{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KCMZZ64OJOA4YRG2BEIV54Z6UE","short_pith_number":"pith:KCMZZ64O","canonical_record":{"source":{"id":"2010.10906","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-21T11:28:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e66e679ad6e49e4af26aa73addbad033118ca91e8105e2cb061cb726c02803aa","abstract_canon_sha256":"0e763389d38f771243444836f3fdde3f13be159e3d52a780e51ee65ab8393c67"},"schema_version":"1.0"},"canonical_sha256":"50999cfb8e4b81cc44da09115ef33ea129d44f91cb409c177df4e5af4babbb49","source":{"kind":"arxiv","id":"2010.10906","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.10906","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"arxiv_version","alias_value":"2010.10906v4","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10906","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"pith_short_12","alias_value":"KCMZZ64OJOA4","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"pith_short_16","alias_value":"KCMZZ64OJOA4YRG2","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"pith_short_8","alias_value":"KCMZZ64O","created_at":"2026-07-05T01:56:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KCMZZ64OJOA4YRG2BEIV54Z6UE","target":"record","payload":{"canonical_record":{"source":{"id":"2010.10906","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-21T11:28:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e66e679ad6e49e4af26aa73addbad033118ca91e8105e2cb061cb726c02803aa","abstract_canon_sha256":"0e763389d38f771243444836f3fdde3f13be159e3d52a780e51ee65ab8393c67"},"schema_version":"1.0"},"canonical_sha256":"50999cfb8e4b81cc44da09115ef33ea129d44f91cb409c177df4e5af4babbb49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:44.752062Z","signature_b64":"uAJuXOg3B1Ww+e1FxmXr0htrux7WYuZdoKb4HEqVF8NwBDMyIUaFHL/Yqsp6joTl0askdaLZzq8tCzJlTjRPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50999cfb8e4b81cc44da09115ef33ea129d44f91cb409c177df4e5af4babbb49","last_reissued_at":"2026-07-05T01:56:44.751611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:44.751611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.10906","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:56:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iTIxHsys07vaWDfEd9FPvA8HbuukPsW8UCTB3Vwu/WG9jctq7VqwksIeNYDX627I5H83sdgwOiZezo1TZEm5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:15:14.315168Z"},"content_sha256":"7ff4ade7895e3155ed7a69f368d7052f1fce309eb690f019377c85e7e5ac469a","schema_version":"1.0","event_id":"sha256:7ff4ade7895e3155ed7a69f368d7052f1fce309eb690f019377c85e7e5ac469a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KCMZZ64OJOA4YRG2BEIV54Z6UE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"German's Next Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Branden Chan, Stefan Schweter, Timo M\\\"oller","submitted_at":"2020-10-21T11:28:23Z","abstract_excerpt":"In this work we present the experiments which lead to the creation of our BERT and ELECTRA based German language models, GBERT and GELECTRA. By varying the input training data, model size, and the presence of Whole Word Masking (WWM) we were able to attain SoTA performance across a set of document classification and named entity recognition (NER) tasks for both models of base and large size. We adopt an evaluation driven approach in training these models and our results indicate that both adding more data and utilizing WWM improve model performance. By benchmarking against existing German mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10906","kind":"arxiv","version":4},"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/2010.10906/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":"2026-07-05T01:56:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fVgA1aHDyGEVrnFfUd10Hi4O5M9lRJo96GMAUriRA6kfeHIteyHBVJ3SCfKq+uHxtSVc1ROlNmizcAwGqvyiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:15:14.315652Z"},"content_sha256":"baa2b5c36cb21312751ccb2f2932705b8a9104dd67cc2645e7b73c8b564f0677","schema_version":"1.0","event_id":"sha256:baa2b5c36cb21312751ccb2f2932705b8a9104dd67cc2645e7b73c8b564f0677"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KCMZZ64OJOA4YRG2BEIV54Z6UE/bundle.json","state_url":"https://pith.science