{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RNOECZ7TWVQX7P3PBCT27BHVYQ","short_pith_number":"pith:RNOECZ7T","canonical_record":{"source":{"id":"2302.01588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-03T08:04:59Z","cross_cats_sorted":[],"title_canon_sha256":"58aa0b93c221d6fd4a4c6d9923deffbaf575f5c354aa29cce428f14ea9f72706","abstract_canon_sha256":"aff5137b7b8776405ed6b6dc861d585f30e6ac9ccb4c6c08802c737c64aa4770"},"schema_version":"1.0"},"canonical_sha256":"8b5c4167f3b5617fbf6f08a7af84f5c410cd203e1ca7c45459dc5dceb59d4f6c","source":{"kind":"arxiv","id":"2302.01588","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01588","created_at":"2026-07-05T05:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01588v1","created_at":"2026-07-05T05:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01588","created_at":"2026-07-05T05:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"RNOECZ7TWVQX","created_at":"2026-07-05T05:38:34Z"},{"alias_kind":"pith_short_16","alias_value":"RNOECZ7TWVQX7P3P","created_at":"2026-07-05T05:38:34Z"},{"alias_kind":"pith_short_8","alias_value":"RNOECZ7T","created_at":"2026-07-05T05:38:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RNOECZ7TWVQX7P3PBCT27BHVYQ","target":"record","payload":{"canonical_record":{"source":{"id":"2302.01588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-03T08:04:59Z","cross_cats_sorted":[],"title_canon_sha256":"58aa0b93c221d6fd4a4c6d9923deffbaf575f5c354aa29cce428f14ea9f72706","abstract_canon_sha256":"aff5137b7b8776405ed6b6dc861d585f30e6ac9ccb4c6c08802c737c64aa4770"},"schema_version":"1.0"},"canonical_sha256":"8b5c4167f3b5617fbf6f08a7af84f5c410cd203e1ca7c45459dc5dceb59d4f6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:34.063567Z","signature_b64":"6nj9hVObVskiWycgEiffHzlBL15ksO7g//xLYfKHOzcf2/2ZC3Jh3cvAogRkCnIeO5A7qdo/P4yliXkFdE+tDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b5c4167f3b5617fbf6f08a7af84f5c410cd203e1ca7c45459dc5dceb59d4f6c","last_reissued_at":"2026-07-05T05:38:34.063107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:34.063107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.01588","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":"2026-07-05T05:38:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hZ3nSqRb2thzcZNC4GdWhG+MzQx/mqqS7FVSOOzM3Gul20Zs8ntXj4udZ4mMcjlkI82i22QOGgKAH/L4w+tlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:23:02.062524Z"},"content_sha256":"3da13a99dd86933a935723d3816a5ad846695edcb07a2340ac135077eb54403d","schema_version":"1.0","event_id":"sha256:3da13a99dd86933a935723d3816a5ad846695edcb07a2340ac135077eb54403d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RNOECZ7TWVQX7P3PBCT27BHVYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bioformer: an efficient transformer language model for biomedical text mining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chih-Hsuan Wei, Kai Wang, Li Fang, Qingyu Chen, Zhiyong Lu","submitted_at":"2023-02-03T08:04:59Z","abstract_excerpt":"Pretrained language models such as Bidirectional Encoder Representations from Transformers (BERT) have achieved state-of-the-art performance in natural language processing (NLP) tasks. Recently, BERT has been adapted to the biomedical domain. Despite the effectiveness, these models have hundreds of millions of parameters and are computationally expensive when applied to large-scale NLP applications. We hypothesized that the number of parameters of the original BERT can be dramatically reduced with minor impact on performance. In this study, we present Bioformer, a compact BERT model for biomed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01588","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/2302.01588/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":"2026-07-05T05:38:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xpKmjs6Ak9/7McKj/t2HabqAbYYKh2YtO5iZUAzieJUFSaVzf3QnkLwNSvUoIzs1hcgyK6ErbAK3ZjG3jugmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:23:02.063044Z"},"content_sha256":"10a9c6d9b659e40cb62920cece6521f1e2117c8b9a8db655608905b83d839b97","schema_version":"1.0","event_id":"sha256:10a9c6d9b659e40cb62920cece6521f1e2117c8b9a8db655608905b83d839b97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RNOECZ7TWVQX7P3PBCT27BHVYQ/bundle.json","state_url":"https://pith.