{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LMV4RQNPZ7TORA2CT4OOJCKJEL","short_pith_number":"pith:LMV4RQNP","canonical_record":{"source":{"id":"1906.01250","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T07:49:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9c53afa478f74203c2e0b356ffb7334b9fdc88a86acb54128f7be46bd4262ea1","abstract_canon_sha256":"5469aab2af879c4e9e8a08d2aaa075bae867698eb04a881c36e6fdb0ab8af36c"},"schema_version":"1.0"},"canonical_sha256":"5b2bc8c1afcfe6e883429f1ce4894922e1dd809354c5e5f0e24adf00e8078941","source":{"kind":"arxiv","id":"1906.01250","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01250","created_at":"2026-05-17T23:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01250v1","created_at":"2026-05-17T23:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01250","created_at":"2026-05-17T23:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"LMV4RQNPZ7TO","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LMV4RQNPZ7TORA2C","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LMV4RQNP","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LMV4RQNPZ7TORA2CT4OOJCKJEL","target":"record","payload":{"canonical_record":{"source":{"id":"1906.01250","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T07:49:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9c53afa478f74203c2e0b356ffb7334b9fdc88a86acb54128f7be46bd4262ea1","abstract_canon_sha256":"5469aab2af879c4e9e8a08d2aaa075bae867698eb04a881c36e6fdb0ab8af36c"},"schema_version":"1.0"},"canonical_sha256":"5b2bc8c1afcfe6e883429f1ce4894922e1dd809354c5e5f0e24adf00e8078941","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:17.340459Z","signature_b64":"8TxauihxE5RQz89jFbOBos5pCyJQa1H5l2YhMeULaJUve0viO/W1wkEZXcv+FhDLiqqf5KGB+FxAiHQPryrQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b2bc8c1afcfe6e883429f1ce4894922e1dd809354c5e5f0e24adf00e8078941","last_reissued_at":"2026-05-17T23:44:17.339843Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:17.339843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.01250","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":"2026-05-17T23:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7FGOnHdlhhIva+PGwLOCj6/WrS9XcbKiovyh4zuETO57nVT60qbiyR/4fhLSUSis2GBjEpup9qP7YYmOVRgXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:18:59.081129Z"},"content_sha256":"d98459a3266da58cd1af0b6d95fecbe5c875a00f13b27982f2679ad0b308ec80","schema_version":"1.0","event_id":"sha256:d98459a3266da58cd1af0b6d95fecbe5c875a00f13b27982f2679ad0b308ec80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LMV4RQNPZ7TORA2CT4OOJCKJEL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Entity Linking Performance by Leveraging Unlabeled Documents","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":"2019-06-04T07:49:46Z","abstract_excerpt":"Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and Wikipedia. Our approach consists of two stages. First, we construct a high recall list of candidate entities for each mention in an unlabeled document. Second, we use the candidate lists as weak supervision to constrain our document-level entity linking model. The model treats entities as latent variables and, when estimated on a collection of unlabelled texts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01250","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":"2026-05-17T23:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bxkg2t0U9ucgzHvWmDP43ESKK14VXIMEWH/h13EA1MamB/ZwOZCw+OWKFZdlq+2w6r/jzL7hkzFLJWveBGW0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:18:59.081497Z"},"content_sha256":"186694a0e09315999ce3e76d182cd6c616c71f83f5382692924c75238c0aa97f","schema_version":"1.0","event_id":"sha256:186694a0e09315999ce3e76d182cd6c616c71f83f5382692924c75238c0aa97f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/bundle.json","state_url":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/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":"2026-06-05T16:18:59Z","links":{"resolver":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL","bundle":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/bundle.json","state":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LMV4RQNPZ7TORA2CT4OOJCKJEL","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":"5469aab2af879c4e9e8a08d2aaa075bae867698eb04a881c36e6fdb0ab8af36c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T07:49:46Z","title_canon_sha256":"9c53afa478f74203c2e0b356ffb7334b9fdc88a86acb54128f7be46bd4262ea1"},"schema_version":"1.0","source":{"id":"1906.01250","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01250","created_at":"2026-05-17T23:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01250v1","created_at":"2026-05-17T23:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01250","created_at":"2026-05-17T23:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"LMV4RQNPZ7TO","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LMV4RQNPZ7TORA2C","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LMV4RQNP","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:186694a0e09315999ce3e76d182cd6c616c71f83f5382692924c75238c0aa97f","target":"graph","created_at":"2026-05-17T23:44:17Z","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":"Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and Wikipedia. Our approach consists of two stages. First, we construct a high recall list of candidate entities for each mention in an unlabeled document. Second, we use the candidate lists as weak supervision to constrain our document-level entity linking model. The model treats entities as latent variables and, when estimated on a collection of unlabelled texts","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":"2019-06-04T07:49:46Z","title":"Boosting Entity Linking Performance by Leveraging Unlabeled Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01250","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:d98459a3266da58cd1af0b6d95fecbe5c875a00f13b27982f2679ad0b308ec80","target":"record","created_at":"2026-05-17T23:44:17Z","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":"5469aab2af879c4e9e8a08d2aaa075bae867698eb04a881c36e6fdb0ab8af36c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T07:49:46Z","title_canon_sha256":"9c53afa478f74203c2e0b356ffb7334b9fdc88a86acb54128f7be46bd4262ea1"},"schema_version":"1.0","source":{"id":"1906.01250","kind":"arxiv","version":1}},"canonical_sha256":"5b2bc8c1afcfe6e883429f1ce4894922e1dd809354c5e5f0e24adf00e8078941","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b2bc8c1afcfe6e883429f1ce4894922e1dd809354c5e5f0e24adf00e8078941","first_computed_at":"2026-05-17T23:44:17.339843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:17.339843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8TxauihxE5RQz89jFbOBos5pCyJQa1H5l2YhMeULaJUve0viO/W1wkEZXcv+FhDLiqqf5KGB+FxAiHQPryrQAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:17.340459Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.01250","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d98459a3266da58cd1af0b6d95fecbe5c875a00f13b27982f2679ad0b308ec80","sha256:186694a0e09315999ce3e76d182cd6c616c71f83f5382692924c75238c0aa97f"],"state_sha256":"0bafe1c6ef40f58fd53fb5027c8a908bded28abc114223563cb352ee25faaec1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Lz2dTzXSUpC3zQYKu9oCdwxXqYUIkCT/Y1xI2kQxxrf4WvUiTpUFrLYAAjd9v864h16L0x5n29Xo/L7sejyAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T16:18:59.083599Z","bundle_sha256":"88ea755bcf07642021b9453fbc7604cf32e88300013a529cb22d32bf0b81c4bc"}}