/pith/KCMZZ64OJOA4YRG2BEIV54Z6UE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KCMZZ64OJOA4YRG2BEIV54Z6UE/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":"2026-08-05T00:15:14Z","links":{"resolver":"https://pith.science/pith/KCMZZ64OJOA4YRG2BEIV54Z6UE","bundle":"https://pith.science/pith/KCMZZ64OJOA4YRG2BEIV54Z6UE/bundle.json","state":"https://pith.science/pith/KCMZZ64OJOA4YRG2BEIV54Z6UE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KCMZZ64OJOA4YRG2BEIV54Z6UE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KCMZZ64OJOA4YRG2BEIV54Z6UE","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":"0e763389d38f771243444836f3fdde3f13be159e3d52a780e51ee65ab8393c67","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-21T11:28:23Z","title_canon_sha256":"e66e679ad6e49e4af26aa73addbad033118ca91e8105e2cb061cb726c02803aa"},"schema_version":"1.0","source":{"id":"2010.10906","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.10906","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"arxiv_version","alias_value":"2010.10906v4","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10906","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"pith_short_12","alias_value":"KCMZZ64OJOA4","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"pith_short_16","alias_value":"KCMZZ64OJOA4YRG2","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"pith_short_8","alias_value":"KCMZZ64O","created_at":"2026-07-05T01:56:44Z"}],"graph_snapshots":[{"event_id":"sha256:baa2b5c36cb21312751ccb2f2932705b8a9104dd67cc2645e7b73c8b564f0677","target":"graph","created_at":"2026-07-05T01:56:44Z","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/2010.10906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work we present the experiments which lead to the creation of our BERT and ELECTRA based German language models, GBERT and GELECTRA. By varying the input training data, model size, and the presence of Whole Word Masking (WWM) we were able to attain SoTA performance across a set of document classification and named entity recognition (NER) tasks for both models of base and large size. We adopt an evaluation driven approach in training these models and our results indicate that both adding more data and utilizing WWM improve model performance. By benchmarking against existing German mode","authors_text":"Branden Chan, Stefan Schweter, Timo M\\\"oller","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-21T11:28:23Z","title":"German's Next Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10906","kind":"arxiv","version":4},"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":"sha256:7ff4ade7895e3155ed7a69f368d7052f1fce309eb690f019377c85e7e5ac469a","target":"record","created_at":"2026-07-05T01:56:44Z","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":"0e763389d38f771243444836f3fdde3f13be159e3d52a780e51ee65ab8393c67","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-21T11:28:23Z","title_canon_sha256":"e66e679ad6e49e4af26aa73addbad033118ca91e8105e2cb061cb726c02803aa"},"schema_version":"1.0","source":{"id":"2010.10906","kind":"arxiv","version":4}},"canonical_sha256":"50999cfb8e4b81cc44da09115ef33ea129d44f91cb409c177df4e5af4babbb49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50999cfb8e4b81cc44da09115ef33ea129d44f91cb409c177df4e5af4babbb49","first_computed_at":"2026-07-05T01:56:44.751611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:44.751611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uAJuXOg3B1Ww+e1FxmXr0htrux7WYuZdoKb4HEqVF8NwBDMyIUaFHL/Yqsp6joTl0askdaLZzq8tCzJlTjRPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:44.752062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.10906","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ff4ade7895e3155ed7a69f368d7052f1fce309eb690f019377c85e7e5ac469a","sha256:baa2b5c36cb21312751ccb2f2932705b8a9104dd67cc2645e7b73c8b564f0677"],"state_sha256":"ece6739cfef1f73c39efd00dc984294fd1ab8c07ad406f2fd38abf2a28f67fbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TswqH79LYXG41xuDLjg29zNBiarxHqemGctkyL7cY4WZIeTBXLpEUJNId9BXzYah0B1zAJSul8MYCqjpfrRjAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:15:14.318977Z","bundle_sha256":"cc6629a3d340c567258602fb7d585cf42c9ea0b42326c8737bea24f56233234f"}}