{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2H5NTINPQR6M5CY3DQU3Z6BZAU","short_pith_number":"pith:2H5NTINP","canonical_record":{"source":{"id":"1810.09807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-23T12:09:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"47ebe4a271e25b516b810ad97fe5d9a59f6197eb75197e33a24fdf97f3da5a74","abstract_canon_sha256":"86b297dcb7761ffc3123998d83be8fd0a1fedb9bb673a62c40b66ca15b40939b"},"schema_version":"1.0"},"canonical_sha256":"d1fad9a1af847cce8b1b1c29bcf83905296e8b7852b20df955626fa49c07f238","source":{"kind":"arxiv","id":"1810.09807","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.09807","created_at":"2026-05-18T00:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"1810.09807v1","created_at":"2026-05-18T00:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09807","created_at":"2026-05-18T00:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"2H5NTINPQR6M","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2H5NTINPQR6M5CY3","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2H5NTINP","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2H5NTINPQR6M5CY3DQU3Z6BZAU","target":"record","payload":{"canonical_record":{"source":{"id":"1810.09807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-23T12:09:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"47ebe4a271e25b516b810ad97fe5d9a59f6197eb75197e33a24fdf97f3da5a74","abstract_canon_sha256":"86b297dcb7761ffc3123998d83be8fd0a1fedb9bb673a62c40b66ca15b40939b"},"schema_version":"1.0"},"canonical_sha256":"d1fad9a1af847cce8b1b1c29bcf83905296e8b7852b20df955626fa49c07f238","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:29.346441Z","signature_b64":"BoAiXx+vWfYMvS2vxXLoa/aDlTpKXEaoJLVlMHPcBzqcPvvmcRsCWAzEhKdHz7NrezrSUvaJtwy1wOrvQOISAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1fad9a1af847cce8b1b1c29bcf83905296e8b7852b20df955626fa49c07f238","last_reissued_at":"2026-05-18T00:02:29.345687Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:29.345687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.09807","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":"2026-05-18T00:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uM8vSm8cUSeiDRe7KNgKjcikY2doDRymXrOnbYbGQuzuPNHlD/GGzViHqbf3RwOnV/Ut4R4Gbx03NxdKnxwBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T09:25:52.656626Z"},"content_sha256":"63ccc4be0fad49ef33a572c6bb4f5e6035ca5c8a764e8b3cbed478570d61602f","schema_version":"1.0","event_id":"sha256:63ccc4be0fad49ef33a572c6bb4f5e6035ca5c8a764e8b3cbed478570d61602f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2H5NTINPQR6M5CY3DQU3Z6BZAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PreCo: A Large-scale Dataset in Preschool Vocabulary for Coreference Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan L. Yuille, Hao Lu, Hong Chen, Shu Rong, Zhenhua Fan","submitted_at":"2018-10-23T12:09:37Z","abstract_excerpt":"We introduce PreCo, a large-scale English dataset for coreference resolution. The dataset is designed to embody the core challenges in coreference, such as entity representation, by alleviating the challenge of low overlap between training and test sets and enabling separated analysis of mention detection and mention clustering. To strengthen the training-test overlap, we collect a large corpus of about 38K documents and 12.4M words which are mostly from the vocabulary of English-speaking preschoolers. Experiments show that with higher training-test overlap, error analysis on PreCo is more eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09807","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":"2026-05-18T00:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DvtpqOyplB4adbkbWGtyOAqQPuISeiFdhQt+gfB6h1FVKTxJ1fy9EPyY1A+wokdDdAZ4AkcPO8bwGz6VuEX1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T09:25:52.657253Z"},"content_sha256":"2739b2437f740829ef36766e4de514a2e2eefaa0746bdd440a6dc09f9d9800e2","schema_version":"1.0","event_id":"sha256:2739b2437f740829ef36766e4de514a2e2eefaa0746bdd440a6dc09f9d9800e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2H5NTINPQR6M5CY3DQU3Z6BZAU/bundle.json","state_url":"https://pith.science