{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5QGGTNODICGZQ67O7FDJIEDYPJ","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":"d2e9e7d0182b296a05d3b51f5cd71e25a30be98a8db20b80795bd9459539f58a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T18:59:21Z","title_canon_sha256":"668b8900bb0ff0b84f9d7c4f19982f4089c1e4d954200b772161c37a44932502"},"schema_version":"1.0","source":{"id":"2407.08818","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08818","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08818v2","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08818","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_12","alias_value":"5QGGTNODICGZ","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_16","alias_value":"5QGGTNODICGZQ67O","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_8","alias_value":"5QGGTNOD","created_at":"2026-07-05T09:36:13Z"}],"graph_snapshots":[{"event_id":"sha256:d6b5d5cb50313dff1f198f9d65a8410015f4d87975e12e83a3fe1a31ed4cbb0d","target":"graph","created_at":"2026-07-05T09:36:13Z","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/2407.08818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In multilingual settings, non-Latin scripts and low-resource languages are usually disadvantaged in terms of language models' utility, efficiency, and cost. Specifically, previous studies have reported multiple modeling biases that the current tokenization algorithms introduce to non-Latin script languages, the main one being over-segmentation. In this work, we propose MAGNET; multilingual adaptive gradient-based tokenization to reduce over-segmentation via adaptive gradient-based subword tokenization. MAGNET learns to predict segment boundaries between byte tokens in a sequence via sub-module","authors_text":"Hila Gonen, Noah A. Smith, Orevaoghene Ahia, Sachin Kumar, Tomasz Limisiewicz, Valentin Hofmann, Yulia Tsvetkov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T18:59:21Z","title":"MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08818","kind":"arxiv","version":2},"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":"sha256:22aa59199a142705c7f11384dc98dcd744b83a2e9cafb32e2d86cdef4b6f7f6e","target":"record","created_at":"2026-07-05T09:36:13Z","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":"d2e9e7d0182b296a05d3b51f5cd71e25a30be98a8db20b80795bd9459539f58a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T18:59:21Z","title_canon_sha256":"668b8900bb0ff0b84f9d7c4f19982f4089c1e4d954200b772161c37a44932502"},"schema_version":"1.0","source":{"id":"2407.08818","kind":"arxiv","version":2}},"canonical_sha256":"ec0c69b5c3408d987beef9469410787a500b6bba2e6e83cef56105d35e598596","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec0c69b5c3408d987beef9469410787a500b6bba2e6e83cef56105d35e598596","first_computed_at":"2026-07-05T09:36:13.088911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:13.088911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4VrCAXDo189uMCrpmizQ73SeNnWHv0MFEDhIcaflIvgPDz7+jM1GocBHoGxw4rNXzM4iadl0L0nt5cCn8SAwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:13.089365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08818","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22aa59199a142705c7f11384dc98dcd744b83a2e9cafb32e2d86cdef4b6f7f6e","sha256:d6b5d5cb50313dff1f198f9d65a8410015f4d87975e12e83a3fe1a31ed4cbb0d"],"state_sha256":"db9e977ba30b64c9e79ac04d5233b984e3fcb19f35702d20fef3375df056b50c"}