{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GC556WP7OSXG6F2YH2PMXINA47","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":"72fb66a9346d025b1958a9206f2ab7ca2aa01b5cd26bcc712fd2b7bc138af9e1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-10T07:00:57Z","title_canon_sha256":"02e551e004c691c96e1f227496ba31564a947320959bb14d2c5e5157b13846e8"},"schema_version":"1.0","source":{"id":"2010.04924","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04924","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04924v1","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04924","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"pith_short_12","alias_value":"GC556WP7OSXG","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"pith_short_16","alias_value":"GC556WP7OSXG6F2Y","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"pith_short_8","alias_value":"GC556WP7","created_at":"2026-07-05T01:42:00Z"}],"graph_snapshots":[{"event_id":"sha256:4dbb143fafd1ed1699e3ac324e1136e0905f37d27344f5c5e2d7e5c6844ad2a7","target":"graph","created_at":"2026-07-05T01:42:00Z","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/2010.04924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art Neural Machine Translation (NMT) models struggle with generating low-frequency tokens, tackling which remains a major challenge. The analysis of long-tailed phenomena in the context of structured prediction tasks is further hindered by the added complexities of search during inference. In this work, we quantitatively characterize such long-tailed phenomena at two levels of abstraction, namely, token classification and sequence generation. We propose a new loss function, the Anti-Focal loss, to better adapt model training to the structural dependencies of conditional text gener","authors_text":"Florian Metze, Siddharth Dalmia, Vikas Raunak, Vivek Gupta","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-10T07:00:57Z","title":"On Long-Tailed Phenomena in Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04924","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":"sha256:38b10facc928431a398e5155f1228869fa977a4ee262a62cf32a8b985af7f126","target":"record","created_at":"2026-07-05T01:42:00Z","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":"72fb66a9346d025b1958a9206f2ab7ca2aa01b5cd26bcc712fd2b7bc138af9e1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-10T07:00:57Z","title_canon_sha256":"02e551e004c691c96e1f227496ba31564a947320959bb14d2c5e5157b13846e8"},"schema_version":"1.0","source":{"id":"2010.04924","kind":"arxiv","version":1}},"canonical_sha256":"30bbdf59ff74ae6f17583e9ecba1a0e7e71ac418139cfec88931928dda0de25a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30bbdf59ff74ae6f17583e9ecba1a0e7e71ac418139cfec88931928dda0de25a","first_computed_at":"2026-07-05T01:42:00.762404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:42:00.762404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Trvv0ibGZ+a2BbE88ElHAdBzDZ3CjFxmg4+UAX8Ywf8Ty4ctzY/1oLDhesXWqPD8vv5jUUQV6UCg0QXmi5NiCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:42:00.762809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04924","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38b10facc928431a398e5155f1228869fa977a4ee262a62cf32a8b985af7f126","sha256:4dbb143fafd1ed1699e3ac324e1136e0905f37d27344f5c5e2d7e5c6844ad2a7"],"state_sha256":"b3ad7843087fccd21c17508749a6f17245492f3ae283787b3db2967ab205bc44"}