{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DF4SN3QN2K37X2IRHWO4LAXW7U","short_pith_number":"pith:DF4SN3QN","schema_version":"1.0","canonical_sha256":"197926ee0dd2b7fbe9113d9dc582f6fd06d3f3bcaac3d44c807a5b2ad19b970f","source":{"kind":"arxiv","id":"2305.18503","version":1},"attestation_state":"computed","paper":{"title":"From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Yuan, Dehan Kong, Ganqu Cui, Hanlu Wu, Heng Ji, Hongcheng Gao, Hui Xue, Lifan Yuan, Longtao Huang, Maosong Sun, Ning Shi, Yangyi Chen, Zhiyuan Liu","submitted_at":"2023-05-29T14:55:20Z","abstract_excerpt":"Textual adversarial attacks can discover models' weaknesses by adding semantic-preserved but misleading perturbations to the inputs. The long-lasting adversarial attack-and-defense arms race in Natural Language Processing (NLP) is algorithm-centric, providing valuable techniques for automatic robustness evaluation. However, the existing practice of robustness evaluation may exhibit issues of incomprehensive evaluation, impractical evaluation protocol, and invalid adversarial samples. In this paper, we aim to set up a unified automatic robustness evaluation framework, shifting towards model-cen"},"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":"2305.18503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T14:55:20Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"4edbe38eedb1e8f96f87323dd0725718925857c6e281c6ca17c6e6bcf46ce122","abstract_canon_sha256":"e7532cfc70e1a161b6ee97de6e091e19d0c1a310db2d5d3d0392e50656d73f6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:01.772835Z","signature_b64":"C8bjv6tvI4l7mFDl5KXw3DdCA3qbgO45ECRm1xUtSejZ7r0+RNtTw9wnSxeDXJoCLPQ51ONMDDYGb/mXBr6bCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"197926ee0dd2b7fbe9113d9dc582f6fd06d3f3bcaac3d44c807a5b2ad19b970f","last_reissued_at":"2026-07-05T06:15:01.772393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:01.772393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Yuan, Dehan Kong, Ganqu Cui, Hanlu Wu, Heng Ji, Hongcheng Gao, Hui Xue, Lifan Yuan, Longtao Huang, Maosong Sun, Ning Shi, Yangyi Chen, Zhiyuan Liu","submitted_at":"2023-05-29T14:55:20Z","abstract_excerpt":"Textual adversarial attacks can discover models' weaknesses by adding semantic-preserved but misleading perturbations to the inputs. The long-lasting adversarial attack-and-defense arms race in Natural Language Processing (NLP) is algorithm-centric, providing valuable techniques for automatic robustness evaluation. However, the existing practice of robustness evaluation may exhibit issues of incomprehensive evaluation, impractical evaluation protocol, and invalid adversarial samples. In this paper, we aim to set up a unified automatic robustness evaluation framework, shifting towards model-cen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18503","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/2305.18503/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":"2305.18503","created_at":"2026-07-05T06:15:01.772451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18503v1","created_at":"2026-07-05T06:15:01.772451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18503","created_at":"2026-07-05T06:15:01.772451+00:00"},{"alias_kind":"pith_short_12","alias_value":"DF4SN3QN2K37","created_at":"2026-07-05T06:15:01.772451+00:00"},{"alias_kind":"pith_short_16","alias_value":"DF4SN3QN2K37X2IR","created_at":"2026-07-05T06:15:01.772451+00:00"},{"alias_kind":"pith_short_8","alias_value":"DF4SN3QN","created_at":"2026-07-05T06:15:01.772451+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/DF4SN3QN2K37X2IRHWO4LAXW7U","json":"https://pith.science/pith/DF4SN3QN2K37X2IRHWO4LAXW7U.json","graph_json":"https://pith.science/api/pith-number/DF4SN3QN2K37X2IRHWO4LAXW7U/graph.json","events_json":"https://pith.science/api/pith-number/DF4SN3QN2K37X2IRHWO4LAXW7U/events.json","paper":"https://pith.science/paper/DF4SN3QN"},"agent_actions":{"view_html":"https://pith.science/pith/DF4SN3QN2K37X2IRHWO4LAXW7U","download_json":"https://pith.science/pith/DF4SN3QN2K37X2IRHWO4LAXW7U.json","view_paper":"https://pith.science/paper/DF4SN3QN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18503&json=true","fetch_graph":"https://pith.science/api/pith-number/DF4SN3QN2K37X2IRHWO4LAXW7U/graph.json","fetch_events":"https://pith.science/api/pith-number/DF4SN3QN2K37X2IRHWO4LAXW7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DF4SN3QN2K37X2IRHWO4LAXW7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DF4SN3QN2K37X2IRHWO4LAXW7U/action/storage_attestation","attest_author":"https://pith.science/pith/DF4SN3QN2K37X2IRHWO4LAXW7U/action/author_attestation","sign_citation":"https://pith.science/pith/DF4SN3QN2K37X2IRHWO4LAXW7U/action/citation_signature","submit_replication":"https://pith.science/pith/DF4SN3QN2K37X2IRHWO4LAXW7U/action/replication_record"}},"created_at":"2026-07-05T06:15:01.772451+00:00","updated_at":"2026-07-05T06:15:01.772451+00:00"}