{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:P6QAA4SPCW6TPUTFIBJUWX2FI3","short_pith_number":"pith:P6QAA4SP","canonical_record":{"source":{"id":"1712.03376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-12-09T10:47:19Z","cross_cats_sorted":[],"title_canon_sha256":"5d5da8443b921ae110736fa315e0049af1f7427768cc09ea3a18ad08afd84eae","abstract_canon_sha256":"8ca0fc0b92677d108ddca848cd6b3ac816816ca1c6e951cd241e2b632cee9664"},"schema_version":"1.0"},"canonical_sha256":"7fa000724f15bd37d26540534b5f4546d57914cdfc336d3b9cc19d13b4b70361","source":{"kind":"arxiv","id":"1712.03376","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03376","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03376v2","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03376","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"pith_short_12","alias_value":"P6QAA4SPCW6T","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"P6QAA4SPCW6TPUTF","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"P6QAA4SP","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:P6QAA4SPCW6TPUTFIBJUWX2FI3","target":"record","payload":{"canonical_record":{"source":{"id":"1712.03376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-12-09T10:47:19Z","cross_cats_sorted":[],"title_canon_sha256":"5d5da8443b921ae110736fa315e0049af1f7427768cc09ea3a18ad08afd84eae","abstract_canon_sha256":"8ca0fc0b92677d108ddca848cd6b3ac816816ca1c6e951cd241e2b632cee9664"},"schema_version":"1.0"},"canonical_sha256":"7fa000724f15bd37d26540534b5f4546d57914cdfc336d3b9cc19d13b4b70361","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:51.895747Z","signature_b64":"Tc8qX0zWidntcqwj+QKH9KPY0T8tf0BrSO3y0LnFPI4FZGyJYprccrgdO8N2rW/TnPwRJpbMH6yheVHQHt33DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fa000724f15bd37d26540534b5f4546d57914cdfc336d3b9cc19d13b4b70361","last_reissued_at":"2026-05-18T00:27:51.895220Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:51.895220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.03376","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":"2026-05-18T00:27:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2rzmLLMM9vgRzEyfeocBVngs5pBqOgs8kFT3iHg1PKVF5Lcpeq3YgKZSixN/XZvcaDvXircp7RPMTXAjc5qlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T21:25:30.289036Z"},"content_sha256":"ceeb1d98ffb80645e3cc1ecf9b5f0ade689d73ad12585f09bc2f1690bbb5557e","schema_version":"1.0","event_id":"sha256:ceeb1d98ffb80645e3cc1ecf9b5f0ade689d73ad12585f09bc2f1690bbb5557e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:P6QAA4SPCW6TPUTFIBJUWX2FI3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Word Sense Disambiguation with LSTM: Do We Really Need 100 Billion Words?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jacopo Urbani, Marten Postma, Minh Le","submitted_at":"2017-12-09T10:47:19Z","abstract_excerpt":"Recently, Yuan et al. (2016) have shown the effectiveness of using Long Short-Term Memory (LSTM) for performing Word Sense Disambiguation (WSD). Their proposed technique outperformed the previous state-of-the-art with several benchmarks, but neither the training data nor the source code was released. This paper presents the results of a reproduction study of this technique using only openly available datasets (GigaWord, SemCore, OMSTI) and software (TensorFlow). From them, it emerged that state-of-the-art results can be obtained with much less data than hinted by Yuan et al. All code and train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03376","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":"2026-05-18T00:27:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hcIRHtNXLLQxcr84JS7BuZMfCRWESjz0r+BNEQ4isEOMs6JL0iQNwszUPze8czsjvY02ShP32BM8kWYCVgl8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T21:25:30.289395Z"},"content_sha256":"84401e2791c2859923ee61b2424b51fad07e0076548e7375da2efca52a6e5a4e","schema_version":"1.0","event_id":"sha256:84401e2791c2859923ee61b2424b51fad07e0076548e7375da2efca52a6e5a4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P6QAA4SPCW6TPUTFIBJUWX2FI3/bundle.json","state_url":"https://pith.science/pith/P6QAA4SPCW6TPUTFIBJUWX2FI3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P6QAA4SPCW6TPUTFIBJUWX2FI3/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":"2026-06-22T21:25:30Z","links":{"resolver":"https://pith.science/pith/P6QAA4SPCW6TPUTFIBJUWX2FI3","bundle":"https://pith.science/pith/P6QAA4SPCW6TPUTFIBJUWX2FI3/bundle.json","state":"https://pith.science/pith/P6QAA4SPCW6TPUTFIBJUWX2FI3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P6QAA4SPCW6TPUTFIBJUWX2FI3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:P6QAA4SPCW6TPUTFIBJUWX2FI3","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":"8ca0fc0b92677d108ddca848cd6b3ac816816ca1c6e951cd241e2b632cee9664","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-12-09T10:47:19Z","title_canon_sha256":"5d5da8443b921ae110736fa315e0049af1f7427768cc09ea3a18ad08afd84eae"},"schema_version":"1.0","source":{"id":"1712.03376","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03376","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03376v2","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03376","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"pith_short_12","alias_value":"P6QAA4SPCW6T","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"P6QAA4SPCW6TPUTF","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"P6QAA4SP","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:84401e2791c2859923ee61b2424b51fad07e0076548e7375da2efca52a6e5a4e","target":"graph","created_at":"2026-05-18T00:27:51Z","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":"Recently, Yuan et al. (2016) have shown the effectiveness of using Long Short-Term Memory (LSTM) for performing Word Sense Disambiguation (WSD). Their proposed technique outperformed the previous state-of-the-art with several benchmarks, but neither the training data nor the source code was released. This paper presents the results of a reproduction study of this technique using only openly available datasets (GigaWord, SemCore, OMSTI) and software (TensorFlow). From them, it emerged that state-of-the-art results can be obtained with much less data than hinted by Yuan et al. All code and train","authors_text":"Jacopo Urbani, Marten Postma, Minh Le","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-12-09T10:47:19Z","title":"Word Sense Disambiguation with LSTM: Do We Really Need 100 Billion Words?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03376","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:ceeb1d98ffb80645e3cc1ecf9b5f0ade689d73ad12585f09bc2f1690bbb5557e","target":"record","created_at":"2026-05-18T00:27:51Z","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":"8ca0fc0b92677d108ddca848cd6b3ac816816ca1c6e951cd241e2b632cee9664","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-12-09T10:47:19Z","title_canon_sha256":"5d5da8443b921ae110736fa315e0049af1f7427768cc09ea3a18ad08afd84eae"},"schema_version":"1.0","source":{"id":"1712.03376","kind":"arxiv","version":2}},"canonical_sha256":"7fa000724f15bd37d26540534b5f4546d57914cdfc336d3b9cc19d13b4b70361","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fa000724f15bd37d26540534b5f4546d57914cdfc336d3b9cc19d13b4b70361","first_computed_at":"2026-05-18T00:27:51.895220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:51.895220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tc8qX0zWidntcqwj+QKH9KPY0T8tf0BrSO3y0LnFPI4FZGyJYprccrgdO8N2rW/TnPwRJpbMH6yheVHQHt33DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:51.895747Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.03376","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ceeb1d98ffb80645e3cc1ecf9b5f0ade689d73ad12585f09bc2f1690bbb5557e","sha256:84401e2791c2859923ee61b2424b51fad07e0076548e7375da2efca52a6e5a4e"],"state_sha256":"4b3c76cb1aeb8b3353b3480ba0c2cad38b4e7d6889fdc1282e13ffceb132430e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dhA/XDtVsPTAxt2k6PDneW/uSxp8awhc5e/StUYW1tVrKwNttj5ycBCaJL8OghWE3fi7G8E+SWIWPmtMct0JAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T21:25:30.291409Z","bundle_sha256":"1bb037001ebe2c5dc74f68fd274170853ab43a5ebd32fccc9836e170aaaa1856"}}