{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AVYSWHRZB5ILWHVVR72WXIZZRN","short_pith_number":"pith:AVYSWHRZ","canonical_record":{"source":{"id":"1707.06841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T11:06:12Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"4605765287c677fddc6724bb1f15bf498b52f2ce7b8f4f2ff3e4e6ae0930ab72","abstract_canon_sha256":"f08bbd2b4251db286a1a91fb3268de124b7545f02af2f16c3a9623edbf9342f1"},"schema_version":"1.0"},"canonical_sha256":"05712b1e390f50bb1eb58ff56ba3398b5abc5dca918658920f58ca41a23ff1c6","source":{"kind":"arxiv","id":"1707.06841","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06841","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06841v1","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06841","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"pith_short_12","alias_value":"AVYSWHRZB5IL","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"AVYSWHRZB5ILWHVV","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"AVYSWHRZ","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AVYSWHRZB5ILWHVVR72WXIZZRN","target":"record","payload":{"canonical_record":{"source":{"id":"1707.06841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T11:06:12Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"4605765287c677fddc6724bb1f15bf498b52f2ce7b8f4f2ff3e4e6ae0930ab72","abstract_canon_sha256":"f08bbd2b4251db286a1a91fb3268de124b7545f02af2f16c3a9623edbf9342f1"},"schema_version":"1.0"},"canonical_sha256":"05712b1e390f50bb1eb58ff56ba3398b5abc5dca918658920f58ca41a23ff1c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:31.418948Z","signature_b64":"PWCUttAgrQogHQR8arCmIUpyVdJS+VXmTUgTLS5QMqqaqsKhLvAmFaoNVTPnxmrV9swHzYH68ZjA+trPPvC3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05712b1e390f50bb1eb58ff56ba3398b5abc5dca918658920f58ca41a23ff1c6","last_reissued_at":"2026-05-17T23:41:31.418277Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:31.418277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.06841","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":"2026-05-17T23:41:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bS/7CGajo1KSfCCJmx9GC2h5GO++WxmtP1UPJ8MCTu0MbKX/bloRU53qiTl0gwVIPQYyvVwSX3nR0HK3VNqrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:13:44.660410Z"},"content_sha256":"89748ecadc4e9256833fa4ee88d79faee820f3c0c3c7243a25d64dd8b726a87b","schema_version":"1.0","event_id":"sha256:89748ecadc4e9256833fa4ee88d79faee820f3c0c3c7243a25d64dd8b726a87b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AVYSWHRZB5ILWHVVR72WXIZZRN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Error-Oriented Approach to Word Embedding Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Marek Rei, Ted Briscoe, Youmna Farag","submitted_at":"2017-07-21T11:06:12Z","abstract_excerpt":"We propose a novel word embedding pre-training approach that exploits writing errors in learners' scripts. We compare our method to previous models that tune the embeddings based on script scores and the discrimination between correct and corrupt word contexts in addition to the generic commonly-used embeddings pre-trained on large corpora. The comparison is achieved by using the aforementioned models to bootstrap a neural network that learns to predict a holistic score for scripts. Furthermore, we investigate augmenting our model with error corrections and monitor the impact on performance. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06841","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":"2026-05-17T23:41:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Ys72LY3d3Il4vBPfhvWoM4ik0MgOVlxGwfO8Pc/Iu5FUdMaD4hFNr/04PfQOdO6JNQ3+OjhjirYMQnIJlGXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:13:44.660828Z"},"content_sha256":"99cb8a9353355d8a28dbb2b10c6df67c83b23f1ee57b3c84561727976b12c0e0","schema_version":"1.0","event_id":"sha256:99cb8a9353355d8a28dbb2b10c6df67c83b23f1ee57b3c84561727976b12c0e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AVYSWHRZB5ILWHVVR72WXIZZRN/bundle.json","state_url":"https://pith.science/pith/AVYSWHRZB5ILWHVVR72WXIZZRN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AVYSWHRZB5ILWHVVR72WXIZZRN/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":"2026-05-26T06:13:44Z","links":{"resolver":"https://pith.science/pith/AVYSWHRZB5ILWHVVR72WXIZZRN","bundle":"https://pith.science/pith/AVYSWHRZB5ILWHVVR72WXIZZRN/bundle.json","state":"https://pith.science/pith/AVYSWHRZB5ILWHVVR72WXIZZRN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AVYSWHRZB5ILWHVVR72WXIZZRN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AVYSWHRZB5ILWHVVR72WXIZZRN","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":"f08bbd2b4251db286a1a91fb3268de124b7545f02af2f16c3a9623edbf9342f1","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T11:06:12Z","title_canon_sha256":"4605765287c677fddc6724bb1f15bf498b52f2ce7b8f4f2ff3e4e6ae0930ab72"},"schema_version":"1.0","source":{"id":"1707.06841","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06841","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06841v1","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06841","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"pith_short_12","alias_value":"AVYSWHRZB5IL","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"AVYSWHRZB5ILWHVV","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"AVYSWHRZ","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:99cb8a9353355d8a28dbb2b10c6df67c83b23f1ee57b3c84561727976b12c0e0","target":"graph","created_at":"2026-05-17T23:41:31Z","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":"We propose a novel word embedding pre-training approach that exploits writing errors in learners' scripts. We compare our method to previous models that tune the embeddings based on script scores and the discrimination between correct and corrupt word contexts in addition to the generic commonly-used embeddings pre-trained on large corpora. The comparison is achieved by using the aforementioned models to bootstrap a neural network that learns to predict a holistic score for scripts. Furthermore, we investigate augmenting our model with error corrections and monitor the impact on performance. O","authors_text":"Marek Rei, Ted Briscoe, Youmna Farag","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T11:06:12Z","title":"An Error-Oriented Approach to Word Embedding Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06841","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":"sha256:89748ecadc4e9256833fa4ee88d79faee820f3c0c3c7243a25d64dd8b726a87b","target":"record","created_at":"2026-05-17T23:41:31Z","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":"f08bbd2b4251db286a1a91fb3268de124b7545f02af2f16c3a9623edbf9342f1","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T11:06:12Z","title_canon_sha256":"4605765287c677fddc6724bb1f15bf498b52f2ce7b8f4f2ff3e4e6ae0930ab72"},"schema_version":"1.0","source":{"id":"1707.06841","kind":"arxiv","version":1}},"canonical_sha256":"05712b1e390f50bb1eb58ff56ba3398b5abc5dca918658920f58ca41a23ff1c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05712b1e390f50bb1eb58ff56ba3398b5abc5dca918658920f58ca41a23ff1c6","first_computed_at":"2026-05-17T23:41:31.418277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:31.418277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PWCUttAgrQogHQR8arCmIUpyVdJS+VXmTUgTLS5QMqqaqsKhLvAmFaoNVTPnxmrV9swHzYH68ZjA+trPPvC3CQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:31.418948Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.06841","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89748ecadc4e9256833fa4ee88d79faee820f3c0c3c7243a25d64dd8b726a87b","sha256:99cb8a9353355d8a28dbb2b10c6df67c83b23f1ee57b3c84561727976b12c0e0"],"state_sha256":"65a1d761f8cda14b7184621423a622d99e95c9fffa86533b26a2cd42eae71af6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9WsgogqclOh8f3NKptEr1vjC9sBJUv0yOj/LEwUJLDlv6oEMhdGmjquJS8BrG0Sx+GFuNnj4jyyXUZ714yZhBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:13:44.663839Z","bundle_sha256":"baed00e9d029b3a667f4d139da487d2b67fcdf72b59176d5d2abbae938aa064a"}}