{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JXDJBEYHHMDNU62LIU2A3GA4ZY","short_pith_number":"pith:JXDJBEYH","canonical_record":{"source":{"id":"2003.02912","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-05T20:42:51Z","cross_cats_sorted":[],"title_canon_sha256":"234d8bb7d423f175e71309af9c36b17b9b9715d78e3676f9f7c36704df1ae817","abstract_canon_sha256":"e4b3d7a51c66f872c769618a34880b4ad37648359c93d9acf6468da309e78f14"},"schema_version":"1.0"},"canonical_sha256":"4dc69093073b06da7b4b45340d981cce0cd32825595f70dffe86586bdf469a70","source":{"kind":"arxiv","id":"2003.02912","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.02912","created_at":"2026-07-05T00:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2003.02912v1","created_at":"2026-07-05T00:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02912","created_at":"2026-07-05T00:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"JXDJBEYHHMDN","created_at":"2026-07-05T00:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"JXDJBEYHHMDNU62L","created_at":"2026-07-05T00:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"JXDJBEYH","created_at":"2026-07-05T00:46:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JXDJBEYHHMDNU62LIU2A3GA4ZY","target":"record","payload":{"canonical_record":{"source":{"id":"2003.02912","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-05T20:42:51Z","cross_cats_sorted":[],"title_canon_sha256":"234d8bb7d423f175e71309af9c36b17b9b9715d78e3676f9f7c36704df1ae817","abstract_canon_sha256":"e4b3d7a51c66f872c769618a34880b4ad37648359c93d9acf6468da309e78f14"},"schema_version":"1.0"},"canonical_sha256":"4dc69093073b06da7b4b45340d981cce0cd32825595f70dffe86586bdf469a70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:46:08.053580Z","signature_b64":"rZ6VIF5atfzC2zaE6I16dn2I4lQ8GIMTw3qylTUt97yC5s2J7+RnsfnoApbpI/I2sT5j34iKhUsL1oLXr88/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dc69093073b06da7b4b45340d981cce0cd32825595f70dffe86586bdf469a70","last_reissued_at":"2026-07-05T00:46:08.053132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:46:08.053132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.02912","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":"2026-07-05T00:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sI6CiEgRFO3X4tKLAEH0/tO/iyPnPd5bv0CyTXEClIB8BnnWBvlBHLAZV6LLB+bLw57tzT9tazw5r3Pp2FnBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:13:21.699856Z"},"content_sha256":"38d4c01e913ea947969cba5b55f7d11072258e131b7e5e9b502eec7b425d3d52","schema_version":"1.0","event_id":"sha256:38d4c01e913ea947969cba5b55f7d11072258e131b7e5e9b502eec7b425d3d52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JXDJBEYHHMDNU62LIU2A3GA4ZY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What the [MASK]? Making Sense of Language-Specific BERT Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Debora Nozza, Dirk Hovy, Federico Bianchi","submitted_at":"2020-03-05T20:42:51Z","abstract_excerpt":"Recently, Natural Language Processing (NLP) has witnessed an impressive progress in many areas, due to the advent of novel, pretrained contextual representation models. In particular, Devlin et al. (2019) proposed a model, called BERT (Bidirectional Encoder Representations from Transformers), which enables researchers to obtain state-of-the art performance on numerous NLP tasks by fine-tuning the representations on their data set and task, without the need for developing and training highly-specific architectures. The authors also released multilingual BERT (mBERT), a model trained on a corpus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02912","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/2003.02912/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":"2026-07-05T00:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NT6kTd5UkIPMkuMPpkQYpa9scwYpN7l89YMbvKZ3nOcuLyZc697hcRoVAGwn5W+c80CL3OMV4jzx5IykJhHjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:13:21.700221Z"},"content_sha256":"291856d08242e17b6eef633cd30eba19979cd5358d88f44c6ac1da1c30b14129","schema_version":"1.0","event_id":"sha256:291856d08242e17b6eef633cd30eba19979cd5358d88f44c6ac1da1c30b14129"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JXDJBEYHHMDNU62LIU2A3GA4ZY/bundle.json","state_url":"https://pith.