{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RJOY5AKWK6T4QXQSXVCLM6SH5K","short_pith_number":"pith:RJOY5AKW","canonical_record":{"source":{"id":"1712.05419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-14T19:00:57Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"968bc3d3c90173c5b4f2f92044514808f5a3e9a26ced00ae2ee5bf7bd80f6240","abstract_canon_sha256":"121e2b199434b1a3474ef143a7ae9498f513899704b687765adf89e17336cc94"},"schema_version":"1.0"},"canonical_sha256":"8a5d8e815657a7c85e12bd44b67a47eaaf1d3735d79fa3683d3bdf2b580f8b0f","source":{"kind":"arxiv","id":"1712.05419","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.05419","created_at":"2026-05-18T00:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"1712.05419v1","created_at":"2026-05-18T00:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.05419","created_at":"2026-05-18T00:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"RJOY5AKWK6T4","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RJOY5AKWK6T4QXQS","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RJOY5AKW","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RJOY5AKWK6T4QXQSXVCLM6SH5K","target":"record","payload":{"canonical_record":{"source":{"id":"1712.05419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-14T19:00:57Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"968bc3d3c90173c5b4f2f92044514808f5a3e9a26ced00ae2ee5bf7bd80f6240","abstract_canon_sha256":"121e2b199434b1a3474ef143a7ae9498f513899704b687765adf89e17336cc94"},"schema_version":"1.0"},"canonical_sha256":"8a5d8e815657a7c85e12bd44b67a47eaaf1d3735d79fa3683d3bdf2b580f8b0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:56.541477Z","signature_b64":"fZk1FjWTfOIBqZGhL4rCyC/qP3+URwCHmuM4+QeiSR+DuPdWvCOrB42Bxb8r14Uf7CZVIcsqfWaAMLDEAr6aAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a5d8e815657a7c85e12bd44b67a47eaaf1d3735d79fa3683d3bdf2b580f8b0f","last_reissued_at":"2026-05-18T00:27:56.540832Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:56.540832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.05419","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":"2026-05-18T00:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tezmaczXrp9sV5rlvgdc9Q9b3gKkFMX2rwqe8IR5CmM99po/eGjOlPy46Oca88V1R6TjjNE5Vrfvhl9ktJI9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:06:50.798485Z"},"content_sha256":"bc60db24c504ac816669ba920c8a3d4eaafa753cb7f07693d4c6af7ef54850be","schema_version":"1.0","event_id":"sha256:bc60db24c504ac816669ba920c8a3d4eaafa753cb7f07693d4c6af7ef54850be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RJOY5AKWK6T4QXQSXVCLM6SH5K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Catherine Wong","submitted_at":"2017-12-14T19:00:57Z","abstract_excerpt":"Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities. Despite significant recent work on adversarial example generation targeting image classifiers, relatively little work exists exploring adversarial example generation for text classifiers; additionally, many existing adversarial example generation algorithms require full access to target model parameters, rendering them impractical for many real-world attacks. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.05419","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":""},"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":"2026-05-18T00:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZbZn4JanQgLDgeedDov0iALvBO24cnqO2mrjduaGQRPwkL+DXQCKxcF6y5jTLTcCA3gSDHIMmlUCeAAql0lnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:06:50.799201Z"},"content_sha256":"8807eea99ef00cfbf1035f9efeafc4c89f758d4e04cb57f1c2d75b4e633c4486","schema_version":"1.0","event_id":"sha256:8807eea99ef00cfbf1035f9efeafc4c89f758d4e04cb57f1c2d75b4e633c4486"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJOY5AKWK6T4QXQSXVCLM6SH5K/bundle.json","state_url":"https://pith.science/pith/RJOY5AKWK6T4QXQSXVCLM6SH5K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJOY5AKWK6T4QXQSXVCLM6SH5K/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":"2026-06-12T02:06:50Z","links":{"resolver":"https://pith.science/pith/RJOY5AKWK6T4QXQSXVCLM6SH5K","bundle":"https://pith.science/pith/RJOY5AKWK6T4QXQSXVCLM6SH5K/bundle.json","state":"https://pith.science/pith/RJOY5AKWK6T4QXQSXVCLM6SH5K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJOY5AKWK6T4QXQSXVCLM6SH5K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RJOY5AKWK6T4QXQSXVCLM6SH5K","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":"121e2b199434b1a3474ef143a7ae9498f513899704b687765adf89e17336cc94","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-14T19:00:57Z","title_canon_sha256":"968bc3d3c90173c5b4f2f92044514808f5a3e9a26ced00ae2ee5bf7bd80f6240"},"schema_version":"1.0","source":{"id":"1712.05419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.05419","created_at":"2026-05-18T00:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"1712.05419v1","created_at":"2026-05-18T00:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.05419","created_at":"2026-05-18T00:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"RJOY5AKWK6T4","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RJOY5AKWK6T4QXQS","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RJOY5AKW","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:8807eea99ef00cfbf1035f9efeafc4c89f758d4e04cb57f1c2d75b4e633c4486","target":"graph","created_at":"2026-05-18T00:27:56Z","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"},"paper":{"abstract_excerpt":"Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities. Despite significant recent work on adversarial example generation targeting image classifiers, relatively little work exists exploring adversarial example generation for text classifiers; additionally, many existing adversarial example generation algorithms require full access to target model parameters, rendering them impractical for many real-world attacks. In","authors_text":"Catherine Wong","cross_cats":["cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-14T19:00:57Z","title":"DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.05419","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:bc60db24c504ac816669ba920c8a3d4eaafa753cb7f07693d4c6af7ef54850be","target":"record","created_at":"2026-05-18T00:27:56Z","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":"121e2b199434b1a3474ef143a7ae9498f513899704b687765adf89e17336cc94","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-14T19:00:57Z","title_canon_sha256":"968bc3d3c90173c5b4f2f92044514808f5a3e9a26ced00ae2ee5bf7bd80f6240"},"schema_version":"1.0","source":{"id":"1712.05419","kind":"arxiv","version":1}},"canonical_sha256":"8a5d8e815657a7c85e12bd44b67a47eaaf1d3735d79fa3683d3bdf2b580f8b0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a5d8e815657a7c85e12bd44b67a47eaaf1d3735d79fa3683d3bdf2b580f8b0f","first_computed_at":"2026-05-18T00:27:56.540832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:56.540832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fZk1FjWTfOIBqZGhL4rCyC/qP3+URwCHmuM4+QeiSR+DuPdWvCOrB42Bxb8r14Uf7CZVIcsqfWaAMLDEAr6aAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:56.541477Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.05419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc60db24c504ac816669ba920c8a3d4eaafa753cb7f07693d4c6af7ef54850be","sha256:8807eea99ef00cfbf1035f9efeafc4c89f758d4e04cb57f1c2d75b4e633c4486"],"state_sha256":"0fc406eec9658b87e3eeff3a13a992799c92dfe9b5f7754b4ba9b1e3af8c29f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X3A6LAtob2FJHCUF3j3Rb/nvG8nJ/KRh5MJrP8uTGtnJLTtS+7d2XEoBV6nBgY4eHfJQiOH5jgLMtmrEnvfMAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T02:06:50.803308Z","bundle_sha256":"39da8c93ce951eb5751c6d55bc622deb44ac1399e76304a1d79f9d2f15e5f0c0"}}