{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:S5Y52KSEHYR6ENTRNH4RXMBQK6","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":"859e86882405960b1ae55e58206721b27304f624f7d28d3573ddfa96618e7dbc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T16:49:52Z","title_canon_sha256":"1aa1c32ddec794617dc515e6a158c317546c0615065628620272b0db4e3b6bc0"},"schema_version":"1.0","source":{"id":"2210.04834","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04834","created_at":"2026-07-05T05:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04834v3","created_at":"2026-07-05T05:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04834","created_at":"2026-07-05T05:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"S5Y52KSEHYR6","created_at":"2026-07-05T05:07:23Z"},{"alias_kind":"pith_short_16","alias_value":"S5Y52KSEHYR6ENTR","created_at":"2026-07-05T05:07:23Z"},{"alias_kind":"pith_short_8","alias_value":"S5Y52KSE","created_at":"2026-07-05T05:07:23Z"}],"graph_snapshots":[{"event_id":"sha256:e7458a81d6399a897135828f587d404a689b8b5616eb5fac8eb32bc28c94e5ec","target":"graph","created_at":"2026-07-05T05:07:23Z","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/2210.04834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Teacher-student knowledge distillation is a popular technique for compressing today's prevailing large language models into manageable sizes that fit low-latency downstream applications. Both the teacher and the choice of transfer set used for distillation are crucial ingredients in creating a high quality student. Yet, the generic corpora used to pretrain the teacher and the corpora associated with the downstream target domain are often significantly different, which raises a natural question: should the student be distilled over the generic corpora, so as to learn from high-quality teacher p","authors_text":"Charith Peris, Gokmen Oz, Lizhen Tan, Pan Wei, Thomas Gueudre, Turan Gojayev","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T16:49:52Z","title":"Knowledge Distillation Transfer Sets and their Impact on Downstream NLU Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04834","kind":"arxiv","version":3},"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":"sha256:57bcae585f058e9b5d1ceea37af5dad1e38023a20e166e3f11388b534ff7220e","target":"record","created_at":"2026-07-05T05:07:23Z","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":"859e86882405960b1ae55e58206721b27304f624f7d28d3573ddfa96618e7dbc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T16:49:52Z","title_canon_sha256":"1aa1c32ddec794617dc515e6a158c317546c0615065628620272b0db4e3b6bc0"},"schema_version":"1.0","source":{"id":"2210.04834","kind":"arxiv","version":3}},"canonical_sha256":"9771dd2a443e23e2367169f91bb03057b892e69ac57d142e552c00a7f45fc844","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9771dd2a443e23e2367169f91bb03057b892e69ac57d142e552c00a7f45fc844","first_computed_at":"2026-07-05T05:07:23.252611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:23.252611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8HA7BPnLmWM4YX5511oSiWLGI3HMd0oavQAhd3tFsQBaY1e9vN+b/SYokWiVesUxzdNLFSaa0UYY5GuHmDnlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:23.253206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04834","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57bcae585f058e9b5d1ceea37af5dad1e38023a20e166e3f11388b534ff7220e","sha256:e7458a81d6399a897135828f587d404a689b8b5616eb5fac8eb32bc28c94e5ec"],"state_sha256":"f41b2a081c5a6b16bd96caaedf9412ce12c7304d782bad56b85c8f69213a6f5d"}