science/pith/RNOECZ7TWVQX7P3PBCT27BHVYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RNOECZ7TWVQX7P3PBCT27BHVYQ/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":"2026-08-11T02:23:02Z","links":{"resolver":"https://pith.science/pith/RNOECZ7TWVQX7P3PBCT27BHVYQ","bundle":"https://pith.science/pith/RNOECZ7TWVQX7P3PBCT27BHVYQ/bundle.json","state":"https://pith.science/pith/RNOECZ7TWVQX7P3PBCT27BHVYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RNOECZ7TWVQX7P3PBCT27BHVYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RNOECZ7TWVQX7P3PBCT27BHVYQ","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":"aff5137b7b8776405ed6b6dc861d585f30e6ac9ccb4c6c08802c737c64aa4770","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-03T08:04:59Z","title_canon_sha256":"58aa0b93c221d6fd4a4c6d9923deffbaf575f5c354aa29cce428f14ea9f72706"},"schema_version":"1.0","source":{"id":"2302.01588","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01588","created_at":"2026-07-05T05:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01588v1","created_at":"2026-07-05T05:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01588","created_at":"2026-07-05T05:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"RNOECZ7TWVQX","created_at":"2026-07-05T05:38:34Z"},{"alias_kind":"pith_short_16","alias_value":"RNOECZ7TWVQX7P3P","created_at":"2026-07-05T05:38:34Z"},{"alias_kind":"pith_short_8","alias_value":"RNOECZ7T","created_at":"2026-07-05T05:38:34Z"}],"graph_snapshots":[{"event_id":"sha256:10a9c6d9b659e40cb62920cece6521f1e2117c8b9a8db655608905b83d839b97","target":"graph","created_at":"2026-07-05T05:38:34Z","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/2302.01588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained language models such as Bidirectional Encoder Representations from Transformers (BERT) have achieved state-of-the-art performance in natural language processing (NLP) tasks. Recently, BERT has been adapted to the biomedical domain. Despite the effectiveness, these models have hundreds of millions of parameters and are computationally expensive when applied to large-scale NLP applications. We hypothesized that the number of parameters of the original BERT can be dramatically reduced with minor impact on performance. In this study, we present Bioformer, a compact BERT model for biomed","authors_text":"Chih-Hsuan Wei, Kai Wang, Li Fang, Qingyu Chen, Zhiyong Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-03T08:04:59Z","title":"Bioformer: an efficient transformer language model for biomedical text mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01588","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":"sha256:3da13a99dd86933a935723d3816a5ad846695edcb07a2340ac135077eb54403d","target":"record","created_at":"2026-07-05T05:38:34Z","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":"aff5137b7b8776405ed6b6dc861d585f30e6ac9ccb4c6c08802c737c64aa4770","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-03T08:04:59Z","title_canon_sha256":"58aa0b93c221d6fd4a4c6d9923deffbaf575f5c354aa29cce428f14ea9f72706"},"schema_version":"1.0","source":{"id":"2302.01588","kind":"arxiv","version":1}},"canonical_sha256":"8b5c4167f3b5617fbf6f08a7af84f5c410cd203e1ca7c45459dc5dceb59d4f6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b5c4167f3b5617fbf6f08a7af84f5c410cd203e1ca7c45459dc5dceb59d4f6c","first_computed_at":"2026-07-05T05:38:34.063107Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:34.063107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6nj9hVObVskiWycgEiffHzlBL15ksO7g//xLYfKHOzcf2/2ZC3Jh3cvAogRkCnIeO5A7qdo/P4yliXkFdE+tDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:34.063567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.01588","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3da13a99dd86933a935723d3816a5ad846695edcb07a2340ac135077eb54403d","sha256:10a9c6d9b659e40cb62920cece6521f1e2117c8b9a8db655608905b83d839b97"],"state_sha256":"83b8c57b19b6aa5f0acfd0efbf709bb05fc917c76843e0c5dca6dad9c8a61a23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z1Ho+0PLXxwcNBR+e3U5eMn00ZnTMZVtg2haPpgAg8Xcw1++pEBFteEInrbOefnaYv5rl8BXcXCTa+yVQXUxDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:23:02.067822Z","bundle_sha256":"f7bd5b7809577d14eed37c987fb7bfddfe87a15606c9423244b01c697b6b55c3"}}