{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EIVWEFKXEVEDA7EJ5TCKXOARKN","short_pith_number":"pith:EIVWEFKX","schema_version":"1.0","canonical_sha256":"222b6215572548307c89ecc4abb8115359120cc6efa09855c8b9334d55a50732","source":{"kind":"arxiv","id":"2501.12183","version":1},"attestation_state":"computed","paper":{"title":"Extend Adversarial Policy Against Neural Machine Translation via Unknown Token","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiajun Chen, Shujian Huang, Wei Zou","submitted_at":"2025-01-21T14:43:04Z","abstract_excerpt":"Generating adversarial examples contributes to mainstream neural machine translation~(NMT) robustness. However, popular adversarial policies are apt for fixed tokenization, hindering its efficacy for common character perturbations involving versatile tokenization. Based on existing adversarial generation via reinforcement learning~(RL), we propose the `DexChar policy' that introduces character perturbations for the existing mainstream adversarial policy based on token substitution. Furthermore, we improve the self-supervised matching that provides feedback in RL to cater to the semantic constr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.12183","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T14:43:04Z","cross_cats_sorted":[],"title_canon_sha256":"1607b889cf322ad1bcef8ad5d701cb696c23191a9043c5fa83e2bb683978e245","abstract_canon_sha256":"fe6aff000c557fbb4326153a85eb5d41d889ab5e075fb5369b9a06778b5fe838"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:32.698276Z","signature_b64":"Qxdwm58MxX/dKWSD9ezha5BFdZGg9CrLI3pbDs6Ue80me5EQzVqTUT5mHrttmWPU/I9radl6hFRqZcAtW8YLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"222b6215572548307c89ecc4abb8115359120cc6efa09855c8b9334d55a50732","last_reissued_at":"2026-07-05T10:03:32.697849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:32.697849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extend Adversarial Policy Against Neural Machine Translation via Unknown Token","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiajun Chen, Shujian Huang, Wei Zou","submitted_at":"2025-01-21T14:43:04Z","abstract_excerpt":"Generating adversarial examples contributes to mainstream neural machine translation~(NMT) robustness. However, popular adversarial policies are apt for fixed tokenization, hindering its efficacy for common character perturbations involving versatile tokenization. Based on existing adversarial generation via reinforcement learning~(RL), we propose the `DexChar policy' that introduces character perturbations for the existing mainstream adversarial policy based on token substitution. Furthermore, we improve the self-supervised matching that provides feedback in RL to cater to the semantic constr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12183","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/2501.12183/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.12183","created_at":"2026-07-05T10:03:32.697906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12183v1","created_at":"2026-07-05T10:03:32.697906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12183","created_at":"2026-07-05T10:03:32.697906+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIVWEFKXEVED","created_at":"2026-07-05T10:03:32.697906+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIVWEFKXEVEDA7EJ","created_at":"2026-07-05T10:03:32.697906+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIVWEFKX","created_at":"2026-07-05T10:03:32.697906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EIVWEFKXEVEDA7EJ5TCKXOARKN","json":"https://pith.science/pith/EIVWEFKXEVEDA7EJ5TCKXOARKN.json","graph_json":"https://pith.science/api/pith-number/EIVWEFKXEVEDA7EJ5TCKXOARKN/graph.json","events_json":"https://pith.science/api/pith-number/EIVWEFKXEVEDA7EJ5TCKXOARKN/events.json","paper":"https://pith.science/paper/EIVWEFKX"},"agent_actions":{"view_html":"https://pith.science/pith/EIVWEFKXEVEDA7EJ5TCKXOARKN","download_json":"https://pith.science/pith/EIVWEFKXEVEDA7EJ5TCKXOARKN.json","view_paper":"https://pith.science/paper/EIVWEFKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12183&json=true","fetch_graph":"https://pith.science/api/pith-number/EIVWEFKXEVEDA7EJ5TCKXOARKN/graph.json","fetch_events":"https://pith.science/api/pith-number/EIVWEFKXEVEDA7EJ5TCKXOARKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIVWEFKXEVEDA7EJ5TCKXOARKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIVWEFKXEVEDA7EJ5TCKXOARKN/action/storage_attestation","attest_author":"https://pith.science/pith/EIVWEFKXEVEDA7EJ5TCKXOARKN/action/author_attestation","sign_citation":"https://pith.science/pith/EIVWEFKXEVEDA7EJ5TCKXOARKN/action/citation_signature","submit_replication":"https://pith.science/pith/EIVWEFKXEVEDA7EJ5TCKXOARKN/action/replication_record"}},"created_at":"2026-07-05T10:03:32.697906+00:00","updated_at":"2026-07-05T10:03:32.697906+00:00"}