{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UECJTQ2C2QTCUHHOQJVRSXXHN6","short_pith_number":"pith:UECJTQ2C","canonical_record":{"source":{"id":"1905.10425","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-24T19:55:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e069aac901254cdd7c1c18a36afdb86cb7b8329ac5518762a089a4cd83fc823","abstract_canon_sha256":"daf5521ad71c73fb85b483c32845a76f955b60b42321120067bb7653ecf2a56b"},"schema_version":"1.0"},"canonical_sha256":"a10499c342d4262a1cee826b195ee76fa48b097acab406c8d425c48361dd0fd0","source":{"kind":"arxiv","id":"1905.10425","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10425","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10425v3","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10425","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"pith_short_12","alias_value":"UECJTQ2C2QTC","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UECJTQ2C2QTCUHHO","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UECJTQ2C","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UECJTQ2C2QTCUHHOQJVRSXXHN6","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10425","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-24T19:55:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e069aac901254cdd7c1c18a36afdb86cb7b8329ac5518762a089a4cd83fc823","abstract_canon_sha256":"daf5521ad71c73fb85b483c32845a76f955b60b42321120067bb7653ecf2a56b"},"schema_version":"1.0"},"canonical_sha256":"a10499c342d4262a1cee826b195ee76fa48b097acab406c8d425c48361dd0fd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:28.421286Z","signature_b64":"mlt1wPKLaskpzfl1D5J2LnyJ6lQ1wuqe6Cjn5SjcB+ZGVoqExAcNF2yBLlJbXxyMg/8aLMD9MZ9jc76VIYKPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a10499c342d4262a1cee826b195ee76fa48b097acab406c8d425c48361dd0fd0","last_reissued_at":"2026-05-17T23:44:28.420754Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:28.420754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10425","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":"2026-05-17T23:44:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IvvU+vfTil/Z/8fbsa3tPHvasriSENoB2juqTkxRS3yTBkxt+HFnmZEx41LdaEg+G4kp1ao9BTX1TShAAYx8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T06:03:27.775038Z"},"content_sha256":"9ea42fb97a630534509ff50fc7908e8a6f1666f59e1a3500deb9a52eb1845bdf","schema_version":"1.0","event_id":"sha256:9ea42fb97a630534509ff50fc7908e8a6f1666f59e1a3500deb9a52eb1845bdf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UECJTQ2C2QTCUHHOQJVRSXXHN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Nikita Nangia, Samuel R. Bowman","submitted_at":"2019-05-24T19:55:34Z","abstract_excerpt":"The GLUE benchmark (Wang et al., 2019b) is a suite of language understanding tasks which has seen dramatic progress in the past year, with average performance moving from 70.0 at launch to 83.9, state of the art at the time of writing (May 24, 2019). Here, we measure human performance on the benchmark, in order to learn whether significant headroom remains for further progress. We provide a conservative estimate of human performance on the benchmark through crowdsourcing: Our annotators are non-experts who must learn each task from a brief set of instructions and 20 examples. In spite of limit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10425","kind":"arxiv","version":3},"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":"2026-05-17T23:44:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLvLVpr3MhmLPuLfuC/IGUL2yYlgH61K28Iau7X2hhlbTUi/dwfg84FdjvBsrnAVH+L4GUrm41IUFnrapjVxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T06:03:27.775895Z"},"content_sha256":"c31c866c2dad9d0195fe1c48c69a43852c6c424dbef88aa4bf0934e6f433a9c8","schema_version":"1.0","event_id":"sha256:c31c866c2dad9d0195fe1c48c69a43852c6c424dbef88aa4bf0934e6f433a9c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UECJTQ2C2QTCUHHOQJVRSXXHN6/bundle.json","state_url":"https://pith.science/pith/UECJTQ2C2QTCUHHOQJVRSXXHN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UECJTQ2C2QTCUHHOQJVRSXXHN6/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":"2026-06-05T06:03:27Z","links":{"resolver":"https://pith.science/pith/UECJTQ2C2QTCUHHOQJVRSXXHN6","bundle":"https://pith.science/pith/UECJTQ2C2QTCUHHOQJVRSXXHN6/bundle.json","state":"https://pith.science/pith/UECJTQ2C2QTCUHHOQJVRSXXHN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UECJTQ2C2QTCUHHOQJVRSXXHN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UECJTQ2C2QTCUHHOQJVRSXXHN6","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":"daf5521ad71c73fb85b483c32845a76f955b60b42321120067bb7653ecf2a56b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-24T19:55:34Z","title_canon_sha256":"0e069aac901254cdd7c1c18a36afdb86cb7b8329ac5518762a089a4cd83fc823"},"schema_version":"1.0","source":{"id":"1905.10425","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10425","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10425v3","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10425","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"pith_short_12","alias_value":"UECJTQ2C2QTC","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UECJTQ2C2QTCUHHO","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UECJTQ2C","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:c31c866c2dad9d0195fe1c48c69a43852c6c424dbef88aa4bf0934e6f433a9c8","target":"graph","created_at":"2026-05-17T23:44:28Z","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":"The GLUE benchmark (Wang et al., 2019b) is a suite of language understanding tasks which has seen dramatic progress in the past year, with average performance moving from 70.0 at launch to 83.9, state of the art at the time of writing (May 24, 2019). Here, we measure human performance on the benchmark, in order to learn whether significant headroom remains for further progress. We provide a conservative estimate of human performance on the benchmark through crowdsourcing: Our annotators are non-experts who must learn each task from a brief set of instructions and 20 examples. In spite of limit","authors_text":"Nikita Nangia, Samuel R. Bowman","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-24T19:55:34Z","title":"Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10425","kind":"arxiv","version":3},"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":"sha256:9ea42fb97a630534509ff50fc7908e8a6f1666f59e1a3500deb9a52eb1845bdf","target":"record","created_at":"2026-05-17T23:44:28Z","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":"daf5521ad71c73fb85b483c32845a76f955b60b42321120067bb7653ecf2a56b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-24T19:55:34Z","title_canon_sha256":"0e069aac901254cdd7c1c18a36afdb86cb7b8329ac5518762a089a4cd83fc823"},"schema_version":"1.0","source":{"id":"1905.10425","kind":"arxiv","version":3}},"canonical_sha256":"a10499c342d4262a1cee826b195ee76fa48b097acab406c8d425c48361dd0fd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a10499c342d4262a1cee826b195ee76fa48b097acab406c8d425c48361dd0fd0","first_computed_at":"2026-05-17T23:44:28.420754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:28.420754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mlt1wPKLaskpzfl1D5J2LnyJ6lQ1wuqe6Cjn5SjcB+ZGVoqExAcNF2yBLlJbXxyMg/8aLMD9MZ9jc76VIYKPDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:28.421286Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10425","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ea42fb97a630534509ff50fc7908e8a6f1666f59e1a3500deb9a52eb1845bdf","sha256:c31c866c2dad9d0195fe1c48c69a43852c6c424dbef88aa4bf0934e6f433a9c8"],"state_sha256":"ac67bb57e96d2a670b312a1b1f2dc73d8dcab1568dbd31b8f655a8ddfe174e80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6JA/2vKtUF10yNV+nqAHJkmLfl1eykdi4U2i/rdm0G9P/xVhEoEr5gozI+vn/DSWxrwgXdcXtPhOollhxwVIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T06:03:27.779991Z","bundle_sha256":"86d1bbf6665df4abb11a8b625aae6ff30225e798aa8de37ec35c41fcd03bc454"}}