{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EPXKZJYSQFCRC4Y4QNQWRZSSHX","short_pith_number":"pith:EPXKZJYS","canonical_record":{"source":{"id":"1805.04685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-12T08:25:33Z","cross_cats_sorted":[],"title_canon_sha256":"c25da2da3e638fb21a187dafc6e3227f7d4bbbbddf37c35fda7f29b283d9b11b","abstract_canon_sha256":"0a049923402d16d0b3c3a434ce7695a8609e3ddcc17180170bc68a789804e759"},"schema_version":"1.0"},"canonical_sha256":"23eeaca712814511731c836168e6523dcec27056d720f6b1b36535081b7f6c88","source":{"kind":"arxiv","id":"1805.04685","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.04685","created_at":"2026-05-18T00:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"1805.04685v1","created_at":"2026-05-18T00:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04685","created_at":"2026-05-18T00:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"EPXKZJYSQFCR","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EPXKZJYSQFCRC4Y4","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EPXKZJYS","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EPXKZJYSQFCRC4Y4QNQWRZSSHX","target":"record","payload":{"canonical_record":{"source":{"id":"1805.04685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-12T08:25:33Z","cross_cats_sorted":[],"title_canon_sha256":"c25da2da3e638fb21a187dafc6e3227f7d4bbbbddf37c35fda7f29b283d9b11b","abstract_canon_sha256":"0a049923402d16d0b3c3a434ce7695a8609e3ddcc17180170bc68a789804e759"},"schema_version":"1.0"},"canonical_sha256":"23eeaca712814511731c836168e6523dcec27056d720f6b1b36535081b7f6c88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:04.784399Z","signature_b64":"JsWrxwxiRp0PZC9jD4dsctL7cTlE0Itm/zkxb7q+xGG+ZXtE8A0xyYnra7BEK1mo4ZV3k/fsEkZ7vNC+5BwADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23eeaca712814511731c836168e6523dcec27056d720f6b1b36535081b7f6c88","last_reissued_at":"2026-05-18T00:16:04.783823Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:04.783823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.04685","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":"2026-05-18T00:16:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1+CnOFVpGt/7dNY01H2ENA463ClNU8NKXgWRh+01eWiHAAIsbs8rje/lGSKCD+UxhwyD8w/i/oFdbtdWc/6jCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:02:00.388370Z"},"content_sha256":"5c3cd4a479840e71f13210883950b96809b85aafe4023e5592246a0bb05d22ba","schema_version":"1.0","event_id":"sha256:5c3cd4a479840e71f13210883950b96809b85aafe4023e5592246a0bb05d22ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EPXKZJYSQFCRC4Y4QNQWRZSSHX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Huge Automatically Extracted Training Sets for Multilingual Word Sense Disambiguation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Francesco Maria Elia, Roberto Navigli, Tommaso Pasini","submitted_at":"2018-05-12T08:25:33Z","abstract_excerpt":"We release to the community six large-scale sense-annotated datasets in multiple language to pave the way for supervised multilingual Word Sense Disambiguation. Our datasets cover all the nouns in the English WordNet and their translations in other languages for a total of millions of sense-tagged sentences. Experiments prove that these corpora can be effectively used as training sets for supervised WSD systems, surpassing the state of the art for low-resourced languages and providing competitive results for English, where manually annotated training sets are accessible. The data is available "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04685","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":"2026-05-18T00:16:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUXRN77ddR2+eotIKirFnezMqGaCtYpaPiJnBLBxhwXuGqsAhFkKQ9S81L6NTFO97vHeB+PNy9RspMVWXzE6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:02:00.388748Z"},"content_sha256":"48eb2becc2bb392c5d56d98af67dacdcec5f14ef62a3f74d1c277cc199a8ff90","schema_version":"1.0","event_id":"sha256:48eb2becc2bb392c5d56d98af67dacdcec5f14ef62a3f74d1c277cc199a8ff90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPXKZJYSQFCRC4Y4QNQWRZSSHX/bundle.json","state_url":"https://pith.science/pith