{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QIWOFYPDZH4Z47W333564RXVQ5","short_pith_number":"pith:QIWOFYPD","canonical_record":{"source":{"id":"2305.08096","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-14T08:23:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b394f0d75adaf71ced46d7b81a1f9d7c0736fe6fe3f90312c5c7cab1b8fd9b05","abstract_canon_sha256":"dc1eb8b3453ab15aaa4f9c4d8a45b67e50af8c343fabc2b5c99c4058d7e0c273"},"schema_version":"1.0"},"canonical_sha256":"822ce2e1e3c9f99e7edbdefbee46f58779c9cfc6c67903fd0df2b8fd8af08ef2","source":{"kind":"arxiv","id":"2305.08096","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08096","created_at":"2026-07-05T08:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08096v2","created_at":"2026-07-05T08:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08096","created_at":"2026-07-05T08:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"QIWOFYPDZH4Z","created_at":"2026-07-05T08:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"QIWOFYPDZH4Z47W3","created_at":"2026-07-05T08:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"QIWOFYPD","created_at":"2026-07-05T08:44:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QIWOFYPDZH4Z47W333564RXVQ5","target":"record","payload":{"canonical_record":{"source":{"id":"2305.08096","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-14T08:23:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b394f0d75adaf71ced46d7b81a1f9d7c0736fe6fe3f90312c5c7cab1b8fd9b05","abstract_canon_sha256":"dc1eb8b3453ab15aaa4f9c4d8a45b67e50af8c343fabc2b5c99c4058d7e0c273"},"schema_version":"1.0"},"canonical_sha256":"822ce2e1e3c9f99e7edbdefbee46f58779c9cfc6c67903fd0df2b8fd8af08ef2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:46.290005Z","signature_b64":"UHsTwEvPZJniSgI8zIEpBcC6bNa1hqiHYZ3YEVfL78U9rrhYrjJ23ABQOVoggNd1/Rv9SljrKHJOBjt3sI2kDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"822ce2e1e3c9f99e7edbdefbee46f58779c9cfc6c67903fd0df2b8fd8af08ef2","last_reissued_at":"2026-07-05T08:44:46.289587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:46.289587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.08096","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZtOhh9IBT/2+W1M+ioHpm1Wx4Vy1KkcAzPGWBvB+sfFUJF4iEssULvvnKubCRr5clRQx+7isOVMavngOGWEpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:50:40.457754Z"},"content_sha256":"64f1a7c2aab8320f88b8d237a4afc69b3bc4ed375fae5aa0ea29a366910412c8","schema_version":"1.0","event_id":"sha256:64f1a7c2aab8320f88b8d237a4afc69b3bc4ed375fae5aa0ea29a366910412c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QIWOFYPDZH4Z47W333564RXVQ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jian Liu, Jinan Xu, Shuaibo Wang, Songming Zhang, Wenjuan Han, Yufeng Chen, Yunlong Liang","submitted_at":"2023-05-14T08:23:03Z","abstract_excerpt":"Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel this mystery from an empirical perspective and show that the knowledge comes from the top-1 predictions of teachers, which also helps us build a potential connection between word- and sequence-level KD. Further, we point out two inherent issues in vanilla word-level KD based on this finding. Firstly, the current objective of KD spreads its focus to whole distr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08096","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.08096/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b7xwvZaiQxpjzk/h+pdPlbFCF1d/r2q+bPnZsi2o2O+g8J6gN/GBlbYS2sES/a6r3QOoILVKXqRV5Lp8jPhvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:50:40.458448Z"},"content_sha256":"d4a6dbc7317c3f1af1e3fe575b7bf9b3a6750f43c45de911f57ea405b3909b41","schema_version":"1.0","event_id":"sha256:d4a6dbc7317c3f1af1e3fe575b7bf9b3a6750f43c45de911f57ea405b3909b41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QIWOFYPDZH4Z47W333564RXVQ5/bundle.json","state_url":"https://pith.science/pith/QIWOFYPDZH4Z47W333564RXVQ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