{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2PWCICMBWZVSEBHOZQ5IPS5H6V","short_pith_number":"pith:2PWCICMB","schema_version":"1.0","canonical_sha256":"d3ec240981b66b2204eecc3a87cba7f57706a87ddcf8a7044817eca80825d509","source":{"kind":"arxiv","id":"2012.02975","version":1},"attestation_state":"computed","paper":{"title":"Reciprocal Supervised Learning Improves Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Zhou, Lei Li, Mingxuan Wang, Minkai Xu, Weinan Zhang, Zhouhan Lin","submitted_at":"2020-12-05T08:23:13Z","abstract_excerpt":"Despite the recent success on image classification, self-training has only achieved limited gains on structured prediction tasks such as neural machine translation (NMT). This is mainly due to the compositionality of the target space, where the far-away prediction hypotheses lead to the notorious reinforced mistake problem. In this paper, we revisit the utilization of multiple diverse models and present a simple yet effective approach named Reciprocal-Supervised Learning (RSL). RSL first exploits individual models to generate pseudo parallel data, and then cooperatively trains each model on th"},"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":"2012.02975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-05T08:23:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f22d8198baba8f32d6c84b3bd9d3eb161b8664d38142983722f83459c8020911","abstract_canon_sha256":"e951b88b5d5cb303b54612d8679b2226b455f859a1428b97e2581357399ee736"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:24.507669Z","signature_b64":"b9ws4d7OVSfT44XumZjrfD8gwmgKHGSq4D+Xos4+EwTtkCD/K6bX8eqHFOPBC+DlhM3ygqW1O+qa89WKAaG5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3ec240981b66b2204eecc3a87cba7f57706a87ddcf8a7044817eca80825d509","last_reissued_at":"2026-07-05T01:57:24.507170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:24.507170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reciprocal Supervised Learning Improves Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Zhou, Lei Li, Mingxuan Wang, Minkai Xu, Weinan Zhang, Zhouhan Lin","submitted_at":"2020-12-05T08:23:13Z","abstract_excerpt":"Despite the recent success on image classification, self-training has only achieved limited gains on structured prediction tasks such as neural machine translation (NMT). This is mainly due to the compositionality of the target space, where the far-away prediction hypotheses lead to the notorious reinforced mistake problem. In this paper, we revisit the utilization of multiple diverse models and present a simple yet effective approach named Reciprocal-Supervised Learning (RSL). RSL first exploits individual models to generate pseudo parallel data, and then cooperatively trains each model on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02975","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/2012.02975/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":"2012.02975","created_at":"2026-07-05T01:57:24.507228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.02975v1","created_at":"2026-07-05T01:57:24.507228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02975","created_at":"2026-07-05T01:57:24.507228+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PWCICMBWZVS","created_at":"2026-07-05T01:57:24.507228+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PWCICMBWZVSEBHO","created_at":"2026-07-05T01:57:24.507228+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PWCICMB","created_at":"2026-07-05T01:57:24.507228+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/2PWCICMBWZVSEBHOZQ5IPS5H6V","json":"https://pith.science/pith/2PWCICMBWZVSEBHOZQ5IPS5H6V.json","graph_json":"https://pith.science/api/pith-number/2PWCICMBWZVSEBHOZQ5IPS5H6V/graph.json","events_json":"https://pith.science/api/pith-number/2PWCICMBWZVSEBHOZQ5IPS5H6V/events.json","paper":"https://pith.science/paper/2PWCICMB"},"agent_actions":{"view_html":"https://pith.science/pith/2PWCICMBWZVSEBHOZQ5IPS5H6V","download_json":"https://pith.science/pith/2PWCICMBWZVSEBHOZQ5IPS5H6V.json","view_paper":"https://pith.science/paper/2PWCICMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.02975&json=true","fetch_graph":"https://pith.science/api/pith-number/2PWCICMBWZVSEBHOZQ5IPS5H6V/graph.json","fetch_events":"https://pith.science/api/pith-number/2PWCICMBWZVSEBHOZQ5IPS5H6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PWCICMBWZVSEBHOZQ5IPS5H6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PWCICMBWZVSEBHOZQ5IPS5H6V/action/storage_attestation","attest_author":"https://pith.science/pith/2PWCICMBWZVSEBHOZQ5IPS5H6V/action/author_attestation","sign_citation":"https://pith.science/pith/2PWCICMBWZVSEBHOZQ5IPS5H6V/action/citation_signature","submit_replication":"https://pith.science/pith/2PWCICMBWZVSEBHOZQ5IPS5H6V/action/replication_record"}},"created_at":"2026-07-05T01:57:24.507228+00:00","updated_at":"2026-07-05T01:57:24.507228+00:00"}