{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:DKCX5FPQXW7BPU2RJUUIPGZ522","short_pith_number":"pith:DKCX5FPQ","canonical_record":{"source":{"id":"1708.00107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T00:05:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"24d41fc2b690dc545f72c7ad46fd339561f78a500cdb421eeb38af8921ef8d37","abstract_canon_sha256":"e2451bd014c4b085dcb7373ea2be03cfc483027f34776e47b3d215975773e0b5"},"schema_version":"1.0"},"canonical_sha256":"1a857e95f0bdbe17d3514d28879b3dd69f9be913938b42aab1682a35b4f39040","source":{"kind":"arxiv","id":"1708.00107","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00107","created_at":"2026-05-18T00:12:48Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00107v2","created_at":"2026-05-18T00:12:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00107","created_at":"2026-05-18T00:12:48Z"},{"alias_kind":"pith_short_12","alias_value":"DKCX5FPQXW7B","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"DKCX5FPQXW7BPU2R","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"DKCX5FPQ","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:DKCX5FPQXW7BPU2RJUUIPGZ522","target":"record","payload":{"canonical_record":{"source":{"id":"1708.00107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T00:05:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"24d41fc2b690dc545f72c7ad46fd339561f78a500cdb421eeb38af8921ef8d37","abstract_canon_sha256":"e2451bd014c4b085dcb7373ea2be03cfc483027f34776e47b3d215975773e0b5"},"schema_version":"1.0"},"canonical_sha256":"1a857e95f0bdbe17d3514d28879b3dd69f9be913938b42aab1682a35b4f39040","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:48.774548Z","signature_b64":"D5JGjsBFU2DGY5r4caAul/ma4zP1ayKfnLzH50MbJj+ozRXXbBpOZT3krBp91HR4yZPIVcv9tuW2pf/Z+Q8WCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a857e95f0bdbe17d3514d28879b3dd69f9be913938b42aab1682a35b4f39040","last_reissued_at":"2026-05-18T00:12:48.773865Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:48.773865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.00107","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:12:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5nf1rHS5aRnCGcgJeOxMbi4zmaK5is27De/hMZy9DGPGNdPuwjszpee5gf0kbhO+NL9WqF8u3HcynOpxOSQ6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:22:17.999067Z"},"content_sha256":"00137a431a52323140679266919fb2040609f721bb1b5e68ec1bd1067c381a35","schema_version":"1.0","event_id":"sha256:00137a431a52323140679266919fb2040609f721bb1b5e68ec1bd1067c381a35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:DKCX5FPQXW7BPU2RJUUIPGZ522","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learned in Translation: Contextualized Word Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Caiming Xiong, James Bradbury, Richard Socher","submitted_at":"2017-08-01T00:05:34Z","abstract_excerpt":"Computer vision has benefited from initializing multiple deep layers with weights pretrained on large supervised training sets like ImageNet. Natural language processing (NLP) typically sees initialization of only the lowest layer of deep models with pretrained word vectors. In this paper, we use a deep LSTM encoder from an attentional sequence-to-sequence model trained for machine translation (MT) to contextualize word vectors. We show that adding these context vectors (CoVe) improves performance over using only unsupervised word and character vectors on a wide variety of common NLP tasks: se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00107","kind":"arxiv","version":2},"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":"2026-05-18T00:12:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RcEbuEViZtJgjTh7RhU8iz6PvytEcsrimmMOOcsd3JzhTfEkCv6CtWiJQUDAIpIuslLMpgii+rkWgynZM5CPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:22:17.999608Z"},"content_sha256":"57e6728f0d2b3f149c54ea42ceeac616ee6c0df03a9eac6b1dcaee2c5765dd12","schema_version":"1.0","event_id":"sha256:57e6728f0d2b3f149c54ea42ceeac616ee6c0df03a9eac6b1dcaee2c5765dd12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/bundle.json","state_url":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/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":"2026-05-27T13:22:18Z","links":{"resolver":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522","bundle":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/bundle.json","state":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DKCX5FPQXW7BPU2RJUUIPGZ522","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":"e2451bd014c4b085dcb7373ea2be03cfc483027f34776e47b3d215975773e0b5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T00:05:34Z","title_canon_sha256":"24d41fc2b690dc545f72c7ad46fd339561f78a500cdb421eeb38af8921ef8d37"},"schema_version":"1.0","source":{"id":"1708.00107","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00107","created_at":"2026-05-18T00:12:48Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00107v2","created_at":"2026-05-18T00:12:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00107","created_at":"2026-05-18T00:12:48Z"},{"alias_kind":"pith_short_12","alias_value":"DKCX5FPQXW7B","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"DKCX5FPQXW7BPU2R","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"DKCX5FPQ","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:57e6728f0d2b3f149c54ea42ceeac616ee6c0df03a9eac6b1dcaee2c5765dd12","target":"graph","created_at":"2026-05-18T00:12:48Z","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":"Computer vision has benefited from initializing multiple deep layers with weights pretrained on large supervised training sets like ImageNet. Natural language processing (NLP) typically sees initialization of only the lowest layer of deep models with pretrained word vectors. In this paper, we use a deep LSTM encoder from an attentional sequence-to-sequence model trained for machine translation (MT) to contextualize word vectors. We show that adding these context vectors (CoVe) improves performance over using only unsupervised word and character vectors on a wide variety of common NLP tasks: se","authors_text":"Bryan McCann, Caiming Xiong, James Bradbury, Richard Socher","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T00:05:34Z","title":"Learned in Translation: Contextualized Word Vectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00107","kind":"arxiv","version":2},"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":"sha256:00137a431a52323140679266919fb2040609f721bb1b5e68ec1bd1067c381a35","target":"record","created_at":"2026-05-18T00:12:48Z","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":"e2451bd014c4b085dcb7373ea2be03cfc483027f34776e47b3d215975773e0b5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T00:05:34Z","title_canon_sha256":"24d41fc2b690dc545f72c7ad46fd339561f78a500cdb421eeb38af8921ef8d37"},"schema_version":"1.0","source":{"id":"1708.00107","kind":"arxiv","version":2}},"canonical_sha256":"1a857e95f0bdbe17d3514d28879b3dd69f9be913938b42aab1682a35b4f39040","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a857e95f0bdbe17d3514d28879b3dd69f9be913938b42aab1682a35b4f39040","first_computed_at":"2026-05-18T00:12:48.773865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:48.773865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D5JGjsBFU2DGY5r4caAul/ma4zP1ayKfnLzH50MbJj+ozRXXbBpOZT3krBp91HR4yZPIVcv9tuW2pf/Z+Q8WCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:48.774548Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.00107","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00137a431a52323140679266919fb2040609f721bb1b5e68ec1bd1067c381a35","sha256:57e6728f0d2b3f149c54ea42ceeac616ee6c0df03a9eac6b1dcaee2c5765dd12"],"state_sha256":"ddb99eb5b8a0bd591411d9e5b20525b8d463dc6bfc132bb5e0d7bb1824d44637"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"95lV1/pcrYG/+/W8uIOk71hzNgIxDpOcv3SFEDN60u0iluBm0wN7vh6tITujexjxH4ivehYXxsZDsQ/3O0h/Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:22:18.002587Z","bundle_sha256":"e80437f8e6ebcb0380d9db5ae6e8fed8215563cd59c2a6efff4c88ea52c35716"}}