{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FLJWGOEGHVBQNQF7ZR5MJMHEMZ","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":"1212cf6537847745eac4e7535afcc950081af40220a22aa774b2ec5f968640e4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-17T10:02:30Z","title_canon_sha256":"4bc450a74b9381c140856ce0cecfd7256cc6975711ce5dcc5836f9f639ea8523"},"schema_version":"1.0","source":{"id":"2107.08212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.08212","created_at":"2026-07-05T02:58:46Z"},{"alias_kind":"arxiv_version","alias_value":"2107.08212v1","created_at":"2026-07-05T02:58:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08212","created_at":"2026-07-05T02:58:46Z"},{"alias_kind":"pith_short_12","alias_value":"FLJWGOEGHVBQ","created_at":"2026-07-05T02:58:46Z"},{"alias_kind":"pith_short_16","alias_value":"FLJWGOEGHVBQNQF7","created_at":"2026-07-05T02:58:46Z"},{"alias_kind":"pith_short_8","alias_value":"FLJWGOEG","created_at":"2026-07-05T02:58:46Z"}],"graph_snapshots":[{"event_id":"sha256:fe8e90c304eba16445a66bfe3b952fd5d0a56484bb85c0b781590910385a9658","target":"graph","created_at":"2026-07-05T02:58:46Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.08212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous studies have shown that initializing neural machine translation (NMT) models with the pre-trained language models (LM) can speed up the model training and boost the model performance. In this work, we identify a critical side-effect of pre-training for NMT, which is due to the discrepancy between the training objectives of LM-based pre-training and NMT. Since the LM objective learns to reconstruct a few source tokens and copy most of them, the pre-training initialization would affect the copying behaviors of NMT models. We provide a quantitative analysis of copying behaviors by introd","authors_text":"Derek F. Wong, Liang Ding, Lidia S. Chao, Longyue Wang, Shuming Shi, Xuebo Liu, Zhaopeng Tu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-17T10:02:30Z","title":"On the Copying Behaviors of Pre-Training for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08212","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":"sha256:067a63fb14e9574dda7ab536f2cf5a11f86706bd21b78562386a45b2910ac19d","target":"record","created_at":"2026-07-05T02:58:46Z","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":"1212cf6537847745eac4e7535afcc950081af40220a22aa774b2ec5f968640e4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-17T10:02:30Z","title_canon_sha256":"4bc450a74b9381c140856ce0cecfd7256cc6975711ce5dcc5836f9f639ea8523"},"schema_version":"1.0","source":{"id":"2107.08212","kind":"arxiv","version":1}},"canonical_sha256":"2ad36338863d4306c0bfcc7ac4b0e4666a904130fca748e47afea1c11433d5af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ad36338863d4306c0bfcc7ac4b0e4666a904130fca748e47afea1c11433d5af","first_computed_at":"2026-07-05T02:58:46.779501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:58:46.779501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hx7nZlJFzjExl3a6MZ7OoizxKo2SxKmm3F1hfl+jqS4jHKTQdThO4rV50EIJPmhmIvyML1t5ElA0BlV4BYgxBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:58:46.779925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.08212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:067a63fb14e9574dda7ab536f2cf5a11f86706bd21b78562386a45b2910ac19d","sha256:fe8e90c304eba16445a66bfe3b952fd5d0a56484bb85c0b781590910385a9658"],"state_sha256":"9a53e23aa116ff314309486ebf70d6554787f03d03e302b9d3eb1363cded1293"}