{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:U6EAZM6S33RBD6DWHKMXF3W67F","short_pith_number":"pith:U6EAZM6S","canonical_record":{"source":{"id":"2111.02840","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-04T12:59:55Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"800adeae09acf562e047777558566c274369efbaf1a00859d6b20eefcc93b4f7","abstract_canon_sha256":"8d39157ebb41f1f4ac6c46bbfc84bb5a9dbac79be624b839d0b89e614714eb1c"},"schema_version":"1.0"},"canonical_sha256":"a7880cb3d2dee211f8763a9972eedef97c78201830a5d6a5cd64d687f44bae2c","source":{"kind":"arxiv","id":"2111.02840","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02840","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02840v2","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02840","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"U6EAZM6S33RB","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_16","alias_value":"U6EAZM6S33RBD6DW","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_8","alias_value":"U6EAZM6S","created_at":"2026-07-05T03:47:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:U6EAZM6S33RBD6DWHKMXF3W67F","target":"record","payload":{"canonical_record":{"source":{"id":"2111.02840","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-04T12:59:55Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"800adeae09acf562e047777558566c274369efbaf1a00859d6b20eefcc93b4f7","abstract_canon_sha256":"8d39157ebb41f1f4ac6c46bbfc84bb5a9dbac79be624b839d0b89e614714eb1c"},"schema_version":"1.0"},"canonical_sha256":"a7880cb3d2dee211f8763a9972eedef97c78201830a5d6a5cd64d687f44bae2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:02.194819Z","signature_b64":"+NghZr3IOu+twkijBssjneT7UjMsOFdQHoZ19aChX5I+FOE0TGCi4l11vrd+4JvGlhcIV18LBGON+E0zEBGeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7880cb3d2dee211f8763a9972eedef97c78201830a5d6a5cd64d687f44bae2c","last_reissued_at":"2026-07-05T03:47:02.194327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:02.194327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.02840","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:47:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYQproHcd+NoxLugW21U89b1dNmgd6J6aJWU0oNseAYpQLtjvJVWsBAqowJ5lgp4Cw7GoaC1Sa5tnS1P9By2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:51.759899Z"},"content_sha256":"d804d61b9782fa63d70c3a28702364b01826299cca9ba3175de32d9cbafafe1b","schema_version":"1.0","event_id":"sha256:d804d61b9782fa63d70c3a28702364b01826299cca9ba3175de32d9cbafafe1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:U6EAZM6S33RBD6DWHKMXF3W67F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmed Hassan Awadallah, Bo Li, Boxin Wang, Chejian Xu, Jianfeng Gao, Shuohang Wang, Yu Cheng, Zhe Gan","submitted_at":"2021-11-04T12:59:55Z","abstract_excerpt":"Large-scale pre-trained language models have achieved tremendous success across a wide range of natural language understanding (NLU) tasks, even surpassing human performance. However, recent studies reveal that the robustness of these models can be challenged by carefully crafted textual adversarial examples. While several individual datasets have been proposed to evaluate model robustness, a principled and comprehensive benchmark is still missing. In this paper, we present Adversarial GLUE (AdvGLUE), a new multi-task benchmark to quantitatively and thoroughly explore and evaluate the vulnerab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02840","kind":"arxiv","version":2},"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/2111.02840/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":"2026-07-05T03:47:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"spfeoQyEQvNaZnajVWDiez5dJzrshep/41jvFgx5ZfneyWbyU8mkUWb+d1uZgy8l/qvAQxGQS8YYTaQUoMNoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:51.760490Z"},"content_sha256":"0c3c1914bdee7ca22ad1ebe3f6fccc12876638ae129474f7ebce94bbba293de9","schema_version":"1.0","event_id":"sha256:0c3c1914bdee7ca22ad1ebe3f6fccc12876638ae129474f7ebce94bbba293de9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6EAZM6S33RBD6DWHKMXF3W67F/bundle.json","state_url":"https://pith.science/pith/U6EAZM6S33RBD6DWHKMXF3W67F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6EAZM6S33RBD6DWHKMXF3W67F/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":"2026-08-07T01:45:51Z","links":{"resolver":"https://pith.science/pith/U6EAZM6S33RBD6DWHKMXF3W67F","bundle":"https://pith.science/pith/U6EAZM6S33RBD6DWHKMXF3W67F/bundle.json","state":"https://pith.science/pith/U6EAZM6S33RBD6DWHKMXF3W67F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6EAZM6S33RBD6DWHKMXF3W67F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:U6EAZM6S33RBD6DWHKMXF3W67F","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":"8d39157ebb41f1f4ac6c46bbfc84bb5a9dbac79be624b839d0b89e614714eb1c","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-04T12:59:55Z","title_canon_sha256":"800adeae09acf562e047777558566c274369efbaf1a00859d6b20eefcc93b4f7"},"schema_version":"1.0","source":{"id":"2111.02840","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02840","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02840v2","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02840","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"U6EAZM6S33RB","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_16","alias_value":"U6EAZM6S33RBD6DW","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_8","alias_value":"U6EAZM6S","created_at":"2026-07-05T03:47:02Z"}],"graph_snapshots":[{"event_id":"sha256:0c3c1914bdee7ca22ad1ebe3f6fccc12876638ae129474f7ebce94bbba293de9","target":"graph","created_at":"2026-07-05T03:47:02Z","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/2111.02840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pre-trained language models have achieved tremendous success across a wide range of natural language understanding (NLU) tasks, even surpassing human performance. However, recent studies reveal that the robustness of these models can be challenged by carefully crafted textual adversarial examples. While several individual datasets have been proposed to evaluate model robustness, a principled and comprehensive benchmark is still missing. In this paper, we present Adversarial GLUE (AdvGLUE), a new multi-task benchmark to quantitatively and thoroughly explore and evaluate the vulnerab","authors_text":"Ahmed Hassan Awadallah, Bo Li, Boxin Wang, Chejian Xu, Jianfeng Gao, Shuohang Wang, Yu Cheng, Zhe Gan","cross_cats":["cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-04T12:59:55Z","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02840","kind":"arxiv","version":2},"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:d804d61b9782fa63d70c3a28702364b01826299cca9ba3175de32d9cbafafe1b","target":"record","created_at":"2026-07-05T03:47:02Z","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":"8d39157ebb41f1f4ac6c46bbfc84bb5a9dbac79be624b839d0b89e614714eb1c","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-04T12:59:55Z","title_canon_sha256":"800adeae09acf562e047777558566c274369efbaf1a00859d6b20eefcc93b4f7"},"schema_version":"1.0","source":{"id":"2111.02840","kind":"arxiv","version":2}},"canonical_sha256":"a7880cb3d2dee211f8763a9972eedef97c78201830a5d6a5cd64d687f44bae2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7880cb3d2dee211f8763a9972eedef97c78201830a5d6a5cd64d687f44bae2c","first_computed_at":"2026-07-05T03:47:02.194327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:47:02.194327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+NghZr3IOu+twkijBssjneT7UjMsOFdQHoZ19aChX5I+FOE0TGCi4l11vrd+4JvGlhcIV18LBGON+E0zEBGeBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:47:02.194819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.02840","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d804d61b9782fa63d70c3a28702364b01826299cca9ba3175de32d9cbafafe1b","sha256:0c3c1914bdee7ca22ad1ebe3f6fccc12876638ae129474f7ebce94bbba293de9"],"state_sha256":"b8590dece762f933dad3b6b2f1e160e8ce5111e5b944bfcd3ce1fe2f6daa9a64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UV55giBi9AAiXdEHXJ+cqU/DoX96Z82jdvENO41TPRvvx6dnKt0ehYFfRlN27A8PikOHYOyP87VnohBQOGqLCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:45:51.764075Z","bundle_sha256":"07a2858fff608b9f9ef64abccc19949e40653c57c359765b53efa451c125ba90"}}