{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CFI4MSSCSTZVMSNNQBW7AHAQPG","short_pith_number":"pith:CFI4MSSC","schema_version":"1.0","canonical_sha256":"1151c64a4294f35649ad806df01c1079a048c695189510873da4eb6da5d53049","source":{"kind":"arxiv","id":"2107.10427","version":1},"attestation_state":"computed","paper":{"title":"Confidence-Aware Scheduled Sampling for Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Jie Zhou, Jinan Xu, Yijin Liu, Yufeng Chen","submitted_at":"2021-07-22T02:49:04Z","abstract_excerpt":"Scheduled sampling is an effective method to alleviate the exposure bias problem of neural machine translation. It simulates the inference scene by randomly replacing ground-truth target input tokens with predicted ones during training. Despite its success, its critical schedule strategies are merely based on training steps, ignoring the real-time model competence, which limits its potential performance and convergence speed. To address this issue, we propose confidence-aware scheduled sampling. Specifically, we quantify real-time model competence by the confidence of model predictions, based "},"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":"2107.10427","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-22T02:49:04Z","cross_cats_sorted":[],"title_canon_sha256":"25a6bf7d3c606565098262deffbfa842cc4c04fb7d83121c6602bc7cffa8e880","abstract_canon_sha256":"3dc12a330df368b03d9b86d00fc1c174d9de02e1104266165128cc0f9d6aebb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:59.894851Z","signature_b64":"T4bDnpmYjlhfgGE6Chs6ffA8bH0c7D5SzEW0AVmIclX9BPGo1c2/FMsEjQ/L600d3cic+ssqvDVdbHxVApB1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1151c64a4294f35649ad806df01c1079a048c695189510873da4eb6da5d53049","last_reissued_at":"2026-07-05T02:59:59.894461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:59.894461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence-Aware Scheduled Sampling for Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Jie Zhou, Jinan Xu, Yijin Liu, Yufeng Chen","submitted_at":"2021-07-22T02:49:04Z","abstract_excerpt":"Scheduled sampling is an effective method to alleviate the exposure bias problem of neural machine translation. It simulates the inference scene by randomly replacing ground-truth target input tokens with predicted ones during training. Despite its success, its critical schedule strategies are merely based on training steps, ignoring the real-time model competence, which limits its potential performance and convergence speed. To address this issue, we propose confidence-aware scheduled sampling. Specifically, we quantify real-time model competence by the confidence of model predictions, based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10427","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.10427/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":"2107.10427","created_at":"2026-07-05T02:59:59.894532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10427v1","created_at":"2026-07-05T02:59:59.894532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10427","created_at":"2026-07-05T02:59:59.894532+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFI4MSSCSTZV","created_at":"2026-07-05T02:59:59.894532+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFI4MSSCSTZVMSNN","created_at":"2026-07-05T02:59:59.894532+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFI4MSSC","created_at":"2026-07-05T02:59:59.894532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFI4MSSCSTZVMSNNQBW7AHAQPG","json":"https://pith.science/pith/CFI4MSSCSTZVMSNNQBW7AHAQPG.json","graph_json":"https://pith.science/api/pith-number/CFI4MSSCSTZVMSNNQBW7AHAQPG/graph.json","events_json":"https://pith.science/api/pith-number/CFI4MSSCSTZVMSNNQBW7AHAQPG/events.json","paper":"https://pith.science/paper/CFI4MSSC"},"agent_actions":{"view_html":"https://pith.science/pith/CFI4MSSCSTZVMSNNQBW7AHAQPG","download_json":"https://pith.science/pith/CFI4MSSCSTZVMSNNQBW7AHAQPG.json","view_paper":"https://pith.science/paper/CFI4MSSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10427&json=true","fetch_graph":"https://pith.science/api/pith-number/CFI4MSSCSTZVMSNNQBW7AHAQPG/graph.json","fetch_events":"https://pith.science/api/pith-number/CFI4MSSCSTZVMSNNQBW7AHAQPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFI4MSSCSTZVMSNNQBW7AHAQPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFI4MSSCSTZVMSNNQBW7AHAQPG/action/storage_attestation","attest_author":"https://pith.science/pith/CFI4MSSCSTZVMSNNQBW7AHAQPG/action/author_attestation","sign_citation":"https://pith.science/pith/CFI4MSSCSTZVMSNNQBW7AHAQPG/action/citation_signature","submit_replication":"https://pith.science/pith/CFI4MSSCSTZVMSNNQBW7AHAQPG/action/replication_record"}},"created_at":"2026-07-05T02:59:59.894532+00:00","updated_at":"2026-07-05T02:59:59.894532+00:00"}