{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JOGCTGIYJM5PQ6X3Z7B2KFVPL4","short_pith_number":"pith:JOGCTGIY","canonical_record":{"source":{"id":"2010.07711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T12:40:56Z","cross_cats_sorted":[],"title_canon_sha256":"acbf5e7205e4fdf6e2500b7e454eee0e5d825d25f76c3cf3abf2392c24286d92","abstract_canon_sha256":"f6c54a05f9eab09f182b8b1b1442860880dd8d306268fea4c80207c63a1a9ca7"},"schema_version":"1.0"},"canonical_sha256":"4b8c2999184b3af87afbcfc3a516af5f1033c1804c986c093a49e86fde28af7f","source":{"kind":"arxiv","id":"2010.07711","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07711","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07711v1","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07711","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"pith_short_12","alias_value":"JOGCTGIYJM5P","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"pith_short_16","alias_value":"JOGCTGIYJM5PQ6X3","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"pith_short_8","alias_value":"JOGCTGIY","created_at":"2026-07-05T01:43:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JOGCTGIYJM5PQ6X3Z7B2KFVPL4","target":"record","payload":{"canonical_record":{"source":{"id":"2010.07711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T12:40:56Z","cross_cats_sorted":[],"title_canon_sha256":"acbf5e7205e4fdf6e2500b7e454eee0e5d825d25f76c3cf3abf2392c24286d92","abstract_canon_sha256":"f6c54a05f9eab09f182b8b1b1442860880dd8d306268fea4c80207c63a1a9ca7"},"schema_version":"1.0"},"canonical_sha256":"4b8c2999184b3af87afbcfc3a516af5f1033c1804c986c093a49e86fde28af7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:19.930452Z","signature_b64":"mrwSS4/8WuUfkKXIuP4RQxns7X4ZrqGOnZi/qwZmhtskcY3q0GvV2Dp6LnUuiOl19bfbhXkOrxBQhdu1YMZMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b8c2999184b3af87afbcfc3a516af5f1033c1804c986c093a49e86fde28af7f","last_reissued_at":"2026-07-05T01:43:19.930036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:19.930036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.07711","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":"2026-07-05T01:43:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tIOol7pAF+xu9Itrq5n84SCUUVciPuom1EE5bGnS7pIcVxbBHOF/XX3NnSkYasp8LatPD8YWNQKKYA9I0+pdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:08:08.826793Z"},"content_sha256":"cc1cf8f643e1adb6a228f3831d916cd88183c1b6701dbbbd85d6638a1987f9b5","schema_version":"1.0","event_id":"sha256:cc1cf8f643e1adb6a228f3831d916cd88183c1b6701dbbbd85d6638a1987f9b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JOGCTGIYJM5PQ6X3Z7B2KFVPL4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Does Chinese BERT Encode Word Structure?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leyang Cui, Yile Wang, Yue Zhang","submitted_at":"2020-10-15T12:40:56Z","abstract_excerpt":"Contextualized representations give significantly improved results for a wide range of NLP tasks. Much work has been dedicated to analyzing the features captured by representative models such as BERT. Existing work finds that syntactic, semantic and word sense knowledge are encoded in BERT. However, little work has investigated word features for character-based languages such as Chinese. We investigate Chinese BERT using both attention weight distribution statistics and probing tasks, finding that (1) word information is captured by BERT; (2) word-level features are mostly in the middle repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07711","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/2010.07711/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":"2026-07-05T01:43:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hc9bzeuGdaZGO2Mt4mB+UbnWzJ6xUz8PThPSMVuOAtR9a3l7tUiSB3iirmpNVWAeraPuhkBeB+PnEt+VBGRrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:08:08.827299Z"},"content_sha256":"8e3a2b083ecccff028e9ec59a25765fce1ad4b872e60564d736e138327d04195","schema_version":"1.0","event_id":"sha256:8e3a2b083ecccff028e9ec59a25765fce1ad4b872e60564d736e138327d04195"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JOGCTGIYJM5PQ6X3Z7B2KFVPL4/bundle.json","state_url":"https://pith.science/pith/JOGCTGIYJM5PQ6X3Z7B2KFVPL4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JOGCTGIYJM5PQ6X3Z7B2KFVPL4/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":"2026-08-04T22:08:08Z","links":{"resolver":"https://pith.science/pith/JOGCTGIYJM5PQ6X3Z7B2KFVPL4","bundle":"https://pith.science/pith/JOGCTGIYJM5PQ6X3Z7B2KFVPL4/bundle.json","state":"https://pith.science/pith/JOGCTGIYJM5PQ6X3Z7B2KFVPL4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JOGCTGIYJM5PQ6X3Z7B2KFVPL4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JOGCTGIYJM5PQ6X3Z7B2KFVPL4","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":"f6c54a05f9eab09f182b8b1b1442860880dd8d306268fea4c80207c63a1a9ca7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T12:40:56Z","title_canon_sha256":"acbf5e7205e4fdf6e2500b7e454eee0e5d825d25f76c3cf3abf2392c24286d92"},"schema_version":"1.0","source":{"id":"2010.07711","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07711","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07711v1","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07711","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"pith_short_12","alias_value":"JOGCTGIYJM5P","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"pith_short_16","alias_value":"JOGCTGIYJM5PQ6X3","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"pith_short_8","alias_value":"JOGCTGIY","created_at":"2026-07-05T01:43:19Z"}],"graph_snapshots":[{"event_id":"sha256:8e3a2b083ecccff028e9ec59a25765fce1ad4b872e60564d736e138327d04195","target":"graph","created_at":"2026-07-05T01:43:19Z","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/2010.07711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contextualized representations give significantly improved results for a wide range of NLP tasks. Much work has been dedicated to analyzing the features captured by representative models such as BERT. Existing work finds that syntactic, semantic and word sense knowledge are encoded in BERT. However, little work has investigated word features for character-based languages such as Chinese. We investigate Chinese BERT using both attention weight distribution statistics and probing tasks, finding that (1) word information is captured by BERT; (2) word-level features are mostly in the middle repres","authors_text":"Leyang Cui, Yile Wang, Yue Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T12:40:56Z","title":"Does Chinese BERT Encode Word Structure?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07711","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:cc1cf8f643e1adb6a228f3831d916cd88183c1b6701dbbbd85d6638a1987f9b5","target":"record","created_at":"2026-07-05T01:43:19Z","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":"f6c54a05f9eab09f182b8b1b1442860880dd8d306268fea4c80207c63a1a9ca7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T12:40:56Z","title_canon_sha256":"acbf5e7205e4fdf6e2500b7e454eee0e5d825d25f76c3cf3abf2392c24286d92"},"schema_version":"1.0","source":{"id":"2010.07711","kind":"arxiv","version":1}},"canonical_sha256":"4b8c2999184b3af87afbcfc3a516af5f1033c1804c986c093a49e86fde28af7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b8c2999184b3af87afbcfc3a516af5f1033c1804c986c093a49e86fde28af7f","first_computed_at":"2026-07-05T01:43:19.930036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:19.930036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mrwSS4/8WuUfkKXIuP4RQxns7X4ZrqGOnZi/qwZmhtskcY3q0GvV2Dp6LnUuiOl19bfbhXkOrxBQhdu1YMZMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:19.930452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.07711","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc1cf8f643e1adb6a228f3831d916cd88183c1b6701dbbbd85d6638a1987f9b5","sha256:8e3a2b083ecccff028e9ec59a25765fce1ad4b872e60564d736e138327d04195"],"state_sha256":"c6141cac444ff300d489be3118b284e6c990a99b64975cf27719b07e75a9348d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rcPscSUVdoBfi3Jq/vwoEP5ztuLrPpP4oYE6LNeYXZ+J6v0vmwq4hs+xJ+Evl5us0lF2gBAMw0aQcohZMSjJBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:08:08.833147Z","bundle_sha256":"612b6835eca368e709f8b9d1c22d8f705dc00f4833380e55edbfa18614031700"}}