{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PPUQHLOGMWVBY6GVSQD4V6R5ZD","short_pith_number":"pith:PPUQHLOG","canonical_record":{"source":{"id":"1804.07461","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T06:35:04Z","cross_cats_sorted":[],"title_canon_sha256":"ca8e56361ec8b4ac7b6d1a9ac5fc06d7f1bb0ec8ca9cf2a6efc6b6865ab94e32","abstract_canon_sha256":"7c3185a67749475da85af13e13a89d4b8e5e1585377e54bbd7179cc03e59de7a"},"schema_version":"1.0"},"canonical_sha256":"7be903adc665aa1c78d59407cafa3dc8dbac72d537996d13c6c93b5a7ea2608e","source":{"kind":"arxiv","id":"1804.07461","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07461","created_at":"2026-07-04T23:25:04Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07461v3","created_at":"2026-07-04T23:25:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07461","created_at":"2026-07-04T23:25:04Z"},{"alias_kind":"pith_short_12","alias_value":"PPUQHLOGMWVB","created_at":"2026-07-04T23:25:04Z"},{"alias_kind":"pith_short_16","alias_value":"PPUQHLOGMWVBY6GV","created_at":"2026-07-04T23:25:04Z"},{"alias_kind":"pith_short_8","alias_value":"PPUQHLOG","created_at":"2026-07-04T23:25:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PPUQHLOGMWVBY6GVSQD4V6R5ZD","target":"record","payload":{"canonical_record":{"source":{"id":"1804.07461","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T06:35:04Z","cross_cats_sorted":[],"title_canon_sha256":"ca8e56361ec8b4ac7b6d1a9ac5fc06d7f1bb0ec8ca9cf2a6efc6b6865ab94e32","abstract_canon_sha256":"7c3185a67749475da85af13e13a89d4b8e5e1585377e54bbd7179cc03e59de7a"},"schema_version":"1.0"},"canonical_sha256":"7be903adc665aa1c78d59407cafa3dc8dbac72d537996d13c6c93b5a7ea2608e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:25:04.286022Z","signature_b64":"uamNLAB45CEKlU6LLgv1N5i7Q5y3ue27I6IfjjIPP5/XO1R5SE13vRhNRXk/KRsocSaYSvPDiAzVv5Q/jFbsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7be903adc665aa1c78d59407cafa3dc8dbac72d537996d13c6c93b5a7ea2608e","last_reissued_at":"2026-07-04T23:25:04.285462Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:25:04.285462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.07461","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:25:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hui1SvSr5DCzlaNWchX3bsbQteZHdW4dM9ORlBDUEMnKUEo7hQKuyjNX9tW5XfWd3knisPki1I7bqOoC5HilAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:31:43.969404Z"},"content_sha256":"7196550562a34de8522e080f832d558feb3317fc2eb0fda660579ea7b1b094ee","schema_version":"1.0","event_id":"sha256:7196550562a34de8522e080f832d558feb3317fc2eb0fda660579ea7b1b094ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PPUQHLOGMWVBY6GVSQD4V6R5ZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GLUE supplies a benchmark of nine NLU tasks plus diagnostics to test models for general rather than task-specific language understanding.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Wang, Amanpreet Singh, Felix Hill, Julian Michael, Omer Levy, Samuel R. Bowman","submitted_at":"2018-04-20T06:35:04Z","abstract_excerpt":"For natural language understanding (NLU) technology to be maximally useful, both practically and as a scientific object of study, it must be general: it must be able to process language in a way that is not exclusively tailored to any one specific task or dataset. In pursuit of this objective, we introduce the General Language Understanding Evaluation benchmark (GLUE), a tool for evaluating and analyzing the performance of models across a diverse range of existing NLU tasks. GLUE is model-agnostic, but it incentivizes sharing knowledge across tasks because certain tasks have very limited train"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce the General Language Understanding Evaluation benchmark (GLUE), a tool for evaluating and analyzing the performance of models across a diverse range of existing NLU tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen collection of tasks is sufficiently diverse and representative to measure general rather than task-specific language understanding capabilities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GLUE is a multi-task benchmark for general natural language understanding that includes a diagnostic test suite and finds limited gains from current multi-task learning methods over single-task training.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GLUE supplies a benchmark of nine NLU tasks plus diagnostics to test models for general rather than task-specific language understanding.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3a92fb1fa49b66669fd4009a1e5cb58546e153de90323ae898b5e04481437703"},"source":{"id":"1804.07461","kind":"arxiv","version":3},"verdict":{"id":"04ff7455-6c27-44a9-8936-4bd98930ccbb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T21:18:30.925461Z","strongest_claim":"We introduce the General Language Understanding Evaluation benchmark (GLUE), a tool for evaluating and analyzing the performance of models across a diverse range of existing NLU tasks.","one_line_summary":"GLUE is a multi-task benchmark for general natural language understanding that includes a diagnostic test suite and finds limited gains from current multi-task learning methods over single-task training.