{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:EK4MP5KTXENVHFBANFIXBLGRY3","short_pith_number":"pith:EK4MP5KT","canonical_record":{"source":{"id":"1905.07189","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-17T10:49:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d1e7a75f42333e217ecd40748bbf6c12bd099f2a2569cbbf80942df47ba7d938","abstract_canon_sha256":"118c4dc1464d93099c2c81f4f4247699fa6ab450cf8dd395b4465da5e2457383"},"schema_version":"1.0"},"canonical_sha256":"22b8c7f553b91b539420695170acd1c6c71812d4fadf285944041745a2a8c7e7","source":{"kind":"arxiv","id":"1905.07189","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07189","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07189v2","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07189","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"pith_short_12","alias_value":"EK4MP5KTXENV","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"EK4MP5KTXENVHFBA","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"EK4MP5KT","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:EK4MP5KTXENVHFBANFIXBLGRY3","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07189","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-17T10:49:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d1e7a75f42333e217ecd40748bbf6c12bd099f2a2569cbbf80942df47ba7d938","abstract_canon_sha256":"118c4dc1464d93099c2c81f4f4247699fa6ab450cf8dd395b4465da5e2457383"},"schema_version":"1.0"},"canonical_sha256":"22b8c7f553b91b539420695170acd1c6c71812d4fadf285944041745a2a8c7e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:18.577515Z","signature_b64":"DTOrgdrIfRc2sarg2KMRE/rFHV9TA/WJ+maMT2RVaCUdhiFpkZPHHwHMRYzCYyKOUfBZmqJ6HzKxxnHJLPrlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22b8c7f553b91b539420695170acd1c6c71812d4fadf285944041745a2a8c7e7","last_reissued_at":"2026-05-17T23:44:18.576832Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:18.576832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07189","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":"2026-05-17T23:44:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ped18YLFOZH7FGMX0sL404I8hiN/H9JdxOxtC2fUvqqY81mfoWlGM56kvD1TeiLbIcr43WNRGxk/Jjq97gFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:57:55.908718Z"},"content_sha256":"3dde88c29e62c4c9b1d65d0bd12195a69a2c9bd7ec257712fcc393ec79eca474","schema_version":"1.0","event_id":"sha256:3dde88c29e62c4c9b1d65d0bd12195a69a2c9bd7ec257712fcc393ec79eca474"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:EK4MP5KTXENVHFBANFIXBLGRY3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distant Learning for Entity Linking with Automatic Noise Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ivan Titov, Phong Le","submitted_at":"2019-05-17T10:49:47Z","abstract_excerpt":"Accurate entity linkers have been produced for domains and languages where annotated data (i.e., texts linked to a knowledge base) is available. However, little progress has been made for the settings where no or very limited amounts of labeled data are present (e.g., legal or most scientific domains). In this work, we show how we can learn to link mentions without having any labeled examples, only a knowledge base and a collection of unannotated texts from the corresponding domain. In order to achieve this, we frame the task as a multi-instance learning problem and rely on surface matching to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07189","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":"2026-05-17T23:44:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKn00CNKvdL+SopVyYtBYOOHdBnAAgVovv2h5FK+XNSdkdsu63iqZK7eSbH6InvigOb9jDkdPvZH7XqDVTmOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:57:55.909110Z"},"content_sha256":"b42264c1f58db918cafcbd967b48bee419bba7f3d052b4673b4193c1a81a52a5","schema_version":"1.0","event_id":"sha256:b42264c1f58db918cafcbd967b48bee419bba7f3d052b4673b4193c1a81a52a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EK4MP5KTXENVHFBANFIXBLGRY3/bundle.json","state_url":"https://pith.science/pith/EK4MP5KTXENVHFBANFIXBLGRY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EK4MP5KTXENVHFBANFIXBLGRY3/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":"2026-06-05T14:57:55Z","links":{"resolver":"https://pith.science/pith/EK4MP5KTXENVHFBANFIXBLGRY3","bundle":"https://pith.science/pith/EK4MP5KTXENVHFBANFIXBLGRY3/bundle.json","state":"https://pith.science/pith/EK4MP5KTXENVHFBANFIXBLGRY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EK4MP5KTXENVHFBANFIXBLGRY3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EK4MP5KTXENVHFBANFIXBLGRY3","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":"118c4dc1464d93099c2c81f4f4247699fa6ab450cf8dd395b4465da5e2457383","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-17T10:49:47Z","title_canon_sha256":"d1e7a75f42333e217ecd40748bbf6c12bd099f2a2569cbbf80942df47ba7d938"},"schema_version":"1.0","source":{"id":"1905.07189","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07189","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07189v2","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07189","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"pith_short_12","alias_value":"EK4MP5KTXENV","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"EK4MP5KTXENVHFBA","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"EK4MP5KT","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:b42264c1f58db918cafcbd967b48bee419bba7f3d052b4673b4193c1a81a52a5","target":"graph","created_at":"2026-05-17T23:44:18Z","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":"Accurate entity linkers have been produced for domains and languages where annotated data (i.e., texts linked to a knowledge base) is available. However, little progress has been made for the settings where no or very limited amounts of labeled data are present (e.g., legal or most scientific domains). In this work, we show how we can learn to link mentions without having any labeled examples, only a knowledge base and a collection of unannotated texts from the corresponding domain. In order to achieve this, we frame the task as a multi-instance learning problem and rely on surface matching to","authors_text":"Ivan Titov, Phong Le","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-17T10:49:47Z","title":"Distant Learning for Entity Linking with Automatic Noise Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07189","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":"sha256:3dde88c29e62c4c9b1d65d0bd12195a69a2c9bd7ec257712fcc393ec79eca474","target":"record","created_at":"2026-05-17T23:44:18Z","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":"118c4dc1464d93099c2c81f4f4247699fa6ab450cf8dd395b4465da5e2457383","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-17T10:49:47Z","title_canon_sha256":"d1e7a75f42333e217ecd40748bbf6c12bd099f2a2569cbbf80942df47ba7d938"},"schema_version":"1.0","source":{"id":"1905.07189","kind":"arxiv","version":2}},"canonical_sha256":"22b8c7f553b91b539420695170acd1c6c71812d4fadf285944041745a2a8c7e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22b8c7f553b91b539420695170acd1c6c71812d4fadf285944041745a2a8c7e7","first_computed_at":"2026-05-17T23:44:18.576832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:18.576832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DTOrgdrIfRc2sarg2KMRE/rFHV9TA/WJ+maMT2RVaCUdhiFpkZPHHwHMRYzCYyKOUfBZmqJ6HzKxxnHJLPrlAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:18.577515Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07189","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dde88c29e62c4c9b1d65d0bd12195a69a2c9bd7ec257712fcc393ec79eca474","sha256:b42264c1f58db918cafcbd967b48bee419bba7f3d052b4673b4193c1a81a52a5"],"state_sha256":"cc1e2f565dfa009b260f4a495a6acc169ed8ada410e78ab42df202a664948b86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W99e8MxTxPHmw38W660ek+0xu0TkBMm9BzvlKa7VAhEWTegNpQOXTrK4REhp1z044jEUrk4eME2QnFS/Z3uxCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T14:57:55.911222Z","bundle_sha256":"16ae14c6781eb2a50dee506771e42bca921c99e48677448861eff7ad7898e8fc"}}