science/pith/JXDJBEYHHMDNU62LIU2A3GA4ZY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JXDJBEYHHMDNU62LIU2A3GA4ZY/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":"2026-08-20T01:13:21Z","links":{"resolver":"https://pith.science/pith/JXDJBEYHHMDNU62LIU2A3GA4ZY","bundle":"https://pith.science/pith/JXDJBEYHHMDNU62LIU2A3GA4ZY/bundle.json","state":"https://pith.science/pith/JXDJBEYHHMDNU62LIU2A3GA4ZY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JXDJBEYHHMDNU62LIU2A3GA4ZY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JXDJBEYHHMDNU62LIU2A3GA4ZY","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":"e4b3d7a51c66f872c769618a34880b4ad37648359c93d9acf6468da309e78f14","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-05T20:42:51Z","title_canon_sha256":"234d8bb7d423f175e71309af9c36b17b9b9715d78e3676f9f7c36704df1ae817"},"schema_version":"1.0","source":{"id":"2003.02912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.02912","created_at":"2026-07-05T00:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2003.02912v1","created_at":"2026-07-05T00:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02912","created_at":"2026-07-05T00:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"JXDJBEYHHMDN","created_at":"2026-07-05T00:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"JXDJBEYHHMDNU62L","created_at":"2026-07-05T00:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"JXDJBEYH","created_at":"2026-07-05T00:46:08Z"}],"graph_snapshots":[{"event_id":"sha256:291856d08242e17b6eef633cd30eba19979cd5358d88f44c6ac1da1c30b14129","target":"graph","created_at":"2026-07-05T00:46:08Z","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/2003.02912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Natural Language Processing (NLP) has witnessed an impressive progress in many areas, due to the advent of novel, pretrained contextual representation models. In particular, Devlin et al. (2019) proposed a model, called BERT (Bidirectional Encoder Representations from Transformers), which enables researchers to obtain state-of-the art performance on numerous NLP tasks by fine-tuning the representations on their data set and task, without the need for developing and training highly-specific architectures. The authors also released multilingual BERT (mBERT), a model trained on a corpus","authors_text":"Debora Nozza, Dirk Hovy, Federico Bianchi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-05T20:42:51Z","title":"What the [MASK]? Making Sense of Language-Specific BERT Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02912","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":"sha256:38d4c01e913ea947969cba5b55f7d11072258e131b7e5e9b502eec7b425d3d52","target":"record","created_at":"2026-07-05T00:46:08Z","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":"e4b3d7a51c66f872c769618a34880b4ad37648359c93d9acf6468da309e78f14","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-05T20:42:51Z","title_canon_sha256":"234d8bb7d423f175e71309af9c36b17b9b9715d78e3676f9f7c36704df1ae817"},"schema_version":"1.0","source":{"id":"2003.02912","kind":"arxiv","version":1}},"canonical_sha256":"4dc69093073b06da7b4b45340d981cce0cd32825595f70dffe86586bdf469a70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dc69093073b06da7b4b45340d981cce0cd32825595f70dffe86586bdf469a70","first_computed_at":"2026-07-05T00:46:08.053132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:46:08.053132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rZ6VIF5atfzC2zaE6I16dn2I4lQ8GIMTw3qylTUt97yC5s2J7+RnsfnoApbpI/I2sT5j34iKhUsL1oLXr88/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T00:46:08.053580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.02912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38d4c01e913ea947969cba5b55f7d11072258e131b7e5e9b502eec7b425d3d52","sha256:291856d08242e17b6eef633cd30eba19979cd5358d88f44c6ac1da1c30b14129"],"state_sha256":"efd5761559db8468d1c0cf4d93b54871e4aac553242359b0f195c67cee531234"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LeMoFssrVBbwGo+d86la346eQhdvmJnjqN5HzIualcELjiexJ9PJ0DvRa2hZXdr0uH8vmpvpMdhwHomcmoM4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:13:21.702668Z","bundle_sha256":"68062dec35ba96af91696f60dce3cdd297c1d47c9e74b00db6ba0e79dc72d312"}}