{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:H5HJTGP2Q22AIAUM3NWII47DMM","short_pith_number":"pith:H5HJTGP2","canonical_record":{"source":{"id":"1705.00108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-29T01:13:04Z","cross_cats_sorted":[],"title_canon_sha256":"b51f80ddfa54cb61feea4d1fe7d73aac082c09f51200b4a7d7e34962a7daa1c6","abstract_canon_sha256":"5d10613b4992e564ca35087d89de40768c7d665b0d37868cdbf5c9288942c164"},"schema_version":"1.0"},"canonical_sha256":"3f4e9999fa86b404028cdb6c8473e3631df664e206b2afcb1d0e5b4746185de7","source":{"kind":"arxiv","id":"1705.00108","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.00108","created_at":"2026-05-18T00:45:21Z"},{"alias_kind":"arxiv_version","alias_value":"1705.00108v1","created_at":"2026-05-18T00:45:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00108","created_at":"2026-05-18T00:45:21Z"},{"alias_kind":"pith_short_12","alias_value":"H5HJTGP2Q22A","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"H5HJTGP2Q22AIAUM","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"H5HJTGP2","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:H5HJTGP2Q22AIAUM3NWII47DMM","target":"record","payload":{"canonical_record":{"source":{"id":"1705.00108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-29T01:13:04Z","cross_cats_sorted":[],"title_canon_sha256":"b51f80ddfa54cb61feea4d1fe7d73aac082c09f51200b4a7d7e34962a7daa1c6","abstract_canon_sha256":"5d10613b4992e564ca35087d89de40768c7d665b0d37868cdbf5c9288942c164"},"schema_version":"1.0"},"canonical_sha256":"3f4e9999fa86b404028cdb6c8473e3631df664e206b2afcb1d0e5b4746185de7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:21.452614Z","signature_b64":"TQqbE10ZFJmMTEyZ2To6ktY7MH7TyYOeHEVhkjsSXu/PnfJg5xeAr+z7nNgcinOa7XpmgfBMMOSHUdxlWpGPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f4e9999fa86b404028cdb6c8473e3631df664e206b2afcb1d0e5b4746185de7","last_reissued_at":"2026-05-18T00:45:21.451868Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:21.451868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.00108","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":"2026-05-18T00:45:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aOgdwXHXNvWxpCyRV1FuwHghlTxT+kKujDbtwPn1C4wXL7sMPtuV6vjBcgKhSy/Uq7WLB/sXuE7y/PbiPZalAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:00:00.558804Z"},"content_sha256":"7bd6a15cfbae5945f91fd29c80d52d48df2fa6ff1546d707a35bbc9079369304","schema_version":"1.0","event_id":"sha256:7bd6a15cfbae5945f91fd29c80d52d48df2fa6ff1546d707a35bbc9079369304"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:H5HJTGP2Q22AIAUM3NWII47DMM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised sequence tagging with bidirectional language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chandra Bhagavatula, Matthew E. Peters, Russell Power, Waleed Ammar","submitted_at":"2017-04-29T01:13:04Z","abstract_excerpt":"Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent network that operates on word-level representations to produce context sensitive representations is trained on relatively little labeled data. In this paper, we demonstrate a general semi-supervised approach for adding pre- trained context embeddings from bidirectional language models to NLP systems and apply it to sequence labeling tasks. We evaluate our model on two standard datasets for named entity recognition (NER) an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00108","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":""},"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":"2026-05-18T00:45:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+TtVen6ADhqcCb8/rcgGrnDwhHDzckIGjp4jVzNUaNWAr0yRqvTGKpH4zzQ2SNST03YGQqz6I1CZDoFT07VNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:00:00.559403Z"},"content_sha256":"1d9f511a35070fdf8d45184a4b074f59ad2f06e861063b6e091643aad21b3f0c","schema_version":"1.0","event_id":"sha256:1d9f511a35070fdf8d45184a4b074f59ad2f06e861063b6e091643aad21b3f0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5HJTGP2Q22AIAUM3NWII47DMM/bundle.json","state_url":"https://pith