{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:AMXHHB7FVY6IB7576TY4VCNRWD","short_pith_number":"pith:AMXHHB7F","canonical_record":{"source":{"id":"1903.10238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-25T11:00:20Z","cross_cats_sorted":[],"title_canon_sha256":"59f9f37627cd57940792f43e933dc8cdb39916e1da2f62e835e723006f19cd1e","abstract_canon_sha256":"2d22edd53a6c62a943a181e444a1620690cd3874be3d3349e784aa761984c61b"},"schema_version":"1.0"},"canonical_sha256":"032e7387e5ae3c80ffbff4f1ca89b1b0e53e65fef67ce8780425b034b3741508","source":{"kind":"arxiv","id":"1903.10238","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10238","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10238v1","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10238","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"pith_short_12","alias_value":"AMXHHB7FVY6I","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AMXHHB7FVY6IB757","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AMXHHB7F","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:AMXHHB7FVY6IB7576TY4VCNRWD","target":"record","payload":{"canonical_record":{"source":{"id":"1903.10238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-25T11:00:20Z","cross_cats_sorted":[],"title_canon_sha256":"59f9f37627cd57940792f43e933dc8cdb39916e1da2f62e835e723006f19cd1e","abstract_canon_sha256":"2d22edd53a6c62a943a181e444a1620690cd3874be3d3349e784aa761984c61b"},"schema_version":"1.0"},"canonical_sha256":"032e7387e5ae3c80ffbff4f1ca89b1b0e53e65fef67ce8780425b034b3741508","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:30.213568Z","signature_b64":"sUHWheeWdICPwfYWOjhrSi6264BBPr15VdDsMO7unDiqp/zWnBiib5tNd74aYSjuxyNtNdHRwjwSzUUnP8h2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"032e7387e5ae3c80ffbff4f1ca89b1b0e53e65fef67ce8780425b034b3741508","last_reissued_at":"2026-05-17T23:50:30.212967Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:30.212967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.10238","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":"2026-05-17T23:50:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7uflflKRtjKB4VO5Fl0CBneBairGZ+N/PFX8MTLT4XsZlt1QnMNXgu4zSnxTZOtajG9/p1QAGdtt1wOqyTcPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:33:45.250830Z"},"content_sha256":"ac5657b7803899256f953a97c65085afa6d9702664d4cb2c32c85522e0c7b917","schema_version":"1.0","event_id":"sha256:ac5657b7803899256f953a97c65085afa6d9702664d4cb2c32c85522e0c7b917"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:AMXHHB7FVY6IB7576TY4VCNRWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Vector-spaces with Noisy Supervised Lexicons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jacob Goldberger, Noa Yehezkel Lubin, Yoav Goldberg","submitted_at":"2019-03-25T11:00:20Z","abstract_excerpt":"The problem of learning to translate between two vector spaces given a set of aligned points arises in several application areas of NLP. Current solutions assume that the lexicon which defines the alignment pairs is noise-free. We consider the case where the set of aligned points is allowed to contain an amount of noise, in the form of incorrect lexicon pairs and show that this arises in practice by analyzing the edited dictionaries after the cleaning process. We demonstrate that such noise substantially degrades the accuracy of the learned translation when using current methods. We propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10238","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":"2026-05-17T23:50:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YJR6/zTJjCpJcUaZRLzs009Y7v+TEvwd9jKqV+LQKf1ZWhMswiyGtSeBcHkkAmwP6aV2cgKqKyAVpTICUu8SAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:33:45.251187Z"},"content_sha256":"b1ff9a4d4fdd4e230b1478c9fcd055f97929b7c64b6136a86a96fd8bcf8ba584","schema_version":"1.0","event_id":"sha256:b1ff9a4d4fdd4e230b1478c9fcd055f97929b7c64b6136a86a96fd8bcf8ba584"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMXHHB7FVY6IB7576TY4VCNRWD/bundle.json","state_url":"https://pith.science/pith/AMXHHB7FVY6IB7576TY4VCNRWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMXHHB7FVY6IB7576TY4VCNRWD/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":"2026-05-30T08:33:45Z","links":{"resolver":"https://pith.science/pith/AMXHHB7FVY6IB7576TY4VCNRWD","bundle":"https://pith.science/pith/AMXHHB7FVY6IB7576TY4VCNRWD/bundle.json","state":"https://pith.science/pith/AMXHHB7FVY6IB7576TY4VCNRWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMXHHB7FVY6IB7576TY4VCNRWD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AMXHHB7FVY6IB7576TY4VCNRWD","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":"2d22edd53a6c62a943a181e444a1620690cd3874be3d3349e784aa761984c61b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-25T11:00:20Z","title_canon_sha256":"59f9f37627cd57940792f43e933dc8cdb39916e1da2f62e835e723006f19cd1e"},"schema_version":"1.0","source":{"id":"1903.10238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10238","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10238v1","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10238","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"pith_short_12","alias_value":"AMXHHB7FVY6I","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AMXHHB7FVY6IB757","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AMXHHB7F","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:b1ff9a4d4fdd4e230b1478c9fcd055f97929b7c64b6136a86a96fd8bcf8ba584","target":"graph","created_at":"2026-05-17T23:50:30Z","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":"The problem of learning to translate between two vector spaces given a set of aligned points arises in several application areas of NLP. Current solutions assume that the lexicon which defines the alignment pairs is noise-free. We consider the case where the set of aligned points is allowed to contain an amount of noise, in the form of incorrect lexicon pairs and show that this arises in practice by analyzing the edited dictionaries after the cleaning process. We demonstrate that such noise substantially degrades the accuracy of the learned translation when using current methods. We propose a ","authors_text":"Jacob Goldberger, Noa Yehezkel Lubin, Yoav Goldberg","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-25T11:00:20Z","title":"Aligning Vector-spaces with Noisy Supervised Lexicons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10238","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:ac5657b7803899256f953a97c65085afa6d9702664d4cb2c32c85522e0c7b917","target":"record","created_at":"2026-05-17T23:50:30Z","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":"2d22edd53a6c62a943a181e444a1620690cd3874be3d3349e784aa761984c61b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-25T11:00:20Z","title_canon_sha256":"59f9f37627cd57940792f43e933dc8cdb39916e1da2f62e835e723006f19cd1e"},"schema_version":"1.0","source":{"id":"1903.10238","kind":"arxiv","version":1}},"canonical_sha256":"032e7387e5ae3c80ffbff4f1ca89b1b0e53e65fef67ce8780425b034b3741508","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"032e7387e5ae3c80ffbff4f1ca89b1b0e53e65fef67ce8780425b034b3741508","first_computed_at":"2026-05-17T23:50:30.212967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:30.212967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sUHWheeWdICPwfYWOjhrSi6264BBPr15VdDsMO7unDiqp/zWnBiib5tNd74aYSjuxyNtNdHRwjwSzUUnP8h2Cg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:30.213568Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.10238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac5657b7803899256f953a97c65085afa6d9702664d4cb2c32c85522e0c7b917","sha256:b1ff9a4d4fdd4e230b1478c9fcd055f97929b7c64b6136a86a96fd8bcf8ba584"],"state_sha256":"dba0c1ab446632fbb2b73d915a408cb27d0a6cb6d771d21a8f9052b06a749e8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBXpmllucVRCoeK0y/zD5MS+g3xKlbSbK5/UJ1uHU7zBXGbsUgeVcy6XUBafVQZdxZJY+ChJsdMCYfJq4J7LDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:33:45.253374Z","bundle_sha256":"8195e0106da514eb8cb92afd70223ba10d1b6ceb88ed98e2d44d4b69ea23d94c"}}