{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BSJO5GDNZH2DHJGJB3KRZIZMQ7","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":"e4552c22bd2158347f33131354a8f140be11eb563e73d4fa69f1b2e5e635c819","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-12T19:49:27Z","title_canon_sha256":"bb704012a5623347633a70c8dba6ca4651eefca1a5f7ca70ad20837453a84f5d"},"schema_version":"1.0","source":{"id":"2004.05686","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05686","created_at":"2026-07-05T01:00:17Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05686v2","created_at":"2026-07-05T01:00:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05686","created_at":"2026-07-05T01:00:17Z"},{"alias_kind":"pith_short_12","alias_value":"BSJO5GDNZH2D","created_at":"2026-07-05T01:00:17Z"},{"alias_kind":"pith_short_16","alias_value":"BSJO5GDNZH2DHJGJ","created_at":"2026-07-05T01:00:17Z"},{"alias_kind":"pith_short_8","alias_value":"BSJO5GDN","created_at":"2026-07-05T01:00:17Z"}],"graph_snapshots":[{"event_id":"sha256:c0e51b82e648835773dd3308035cec895a46af9b1a7d0aa55f2114523e5f213a","target":"graph","created_at":"2026-07-05T01:00:17Z","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/2004.05686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep and large pre-trained language models are the state-of-the-art for various natural language processing tasks. However, the huge size of these models could be a deterrent to use them in practice. Some recent and concurrent works use knowledge distillation to compress these huge models into shallow ones. In this work we study knowledge distillation with a focus on multi-lingual Named Entity Recognition (NER). In particular, we study several distillation strategies and propose a stage-wise optimization scheme leveraging teacher internal representations that is agnostic of teacher architectur","authors_text":"Ahmed Awadallah, Subhabrata Mukherjee","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-12T19:49:27Z","title":"XtremeDistil: Multi-stage Distillation for Massive Multilingual Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05686","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:c84c6c41d858ab9915b139012075e60e4cf1b97932b70b5c064ff34e56cd793c","target":"record","created_at":"2026-07-05T01:00:17Z","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":"e4552c22bd2158347f33131354a8f140be11eb563e73d4fa69f1b2e5e635c819","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-12T19:49:27Z","title_canon_sha256":"bb704012a5623347633a70c8dba6ca4651eefca1a5f7ca70ad20837453a84f5d"},"schema_version":"1.0","source":{"id":"2004.05686","kind":"arxiv","version":2}},"canonical_sha256":"0c92ee986dc9f433a4c90ed51ca32c87d3c99d33017c9d7ffa6e8d69a9aadd6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c92ee986dc9f433a4c90ed51ca32c87d3c99d33017c9d7ffa6e8d69a9aadd6b","first_computed_at":"2026-07-05T01:00:17.504888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:17.504888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/0T005lNiAS/VoOs0GqcPlC2kJiOTxqCqT30yUXzhhXxWjsrdt6UVD4ORhdVZWaynvX9z/W1haD/fKRVwDv6Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:17.505280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.05686","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c84c6c41d858ab9915b139012075e60e4cf1b97932b70b5c064ff34e56cd793c","sha256:c0e51b82e648835773dd3308035cec895a46af9b1a7d0aa55f2114523e5f213a"],"state_sha256":"3941d273a46cf9356a70dc4ff49d4c9e38d10aff3c5dc1e5c760603557c05a54"}