{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6KGESHRL2DLBFRRAKPJOXIUWNW","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":"a271952102418316fd9d6d3de461f9db69cdbb98726d32005b15a6cd20722d9b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T07:01:10Z","title_canon_sha256":"6122ed74aab5b4916df2e9fa0ed4a3e58053c7cbc96f698827daf6a6b7d2da65"},"schema_version":"1.0","source":{"id":"2402.11890","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11890","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11890v2","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11890","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"6KGESHRL2DLB","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"6KGESHRL2DLBFRRA","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"6KGESHRL","created_at":"2026-07-05T08:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:2ae610206c209c3ece20d25f6badfa96a75b5e270d9da318b18a3a04d02eeae9","target":"graph","created_at":"2026-07-05T08:32:37Z","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/2402.11890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we empirically find that larger teacher LMs might dramatically result in a poorer student. In response to this problem, we conduct a series of analyses and reveal that different tokens have different teaching modes, neglecting which will lead to performance degradation. Motivated by this, we propose a simple yet effective adaptive teaching approach (ATKD) to improve t","authors_text":"Bo Du, Dacheng Tao, Juhua Liu, Liang Ding, Li Shen, Qihuang Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T07:01:10Z","title":"Revisiting Knowledge Distillation for Autoregressive Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11890","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":"sha256:685cf01e549977e2de355cc8092e9da6b7569dc39867b7ddb87cac2c55b2643b","target":"record","created_at":"2026-07-05T08:32:37Z","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":"a271952102418316fd9d6d3de461f9db69cdbb98726d32005b15a6cd20722d9b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T07:01:10Z","title_canon_sha256":"6122ed74aab5b4916df2e9fa0ed4a3e58053c7cbc96f698827daf6a6b7d2da65"},"schema_version":"1.0","source":{"id":"2402.11890","kind":"arxiv","version":2}},"canonical_sha256":"f28c491e2bd0d612c62053d2eba2966d89ab28efd77c003da4316b66ff6f5072","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f28c491e2bd0d612c62053d2eba2966d89ab28efd77c003da4316b66ff6f5072","first_computed_at":"2026-07-05T08:32:37.044290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:37.044290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p8pJQjlkEJqeiNTHswC97dlaSJRRTnLQZej/TUkOyTsM0rlrnY2niCw5m1wV9HTrfH72dOJJfTYo8fqqUSTmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:37.044771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11890","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:685cf01e549977e2de355cc8092e9da6b7569dc39867b7ddb87cac2c55b2643b","sha256:2ae610206c209c3ece20d25f6badfa96a75b5e270d9da318b18a3a04d02eeae9"],"state_sha256":"7e613e7ab982cbab6af420330248884646eb819035b590b29eb651d20edb763e"}