/pith/2H5NTINPQR6M5CY3DQU3Z6BZAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2H5NTINPQR6M5CY3DQU3Z6BZAU/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":"2026-06-07T09:25:52Z","links":{"resolver":"https://pith.science/pith/2H5NTINPQR6M5CY3DQU3Z6BZAU","bundle":"https://pith.science/pith/2H5NTINPQR6M5CY3DQU3Z6BZAU/bundle.json","state":"https://pith.science/pith/2H5NTINPQR6M5CY3DQU3Z6BZAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2H5NTINPQR6M5CY3DQU3Z6BZAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2H5NTINPQR6M5CY3DQU3Z6BZAU","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":"86b297dcb7761ffc3123998d83be8fd0a1fedb9bb673a62c40b66ca15b40939b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-23T12:09:37Z","title_canon_sha256":"47ebe4a271e25b516b810ad97fe5d9a59f6197eb75197e33a24fdf97f3da5a74"},"schema_version":"1.0","source":{"id":"1810.09807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.09807","created_at":"2026-05-18T00:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"1810.09807v1","created_at":"2026-05-18T00:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09807","created_at":"2026-05-18T00:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"2H5NTINPQR6M","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2H5NTINPQR6M5CY3","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2H5NTINP","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:2739b2437f740829ef36766e4de514a2e2eefaa0746bdd440a6dc09f9d9800e2","target":"graph","created_at":"2026-05-18T00:02:29Z","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 introduce PreCo, a large-scale English dataset for coreference resolution. The dataset is designed to embody the core challenges in coreference, such as entity representation, by alleviating the challenge of low overlap between training and test sets and enabling separated analysis of mention detection and mention clustering. To strengthen the training-test overlap, we collect a large corpus of about 38K documents and 12.4M words which are mostly from the vocabulary of English-speaking preschoolers. Experiments show that with higher training-test overlap, error analysis on PreCo is more eff","authors_text":"Alan L. Yuille, Hao Lu, Hong Chen, Shu Rong, Zhenhua Fan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-23T12:09:37Z","title":"PreCo: A Large-scale Dataset in Preschool Vocabulary for Coreference Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09807","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":"sha256:63ccc4be0fad49ef33a572c6bb4f5e6035ca5c8a764e8b3cbed478570d61602f","target":"record","created_at":"2026-05-18T00:02:29Z","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":"86b297dcb7761ffc3123998d83be8fd0a1fedb9bb673a62c40b66ca15b40939b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-23T12:09:37Z","title_canon_sha256":"47ebe4a271e25b516b810ad97fe5d9a59f6197eb75197e33a24fdf97f3da5a74"},"schema_version":"1.0","source":{"id":"1810.09807","kind":"arxiv","version":1}},"canonical_sha256":"d1fad9a1af847cce8b1b1c29bcf83905296e8b7852b20df955626fa49c07f238","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1fad9a1af847cce8b1b1c29bcf83905296e8b7852b20df955626fa49c07f238","first_computed_at":"2026-05-18T00:02:29.345687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:29.345687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BoAiXx+vWfYMvS2vxXLoa/aDlTpKXEaoJLVlMHPcBzqcPvvmcRsCWAzEhKdHz7NrezrSUvaJtwy1wOrvQOISAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:29.346441Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.09807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63ccc4be0fad49ef33a572c6bb4f5e6035ca5c8a764e8b3cbed478570d61602f","sha256:2739b2437f740829ef36766e4de514a2e2eefaa0746bdd440a6dc09f9d9800e2"],"state_sha256":"7ecfa99be36c0dea91c40bc460b179f48213c86f94bb88d43f2fe30ed385cf87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6OndEHNCVZYBN4rwcuqTAk+TCvtAOPhqCNY9E7nCZm+XptQ+7E5c5nnflKwB7odfXk1cpyBxs36pSHhYlUT+CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T09:25:52.660403Z","bundle_sha256":"81a8e80eadc7b949e79fe91f12ef35e948e21b1ff853d04203d1eb43a4618651"}}