/EPXKZJYSQFCRC4Y4QNQWRZSSHX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPXKZJYSQFCRC4Y4QNQWRZSSHX/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":"2026-05-31T01:02:00Z","links":{"resolver":"https://pith.science/pith/EPXKZJYSQFCRC4Y4QNQWRZSSHX","bundle":"https://pith.science/pith/EPXKZJYSQFCRC4Y4QNQWRZSSHX/bundle.json","state":"https://pith.science/pith/EPXKZJYSQFCRC4Y4QNQWRZSSHX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPXKZJYSQFCRC4Y4QNQWRZSSHX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EPXKZJYSQFCRC4Y4QNQWRZSSHX","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":"0a049923402d16d0b3c3a434ce7695a8609e3ddcc17180170bc68a789804e759","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-12T08:25:33Z","title_canon_sha256":"c25da2da3e638fb21a187dafc6e3227f7d4bbbbddf37c35fda7f29b283d9b11b"},"schema_version":"1.0","source":{"id":"1805.04685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.04685","created_at":"2026-05-18T00:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"1805.04685v1","created_at":"2026-05-18T00:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04685","created_at":"2026-05-18T00:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"EPXKZJYSQFCR","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EPXKZJYSQFCRC4Y4","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EPXKZJYS","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:48eb2becc2bb392c5d56d98af67dacdcec5f14ef62a3f74d1c277cc199a8ff90","target":"graph","created_at":"2026-05-18T00:16:04Z","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 release to the community six large-scale sense-annotated datasets in multiple language to pave the way for supervised multilingual Word Sense Disambiguation. Our datasets cover all the nouns in the English WordNet and their translations in other languages for a total of millions of sense-tagged sentences. Experiments prove that these corpora can be effectively used as training sets for supervised WSD systems, surpassing the state of the art for low-resourced languages and providing competitive results for English, where manually annotated training sets are accessible. The data is available ","authors_text":"Francesco Maria Elia, Roberto Navigli, Tommaso Pasini","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-12T08:25:33Z","title":"Huge Automatically Extracted Training Sets for Multilingual Word Sense Disambiguation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04685","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":"sha256:5c3cd4a479840e71f13210883950b96809b85aafe4023e5592246a0bb05d22ba","target":"record","created_at":"2026-05-18T00:16:04Z","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":"0a049923402d16d0b3c3a434ce7695a8609e3ddcc17180170bc68a789804e759","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-12T08:25:33Z","title_canon_sha256":"c25da2da3e638fb21a187dafc6e3227f7d4bbbbddf37c35fda7f29b283d9b11b"},"schema_version":"1.0","source":{"id":"1805.04685","kind":"arxiv","version":1}},"canonical_sha256":"23eeaca712814511731c836168e6523dcec27056d720f6b1b36535081b7f6c88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23eeaca712814511731c836168e6523dcec27056d720f6b1b36535081b7f6c88","first_computed_at":"2026-05-18T00:16:04.783823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:04.783823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JsWrxwxiRp0PZC9jD4dsctL7cTlE0Itm/zkxb7q+xGG+ZXtE8A0xyYnra7BEK1mo4ZV3k/fsEkZ7vNC+5BwADQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:04.784399Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.04685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c3cd4a479840e71f13210883950b96809b85aafe4023e5592246a0bb05d22ba","sha256:48eb2becc2bb392c5d56d98af67dacdcec5f14ef62a3f74d1c277cc199a8ff90"],"state_sha256":"31f110295b5777be1b8302c422f9cc288fc70f5ccbef4987745b15698a67d43e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1nNZcfOOguk80i8cZFovjAJItsFdtzRT4MU7uLifAjPWFN4AI5IeKnS8qCgrIfVpAgc9V7vUZU36HKWU99OBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T01:02:00.390857Z","bundle_sha256":"f7c17d0665653ee6ad871dedb27aa383c8dfb3ee00dc597a7365ee78264d6459"}}