{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UZU25BQMGGPLQFJ2USVNXRD44F","short_pith_number":"pith:UZU25BQM","schema_version":"1.0","canonical_sha256":"a669ae860c319eb8153aa4aadbc47ce16dd67683f20185ab1643b51c670f618f","source":{"kind":"arxiv","id":"1905.10847","version":1},"attestation_state":"computed","paper":{"title":"Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Aston Zhang, Jie Fu, Jinfeng Rao, Luu Anh Tuan, Minh C. Phan, Shuohang Wang, Siu Cheung Hui, Xingdi Yuan, Yi Tay","submitted_at":"2019-05-26T17:56:11Z","abstract_excerpt":"This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty. This can be interpreted as a form of domain randomization and/or generative pretraining during training. To this end, the usage of the Pointer-Generator softens the requirement of having the answer within the context, enabling us to construct diverse"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.10847","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-26T17:56:11Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"10188b7a75faf4e818165fc6d4f1bdd4bac388597ca03ba9a28ca161d47ba486","abstract_canon_sha256":"cabfedea5c942e74992c36a70bcb74c5cd211d58029eef05d09f74ee44b5ee8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:03.600026Z","signature_b64":"Rjjl0Wa5gr2LGwmp1QmzQYqwzgh6ZmLgLE4IFWMUMDs7KzWL3700oeAHOf+hmK+AagGmGedHx9+3wLrFfTDKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a669ae860c319eb8153aa4aadbc47ce16dd67683f20185ab1643b51c670f618f","last_reissued_at":"2026-05-17T23:45:03.599602Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:03.599602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Aston Zhang, Jie Fu, Jinfeng Rao, Luu Anh Tuan, Minh C. Phan, Shuohang Wang, Siu Cheung Hui, Xingdi Yuan, Yi Tay","submitted_at":"2019-05-26T17:56:11Z","abstract_excerpt":"This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty. This can be interpreted as a form of domain randomization and/or generative pretraining during training. To this end, the usage of the Pointer-Generator softens the requirement of having the answer within the context, enabling us to construct diverse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10847","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.10847","created_at":"2026-05-17T23:45:03.599675+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10847v1","created_at":"2026-05-17T23:45:03.599675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10847","created_at":"2026-05-17T23:45:03.599675+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZU25BQMGGPL","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZU25BQMGGPLQFJ2","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZU25BQM","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00473","citing_title":"Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZU25BQMGGPLQFJ2USVNXRD44F","json":"https://pith.science/pith/UZU25BQMGGPLQFJ2USVNXRD44F.json","graph_json":"https://pith.science/api/pith-number/UZU25BQMGGPLQFJ2USVNXRD44F/graph.json","events_json":"https://pith.science/api/pith-number/UZU25BQMGGPLQFJ2USVNXRD44F/events.json","paper":"https://pith.science/paper/UZU25BQM"},"agent_actions":{"view_html":"https://pith.science/pith/UZU25BQMGGPLQFJ2USVNXRD44F","download_json":"https://pith.science/pith/UZU25BQMGGPLQFJ2USVNXRD44F.json","view_paper":"https://pith.science/paper/UZU25BQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10847&json=true","fetch_graph":"https://pith.science/api/pith-number/UZU25BQMGGPLQFJ2USVNXRD44F/graph.json","fetch_events":"https://pith.science/api/pith-number/UZU25BQMGGPLQFJ2USVNXRD44F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZU25BQMGGPLQFJ2USVNXRD44F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZU25BQMGGPLQFJ2USVNXRD44F/action/storage_attestation","attest_author":"https://pith.science/pith/UZU25BQMGGPLQFJ2USVNXRD44F/action/author_attestation","sign_citation":"https://pith.science/pith/UZU25BQMGGPLQFJ2USVNXRD44F/action/citation_signature","submit_replication":"https://pith.science/pith/UZU25BQMGGPLQFJ2USVNXRD44F/action/replication_record"}},"created_at":"2026-05-17T23:45:03.599675+00:00","updated_at":"2026-05-17T23:45:03.599675+00:00"}