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen collection of tasks is sufficiently diverse and representative to measure general rather than task-specific language understanding capabilities.","pith_extraction_headline":"GLUE supplies a benchmark of nine NLU tasks plus diagnostics to test models for general rather than task-specific language understanding."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1804.07461/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":52,"sample":[{"doi":"","year":2015,"title":"Neural machine translation by jointly learning to align and translate","work_id":"d075a3c7-7a5a-4abb-88f6-cec9907b6bd6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"The second PASCAL recognising textual entailment challenge","work_id":"449f838d-881f-4ef8-a2dc-bf26172c8ff6","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2009,"title":"The fifth PASCAL recognizing textual entailment challenge","work_id":"035745eb-8dd5-4ddf-873a-f55125dd03e1","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Bowman, Gabor Angeli, Christopher Potts, and Christopher D","work_id":"05240ae0-6419-4ed5-a4f3-816f8c6b6e15","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Semeval-2017 task 1: Semantic textual similarity-multilingual and cross-lingual focused evaluation","work_id":"5d74b84c-cebd-4d37-841c-017aed36aa21","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":52,"snapshot_sha256":"ee54e3734c79debd454e2fa280cb901da922c26aec39372103736eccdaaaf213","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"efdd40a0c6088f115c2617cb559013d247f967ce3af681ebe7c9343060399cc4"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"04ff7455-6c27-44a9-8936-4bd98930ccbb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:25:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ndQ2l5tLwgTlYFbmTIidy4aWxeOCOvUe6paYp+etNZF8zshJU0F1RjmNhm2MV49Dvhn+v3qHMn8kgFdu386fDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:31:43.970304Z"},"content_sha256":"10d1185458eb14e5dfe4659b061c80bccd66eb0b7e836031daaa229b74a7aacc","schema_version":"1.0","event_id":"sha256:10d1185458eb14e5dfe4659b061c80bccd66eb0b7e836031daaa229b74a7aacc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPUQHLOGMWVBY6GVSQD4V6R5ZD/bundle.json","state_url":"https://pith.science/pith/PPUQHLOGMWVBY6GVSQD4V6R5ZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPUQHLOGMWVBY6GVSQD4V6R5ZD/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":"2026-08-03T16:31:43Z","links":{"resolver":"https://pith.science/pith/PPUQHLOGMWVBY6GVSQD4V6R5ZD","bundle":"https://pith.science/pith/PPUQHLOGMWVBY6GVSQD4V6R5ZD/bundle.json","state":"https://pith.science/pith/PPUQHLOGMWVBY6GVSQD4V6R5ZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPUQHLOGMWVBY6GVSQD4V6R5ZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PPUQHLOGMWVBY6GVSQD4V6R5ZD","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":"7c3185a67749475da85af13e13a89d4b8e5e1585377e54bbd7179cc03e59de7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T06:35:04Z","title_canon_sha256":"ca8e56361ec8b4ac7b6d1a9ac5fc06d7f1bb0ec8ca9cf2a6efc6b6865ab94e32"},"schema_version":"1.0","source":{"id":"1804.07461","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07461","created_at":"2026-07-04T23:25:04Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07461v3","created_at":"2026-07-04T23:25:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07461","created_at":"2026-07-04T23:25:04Z"},{"alias_kind":"pith_short_12","alias_value":"PPUQHLOGMWVB","created_at":"2026-07-04T23:25:04Z"},{"alias_kind":"pith_short_16","alias_value":"PPUQHLOGMWVBY6GV","created_at":"2026-07-04T23:25:04Z"},{"alias_kind":"pith_short_8","alias_value":"PPUQHLOG","created_at":"2026-07-04T23:25:04Z"}],"graph_snapshots":[{"event_id":"sha256:10d1185458eb14e5dfe4659b061c80bccd66eb0b7e836031daaa229b74a7aacc","target":"graph","created_at":"2026-07-04T23:25:04Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We introduce the General Language Understanding Evaluation benchmark (GLUE), a tool for evaluating and analyzing the performance of models across a diverse range of existing NLU tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the chosen collection of tasks is sufficiently diverse and representative to measure general rather than task-specific language understanding capabilities."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GLUE is a multi-task benchmark for general natural language understanding that includes a diagnostic test suite and finds limited gains from current multi-task learning methods over single-task training."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GLUE supplies a benchmark of nine NLU tasks plus diagnostics to test models for general rather than task-specific language understanding."}],"snapshot_sha256":"3a92fb1fa49b66669fd4009a1e5cb58546e153de90323ae898b5e04481437703"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"efdd40a0c6088f115c2617cb559013d247f967ce3af681ebe7c9343060399cc4"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1804.07461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For natural language understanding (NLU) technology to be maximally useful, both practically and as a scientific object of study, it must be general: it must be able to process language in a way that is not exclusively tailored to any one specific task or dataset. In pursuit of this objective, we introduce the General Language Understanding Evaluation benchmark (GLUE), a tool for evaluating and analyzing the performance of models across a diverse range of existing NLU tasks. GLUE is model-agnostic, but it incentivizes sharing knowledge across tasks because certain tasks have very limited train","authors_text":"Alex Wang, Amanpreet Singh, Felix Hill, Julian Michael, Omer Levy, Samuel R. Bowman","cross_cats":[],"headline":"GLUE supplies a benchmark of nine NLU tasks plus diagnostics to test models for general rather than task-specific language understanding.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T06:35:04Z","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding"},"references":{"count":52,"internal_anchors":0,"resolved_work":52,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Neural machine translation by jointly learning to align and translate","work_id":"d075a3c7-7a5a-4abb-88f6-cec9907b6bd6","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"The second PASCAL recognising textual entailment challenge","work_id":"449f838d-881f-4ef8-a2dc-bf26172c8ff6","year":2006},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"The fifth PASCAL recognizing textual entailment challenge","work_id":"035745eb-8dd5-4ddf-873a-f55125dd03e1","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Bowman, Gabor Angeli, Christopher Potts, and Christopher D","work_id":"05240ae0-6419-4ed5-a4f3-816f8c6b6e15","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Semeval-2017 task 1: Semantic textual similarity-multilingual and cross-lingual focused evaluation","work_id":"5d74b84c-cebd-4d37-841c-017aed36aa21","year":2017}],"snapshot_sha256":"ee54e3734c79debd454e2fa280cb901da922c26aec39372103736eccdaaaf213"},"source":{"id":"1804.07461","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-12T21:18:30.925461Z","id":"04ff7455-6c27-44a9-8936-4bd98930ccbb","model_set":{"reader":"grok-4.3"},"one_line_summary":"GLUE is a multi-task benchmark for general natural language understanding that includes a diagnostic test suite and finds limited gains from current multi-task learning methods over single-task training.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"GLUE supplies a benchmark of nine NLU tasks plus diagnostics to test models for general rather than task-specific language understanding.","strongest_claim":"We introduce the General Language Understanding Evaluation benchmark (GLUE), a tool for evaluating and analyzing the performance of models across a diverse range of existing NLU tasks.","weakest_assumption":"That the chosen collection of tasks is sufficiently diverse and representative to measure general rather than task-specific language understanding capabilities."}},"verdict_id":"04ff7455-6c27-44a9-8936-4bd98930ccbb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7196550562a34de8522e080f832d558feb3317fc2eb0fda660579ea7b1b094ee","target":"record","created_at":"2026-07-04T23:25:04Z","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":"7c3185a67749475da85af13e13a89d4b8e5e1585377e54bbd7179cc03e59de7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T06:35:04Z","title_canon_sha256":"ca8e56361ec8b4ac7b6d1a9ac5fc06d7f1bb0ec8ca9cf2a6efc6b6865ab94e32"},"schema_version":"1.0","source":{"id":"1804.07461","kind":"arxiv","version":3}},"canonical_sha256":"7be903adc665aa1c78d59407cafa3dc8dbac72d537996d13c6c93b5a7ea2608e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7be903adc665aa1c78d59407cafa3dc8dbac72d537996d13c6c93b5a7ea2608e","first_computed_at":"2026-07-04T23:25:04.285462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:25:04.285462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uamNLAB45CEKlU6LLgv1N5i7Q5y3ue27I6IfjjIPP5/XO1R5SE13vRhNRXk/KRsocSaYSvPDiAzVv5Q/jFbsAQ==","signature_status":"signed_v1","signed_at":"2026-07-04T23:25:04.286022Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.07461","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7196550562a34de8522e080f832d558feb3317fc2eb0fda660579ea7b1b094ee","sha256:10d1185458eb14e5dfe4659b061c80bccd66eb0b7e836031daaa229b74a7aacc"],"state_sha256":"24da7bbbe346f1dc1783a08b3d8f4c66eb560b9d592c3162b14c7feabefc6bfe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7b90gxZdySeAb2JSaHvSoKl1j2QlBmxLFCLSwGjMmNoZamLDSViopZZqWBxvLWrXf07YQqd8Io/OLApmf2CwCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:31:43.976222Z","bundle_sha256":"e8bbe3fc4e85fad8b9f851d4ecd47136cfa961bd3f7b76f2db76f62110fb23e4"}}