.science/pith/H5HJTGP2Q22AIAUM3NWII47DMM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5HJTGP2Q22AIAUM3NWII47DMM/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":"2026-05-28T23:00:00Z","links":{"resolver":"https://pith.science/pith/H5HJTGP2Q22AIAUM3NWII47DMM","bundle":"https://pith.science/pith/H5HJTGP2Q22AIAUM3NWII47DMM/bundle.json","state":"https://pith.science/pith/H5HJTGP2Q22AIAUM3NWII47DMM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5HJTGP2Q22AIAUM3NWII47DMM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:H5HJTGP2Q22AIAUM3NWII47DMM","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":"5d10613b4992e564ca35087d89de40768c7d665b0d37868cdbf5c9288942c164","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-29T01:13:04Z","title_canon_sha256":"b51f80ddfa54cb61feea4d1fe7d73aac082c09f51200b4a7d7e34962a7daa1c6"},"schema_version":"1.0","source":{"id":"1705.00108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.00108","created_at":"2026-05-18T00:45:21Z"},{"alias_kind":"arxiv_version","alias_value":"1705.00108v1","created_at":"2026-05-18T00:45:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00108","created_at":"2026-05-18T00:45:21Z"},{"alias_kind":"pith_short_12","alias_value":"H5HJTGP2Q22A","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"H5HJTGP2Q22AIAUM","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"H5HJTGP2","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:1d9f511a35070fdf8d45184a4b074f59ad2f06e861063b6e091643aad21b3f0c","target":"graph","created_at":"2026-05-18T00:45:21Z","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"},"paper":{"abstract_excerpt":"Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent network that operates on word-level representations to produce context sensitive representations is trained on relatively little labeled data. In this paper, we demonstrate a general semi-supervised approach for adding pre- trained context embeddings from bidirectional language models to NLP systems and apply it to sequence labeling tasks. We evaluate our model on two standard datasets for named entity recognition (NER) an","authors_text":"Chandra Bhagavatula, Matthew E. Peters, Russell Power, Waleed Ammar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-29T01:13:04Z","title":"Semi-supervised sequence tagging with bidirectional language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00108","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":"sha256:7bd6a15cfbae5945f91fd29c80d52d48df2fa6ff1546d707a35bbc9079369304","target":"record","created_at":"2026-05-18T00:45:21Z","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":"5d10613b4992e564ca35087d89de40768c7d665b0d37868cdbf5c9288942c164","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-29T01:13:04Z","title_canon_sha256":"b51f80ddfa54cb61feea4d1fe7d73aac082c09f51200b4a7d7e34962a7daa1c6"},"schema_version":"1.0","source":{"id":"1705.00108","kind":"arxiv","version":1}},"canonical_sha256":"3f4e9999fa86b404028cdb6c8473e3631df664e206b2afcb1d0e5b4746185de7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f4e9999fa86b404028cdb6c8473e3631df664e206b2afcb1d0e5b4746185de7","first_computed_at":"2026-05-18T00:45:21.451868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:21.451868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TQqbE10ZFJmMTEyZ2To6ktY7MH7TyYOeHEVhkjsSXu/PnfJg5xeAr+z7nNgcinOa7XpmgfBMMOSHUdxlWpGPCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:21.452614Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.00108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bd6a15cfbae5945f91fd29c80d52d48df2fa6ff1546d707a35bbc9079369304","sha256:1d9f511a35070fdf8d45184a4b074f59ad2f06e861063b6e091643aad21b3f0c"],"state_sha256":"d873ffa7f52ab18f0059ab514b447ef71f928ea3dadaf204a4493dadba50e7f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tK6nceuYthtd4LMKPg3pIZGumggZzxBhNb2Qu9gmkxEuSVCPLb5b8ngOGU1JItkLrH8ZfgFtIs1I6Elzu3iWBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:00:00.562309Z","bundle_sha256":"a425f18532763438b0a0638860da69c56b0d26672a7abba3cb6e39611bbaa614"}}