{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GSGPBBK34XSZ7MIQXK6EAYMWHG","short_pith_number":"pith:GSGPBBK3","canonical_record":{"source":{"id":"2110.03353","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-07T11:45:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"76cc76f6820375b28760aff6e90efec19d875ca51263897bfb75d87083f02f76","abstract_canon_sha256":"4e914eb6e43c2e68d4e865b89e113505d862188865416cff17bc9e14a4379fec"},"schema_version":"1.0"},"canonical_sha256":"348cf0855be5e59fb110babc40619639ba086d165cf58b980376bc1aeb45881e","source":{"kind":"arxiv","id":"2110.03353","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03353","created_at":"2026-07-05T03:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03353v1","created_at":"2026-07-05T03:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03353","created_at":"2026-07-05T03:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"GSGPBBK34XSZ","created_at":"2026-07-05T03:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"GSGPBBK34XSZ7MIQ","created_at":"2026-07-05T03:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"GSGPBBK3","created_at":"2026-07-05T03:20:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GSGPBBK34XSZ7MIQXK6EAYMWHG","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03353","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-07T11:45:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"76cc76f6820375b28760aff6e90efec19d875ca51263897bfb75d87083f02f76","abstract_canon_sha256":"4e914eb6e43c2e68d4e865b89e113505d862188865416cff17bc9e14a4379fec"},"schema_version":"1.0"},"canonical_sha256":"348cf0855be5e59fb110babc40619639ba086d165cf58b980376bc1aeb45881e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:41.711783Z","signature_b64":"YMG+F1MI0pwGpVZdlMEBHRUHJdT1IDGcXURDapjXMaDtDLqYrwXCpvOE611bunZacaD4H+Qfl4j3BAoAcTdcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"348cf0855be5e59fb110babc40619639ba086d165cf58b980376bc1aeb45881e","last_reissued_at":"2026-07-05T03:20:41.711294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:41.711294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03353","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:20:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DpnQewmSzAFw0D0+cWZDcqBQpAz0tKNR2YpIqrgDk2k2Vv3D/l2vsC+UtEcgqSKIfAsmGO2f6VNNV50TxSACCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T18:09:09.047690Z"},"content_sha256":"2969117c5551065ef89c5720632e151a988a09bcafa5af86d72e3418730f962b","schema_version":"1.0","event_id":"sha256:2969117c5551065ef89c5720632e151a988a09bcafa5af86d72e3418730f962b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GSGPBBK34XSZ7MIQXK6EAYMWHG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noisy Text Data: Achilles' Heel of popular transformer based NLP models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankit Kumar, Anuj Gupta, Kartikay Bagla, Shivam Gupta","submitted_at":"2021-10-07T11:45:31Z","abstract_excerpt":"In the last few years, the ML community has created a number of new NLP models based on transformer architecture. These models have shown great performance for various NLP tasks on benchmark datasets, often surpassing SOTA results. Buoyed with this success, one often finds industry practitioners actively experimenting with fine-tuning these models to build NLP applications for industry use cases. However, for most datasets that are used by practitioners to build industrial NLP applications, it is hard to guarantee the presence of any noise in the data. While most transformer based NLP models h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03353","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/2110.03353/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":"2026-07-05T03:20:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DhY6aG34SXXCmzQ7IEKo+cr23qsLQA7TmirWMXYxPW2vlwjn96hNcRkPVssJhru3bEEQ+vH3BIem4v+InXDRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T18:09:09.048153Z"},"content_sha256":"07010ea03049740140eeb8b4bdd91578f02f0e60a195797e1fa61ce3e09cb9ad","schema_version":"1.0","event_id":"sha256:07010ea03049740140eeb8b4bdd91578f02f0e60a195797e1fa61ce3e09cb9ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GSGPBBK34XSZ7MIQXK6EAYMWHG/bundle.json","state_url":"https://pith.science/pith/GSGPBBK34XSZ7MIQXK6EAYMWHG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GSGPBBK34XSZ7MIQXK6EAYMWHG/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":"2026-07-31T18:09:09Z","links":{"resolver":"https://pith.science/pith/GSGPBBK34XSZ7MIQXK6EAYMWHG","bundle":"https://pith.science/pith/GSGPBBK34XSZ7MIQXK6EAYMWHG/bundle.json","state":"https://pith.science/pith/GSGPBBK34XSZ7MIQXK6EAYMWHG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GSGPBBK34XSZ7MIQXK6EAYMWHG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GSGPBBK34XSZ7MIQXK6EAYMWHG","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":"4e914eb6e43c2e68d4e865b89e113505d862188865416cff17bc9e14a4379fec","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-07T11:45:31Z","title_canon_sha256":"76cc76f6820375b28760aff6e90efec19d875ca51263897bfb75d87083f02f76"},"schema_version":"1.0","source":{"id":"2110.03353","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03353","created_at":"2026-07-05T03:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03353v1","created_at":"2026-07-05T03:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03353","created_at":"2026-07-05T03:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"GSGPBBK34XSZ","created_at":"2026-07-05T03:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"GSGPBBK34XSZ7MIQ","created_at":"2026-07-05T03:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"GSGPBBK3","created_at":"2026-07-05T03:20:41Z"}],"graph_snapshots":[{"event_id":"sha256:07010ea03049740140eeb8b4bdd91578f02f0e60a195797e1fa61ce3e09cb9ad","target":"graph","created_at":"2026-07-05T03:20:41Z","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/2110.03353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the last few years, the ML community has created a number of new NLP models based on transformer architecture. These models have shown great performance for various NLP tasks on benchmark datasets, often surpassing SOTA results. Buoyed with this success, one often finds industry practitioners actively experimenting with fine-tuning these models to build NLP applications for industry use cases. However, for most datasets that are used by practitioners to build industrial NLP applications, it is hard to guarantee the presence of any noise in the data. While most transformer based NLP models h","authors_text":"Ankit Kumar, Anuj Gupta, Kartikay Bagla, Shivam Gupta","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-07T11:45:31Z","title":"Noisy Text Data: Achilles' Heel of popular transformer based NLP models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03353","kind":"arxiv","version":1},"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":"sha256:2969117c5551065ef89c5720632e151a988a09bcafa5af86d72e3418730f962b","target":"record","created_at":"2026-07-05T03:20:41Z","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":"4e914eb6e43c2e68d4e865b89e113505d862188865416cff17bc9e14a4379fec","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-07T11:45:31Z","title_canon_sha256":"76cc76f6820375b28760aff6e90efec19d875ca51263897bfb75d87083f02f76"},"schema_version":"1.0","source":{"id":"2110.03353","kind":"arxiv","version":1}},"canonical_sha256":"348cf0855be5e59fb110babc40619639ba086d165cf58b980376bc1aeb45881e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"348cf0855be5e59fb110babc40619639ba086d165cf58b980376bc1aeb45881e","first_computed_at":"2026-07-05T03:20:41.711294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:41.711294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YMG+F1MI0pwGpVZdlMEBHRUHJdT1IDGcXURDapjXMaDtDLqYrwXCpvOE611bunZacaD4H+Qfl4j3BAoAcTdcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:41.711783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03353","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2969117c5551065ef89c5720632e151a988a09bcafa5af86d72e3418730f962b","sha256:07010ea03049740140eeb8b4bdd91578f02f0e60a195797e1fa61ce3e09cb9ad"],"state_sha256":"60839474b3e07b2eb83f238d8fa41beaeaefa33b769a3103eb05352a60072728"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IA1Xkl558N2czVdRYK8BH5jeza9fwzGZZhcMsMitS5fgY75PLBotZMVbPYFLrMvdZ3vD6pvQcTDxAsME7d28Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T18:09:09.052892Z","bundle_sha256":"12023f843fad89bee6b9a9f339ac9f9813e227899eb3efd8238594bfd9e0aa3a"}}