QIWOFYPDZH4Z47W333564RXVQ5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T19:50:40Z","links":{"resolver":"https://pith.science/pith/QIWOFYPDZH4Z47W333564RXVQ5","bundle":"https://pith.science/pith/QIWOFYPDZH4Z47W333564RXVQ5/bundle.json","state":"https://pith.science/pith/QIWOFYPDZH4Z47W333564RXVQ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QIWOFYPDZH4Z47W333564RXVQ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QIWOFYPDZH4Z47W333564RXVQ5","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":"dc1eb8b3453ab15aaa4f9c4d8a45b67e50af8c343fabc2b5c99c4058d7e0c273","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-14T08:23:03Z","title_canon_sha256":"b394f0d75adaf71ced46d7b81a1f9d7c0736fe6fe3f90312c5c7cab1b8fd9b05"},"schema_version":"1.0","source":{"id":"2305.08096","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08096","created_at":"2026-07-05T08:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08096v2","created_at":"2026-07-05T08:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08096","created_at":"2026-07-05T08:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"QIWOFYPDZH4Z","created_at":"2026-07-05T08:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"QIWOFYPDZH4Z47W3","created_at":"2026-07-05T08:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"QIWOFYPD","created_at":"2026-07-05T08:44:46Z"}],"graph_snapshots":[{"event_id":"sha256:d4a6dbc7317c3f1af1e3fe575b7bf9b3a6750f43c45de911f57ea405b3909b41","target":"graph","created_at":"2026-07-05T08:44:46Z","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/2305.08096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel this mystery from an empirical perspective and show that the knowledge comes from the top-1 predictions of teachers, which also helps us build a potential connection between word- and sequence-level KD. Further, we point out two inherent issues in vanilla word-level KD based on this finding. Firstly, the current objective of KD spreads its focus to whole distr","authors_text":"Jian Liu, Jinan Xu, Shuaibo Wang, Songming Zhang, Wenjuan Han, Yufeng Chen, Yunlong Liang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-14T08:23:03Z","title":"Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08096","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":"sha256:64f1a7c2aab8320f88b8d237a4afc69b3bc4ed375fae5aa0ea29a366910412c8","target":"record","created_at":"2026-07-05T08:44:46Z","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":"dc1eb8b3453ab15aaa4f9c4d8a45b67e50af8c343fabc2b5c99c4058d7e0c273","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-14T08:23:03Z","title_canon_sha256":"b394f0d75adaf71ced46d7b81a1f9d7c0736fe6fe3f90312c5c7cab1b8fd9b05"},"schema_version":"1.0","source":{"id":"2305.08096","kind":"arxiv","version":2}},"canonical_sha256":"822ce2e1e3c9f99e7edbdefbee46f58779c9cfc6c67903fd0df2b8fd8af08ef2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"822ce2e1e3c9f99e7edbdefbee46f58779c9cfc6c67903fd0df2b8fd8af08ef2","first_computed_at":"2026-07-05T08:44:46.289587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:46.289587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UHsTwEvPZJniSgI8zIEpBcC6bNa1hqiHYZ3YEVfL78U9rrhYrjJ23ABQOVoggNd1/Rv9SljrKHJOBjt3sI2kDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:46.290005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.08096","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64f1a7c2aab8320f88b8d237a4afc69b3bc4ed375fae5aa0ea29a366910412c8","sha256:d4a6dbc7317c3f1af1e3fe575b7bf9b3a6750f43c45de911f57ea405b3909b41"],"state_sha256":"3a08356381dcc7816b9e75681a810c0b3bd4aec0f81540f926b71c51f1039236"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXZb71mfzaYIelI+xU55B2cAE/wXP2H90NbGRvLbZ7MxBBgnu4RWLV8Hs43KYlDLzGiQ+gK1PByx3g+cxW3YDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:50:40.464307Z","bundle_sha256":"8740bb7f904025c43cc2a48de2f9d7968720233634d87f5cc0702eb8befcd9a6"}}