05T04:58:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LWQNCE6AUDKEIYOOY3E374DDRN","target":"record","payload":{"canonical_record":{"source":{"id":"2209.07735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-16T06:25:06Z","cross_cats_sorted":[],"title_canon_sha256":"6bf411e4d6cd1aa395d12e579a4d1bd3b221478486e88cc3239ff232e3e0ea33","abstract_canon_sha256":"571f7778ed1f18e13c490226dfd9f0d583d494ba07d275498782f51a91b83f36"},"schema_version":"1.0"},"canonical_sha256":"5da0d113c0a0d44461cec6c9bff0638b5496290d937111da2e07b9270b149115","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:09.320539Z","signature_b64":"K/5l9kQ4KoVPsWuI60442T1Npo4d8lwhq3xauKv0YJ7G/6LVHbmnHELYoGZtBOUh4LZE2hl9rOoFbPQWApNJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5da0d113c0a0d44461cec6c9bff0638b5496290d937111da2e07b9270b149115","last_reissued_at":"2026-07-05T04:58:09.320188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:09.320188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.07735","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":"2026-07-05T04:58:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6eiamvjUQ8yYJsSEaI7n0HQgY5tjt72LscTcxQxw9J3J6Qk3B+fNY4Br3QQ3/cx/2tVK33G5df1937lqSXmABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:43:19.547555Z"},"content_sha256":"1b239d9bab00d5142297c0abe7ca09de991e12f5e8e91cdb7537c617826b976b","schema_version":"1.0","event_id":"sha256:1b239d9bab00d5142297c0abe7ca09de991e12f5e8e91cdb7537c617826b976b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LWQNCE6AUDKEIYOOY3E374DDRN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhance the Visual Representation via Discrete Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gege Qi, Hui Xue, Ranjie Duan, Rong Zhang, Shaokai Ye, Xiaodan Li, Xiaofeng Mao, Yao Zhu, Yuefeng Chen","submitted_at":"2022-09-16T06:25:06Z","abstract_excerpt":"Adversarial Training (AT), which is commonly accepted as one of the most effective approaches defending against adversarial examples, can largely harm the standard performance, thus has limited usefulness on industrial-scale production and applications. Surprisingly, this phenomenon is totally opposite in Natural Language Processing (NLP) task, where AT can even benefit for generalization. We notice the merit of AT in NLP tasks could derive from the discrete and symbolic input space. For borrowing the advantage from NLP-style AT, we propose Discrete Adversarial Training (DAT). DAT leverages VQ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07735","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/2209.07735/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":"2026-07-05T04:58:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yvme6nzwKVWge65HZVc8RppRT8GrEzNl2I8rVPiP8TE/R4GbgOgjy223eo7C+UIRHak4J+Px0U+qA6Do+TDqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:43:19.548068Z"},"content_sha256":"e749de6e4850ff44da26aaced5fe8fdc9b373acb2bafc2c3e1ba03cb8fb0db28","schema_version":"1.0","event_id":"sha256:e749de6e4850ff44da26aaced5fe8fdc9b373acb2bafc2c3e1ba03cb8fb0db28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LWQNCE6AUDKEIYOOY3E374DDRN/bundle.json","state_url":"https://pith.science/pith/LWQNCE6AUDKEIYOOY3E374DDRN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LWQNCE6AUDKEIYOOY3E374DDRN/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":"2026-08-03T16:43:19Z","links":{"resolver":"https://pith.science/pith/LWQNCE6AUDKEIYOOY3E374DDRN","bundle":"https://pith.science/pith/LWQNCE6AUDKEIYOOY3E374DDRN/bundle.json","state":"https://pith.science/pith/LWQNCE6AUDKEIYOOY3E374DDRN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LWQNCE6AUDKEIYOOY3E374DDRN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LWQNCE6AUDKEIYOOY3E374DDRN","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":"571f7778ed1f18e13c490226dfd9f0d583d494ba07d275498782f51a91b83f36","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-16T06:25:06Z","title_canon_sha256":"6bf411e4d6cd1aa395d12e579a4d1bd3b221478486e88cc3239ff232e3e0ea33"},"schema_version":"1.0","source":{"id":"2209.07735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.07735","created_at":"2026-07-05T04:58:09Z"},{"alias_kind":"arxiv_version","alias_value":"2209.07735v1","created_at":"2026-07-05T04:58:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07735","created_at":"2026-07-05T04:58:09Z"},{"alias_kind":"pith_short_12","alias_value":"LWQNCE6AUDKE","created_at":"2026-07-05T04:58:09Z"},{"alias_kind":"pith_short_16","alias_value":"LWQNCE6AUDKEIYOO","created_at":"2026-07-05T04:58:09Z"},{"alias_kind":"pith_short_8","alias_value":"LWQNCE6A","created_at":"2026-07-05T04:58:09Z"}],"graph_snapshots":[{"event_id":"sha256:e749de6e4850ff44da26aaced5fe8fdc9b373acb2bafc2c3e1ba03cb8fb0db28","target":"graph","created_at":"2026-07-05T04:58:09Z","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/2209.07735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial Training (AT), which is commonly accepted as one of the most effective approaches defending against adversarial examples, can largely harm the standard performance, thus has limited usefulness on industrial-scale production and applications. Surprisingly, this phenomenon is totally opposite in Natural Language Processing (NLP) task, where AT can even benefit for generalization. We notice the merit of AT in NLP tasks could derive from the discrete and symbolic input space. For borrowing the advantage from NLP-style AT, we propose Discrete Adversarial Training (DAT). DAT leverages VQ","authors_text":"Gege Qi, Hui Xue, Ranjie Duan, Rong Zhang, Shaokai Ye, Xiaodan Li, Xiaofeng Mao, Yao Zhu, Yuefeng Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-16T06:25:06Z","title":"Enhance the Visual Representation via Discrete Adversarial Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07735","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":"sha256:1b239d9bab00d5142297c0abe7ca09de991e12f5e8e91cdb7537c617826b976b","target":"record","created_at":"2026-07-05T04:58:09Z","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":"571f7778ed1f18e13c490226dfd9f0d583d494ba07d275498782f51a91b83f36","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-16T06:25:06Z","title_canon_sha256":"6bf411e4d6cd1aa395d12e579a4d1bd3b221478486e88cc3239ff232e3e0ea33"},"schema_version":"1.0","source":{"id":"2209.07735","kind":"arxiv","version":1}},"canonical_sha256":"5da0d113c0a0d44461cec6c9bff0638b5496290d937111da2e07b9270b149115","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5da0d113c0a0d44461cec6c9bff0638b5496290d937111da2e07b9270b149115","first_computed_at":"2026-07-05T04:58:09.320188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:09.320188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K/5l9kQ4KoVPsWuI60442T1Npo4d8lwhq3xauKv0YJ7G/6LVHbmnHELYoGZtBOUh4LZE2hl9rOoFbPQWApNJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:09.320539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.07735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b239d9bab00d5142297c0abe7ca09de991e12f5e8e91cdb7537c617826b976b","sha256:e749de6e4850ff44da26aaced5fe8fdc9b373acb2bafc2c3e1ba03cb8fb0db28"],"state_sha256":"9750992a8662dc5ac6b27c5a85e6a58a3a6c00359b09b44f92c9ea214eff46dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OpBj23bJQcXwfWgymvKLRb49ROt6kW2S/4XA5bJwc4jic9VVzQzrfY3XG2AqlyCO02AN5m3Na4e/k4Ky9Tw8AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:43:19.555568Z","bundle_sha256":"9f1d7f3d25f23d894e6cf75626393567f341ea1137610d6096338d0a061b979a"}}