{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TPZETSDOUH3K6IYDXBXL4SMTEB","short_pith_number":"pith:TPZETSDO","schema_version":"1.0","canonical_sha256":"9bf249c86ea1f6af2303b86ebe4993205c17787d9d1772392e6740cf06a02e47","source":{"kind":"arxiv","id":"1805.00178","version":3},"attestation_state":"computed","paper":{"title":"Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eiichiro Sumita, Masao Utiyama, Rui Wang","submitted_at":"2018-05-01T04:09:09Z","abstract_excerpt":"Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch. In reality, some sentences are well-learned during the initial few epochs; however, using this approach, the well-learned sentences would continue to be trained along with those sentences that were not well learned for 10-30 epochs, which results in a wastage of time. Here, we propose an efficient method to dynamically sample the sentences in order to accelerate the NMT training. In this approach, a weight is assigned to each sentence based on the measured dif"},"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":"1805.00178","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-01T04:09:09Z","cross_cats_sorted":[],"title_canon_sha256":"dbd8db77cfca005a8878f217ae04a3c8c9f3f9866481ab64b56a84ccdbcb91ca","abstract_canon_sha256":"bed7314d3fce45fdbe670f55993e3beef93db1400519ef81145ab090788431b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:09:23.284406Z","signature_b64":"cXoxWeBt//tP+3kADV+KP8AJvplaOA32ZMUONf5EbXWDewQbWXN/Hmqt/VDuw/ZT/HDFshYcwv3QXZ/FH8qhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bf249c86ea1f6af2303b86ebe4993205c17787d9d1772392e6740cf06a02e47","last_reissued_at":"2026-07-05T00:09:23.283745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:09:23.283745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eiichiro Sumita, Masao Utiyama, Rui Wang","submitted_at":"2018-05-01T04:09:09Z","abstract_excerpt":"Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch. In reality, some sentences are well-learned during the initial few epochs; however, using this approach, the well-learned sentences would continue to be trained along with those sentences that were not well learned for 10-30 epochs, which results in a wastage of time. Here, we propose an efficient method to dynamically sample the sentences in order to accelerate the NMT training. In this approach, a weight is assigned to each sentence based on the measured dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00178","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1805.00178/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1805.00178","created_at":"2026-07-05T00:09:23.283806+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.00178v3","created_at":"2026-07-05T00:09:23.283806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00178","created_at":"2026-07-05T00:09:23.283806+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPZETSDOUH3K","created_at":"2026-07-05T00:09:23.283806+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPZETSDOUH3K6IYD","created_at":"2026-07-05T00:09:23.283806+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPZETSDO","created_at":"2026-07-05T00:09:23.283806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18434","citing_title":"TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPZETSDOUH3K6IYDXBXL4SMTEB","json":"https://pith.science/pith/TPZETSDOUH3K6IYDXBXL4SMTEB.json","graph_json":"https://pith.science/api/pith-number/TPZETSDOUH3K6IYDXBXL4SMTEB/graph.json","events_json":"https://pith.science/api/pith-number/TPZETSDOUH3K6IYDXBXL4SMTEB/events.json","paper":"https://pith.science/paper/TPZETSDO"},"agent_actions":{"view_html":"https://pith.science/pith/TPZETSDOUH3K6IYDXBXL4SMTEB","download_json":"https://pith.science/pith/TPZETSDOUH3K6IYDXBXL4SMTEB.json","view_paper":"https://pith.science/paper/TPZETSDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.00178&json=true","fetch_graph":"https://pith.science/api/pith-number/TPZETSDOUH3K6IYDXBXL4SMTEB/graph.json","fetch_events":"https://pith.science/api/pith-number/TPZETSDOUH3K6IYDXBXL4SMTEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPZETSDOUH3K6IYDXBXL4SMTEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPZETSDOUH3K6IYDXBXL4SMTEB/action/storage_attestation","attest_author":"https://pith.science/pith/TPZETSDOUH3K6IYDXBXL4SMTEB/action/author_attestation","sign_citation":"https://pith.science/pith/TPZETSDOUH3K6IYDXBXL4SMTEB/action/citation_signature","submit_replication":"https://pith.science/pith/TPZETSDOUH3K6IYDXBXL4SMTEB/action/replication_record"}},"created_at":"2026-07-05T00:09:23.283806+00:00","updated_at":"2026-07-05T00:09:23.283806+00:00"}