{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3GKBKLGQO43F2VS4YEH3M32IQH","short_pith_number":"pith:3GKBKLGQ","canonical_record":{"source":{"id":"2306.06629","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-11T09:17:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2306e41db846efc7a099573bbf91d6673855b23368e8416e6d17a810b301e0ac","abstract_canon_sha256":"dbfb96fce14a7e315118e57e4fbe9bf111e4345a5f4ccbdf157ec4be0a6981c4"},"schema_version":"1.0"},"canonical_sha256":"d994152cd077365d565cc10fb66f4881c8ab97211fe6859c51b6d7b39f3a76ab","source":{"kind":"arxiv","id":"2306.06629","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06629","created_at":"2026-07-05T06:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06629v1","created_at":"2026-07-05T06:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06629","created_at":"2026-07-05T06:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"3GKBKLGQO43F","created_at":"2026-07-05T06:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"3GKBKLGQO43F2VS4","created_at":"2026-07-05T06:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"3GKBKLGQ","created_at":"2026-07-05T06:19:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3GKBKLGQO43F2VS4YEH3M32IQH","target":"record","payload":{"canonical_record":{"source":{"id":"2306.06629","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-11T09:17:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2306e41db846efc7a099573bbf91d6673855b23368e8416e6d17a810b301e0ac","abstract_canon_sha256":"dbfb96fce14a7e315118e57e4fbe9bf111e4345a5f4ccbdf157ec4be0a6981c4"},"schema_version":"1.0"},"canonical_sha256":"d994152cd077365d565cc10fb66f4881c8ab97211fe6859c51b6d7b39f3a76ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:27.064907Z","signature_b64":"Xf6nB1hfYFsdQy85jemqrvSG9/hEoibhYZmN6rFGEqOFWqKMHotxjwMGJhZDHUCEyZ3x0SIwH+15XkSMFB7iBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d994152cd077365d565cc10fb66f4881c8ab97211fe6859c51b6d7b39f3a76ab","last_reissued_at":"2026-07-05T06:19:27.064416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:27.064416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.06629","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:19:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AeI/kZ52k4h+Iml3sbV6mqZNM9qeUIZs19QueWg/nL2sAdnHxV89weTYUS140cM7jXA/Jr2eKq9oqyP4aewyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:20:48.555343Z"},"content_sha256":"a428e1b48c767ea7b5173efe76e68dce88353cf5e55b23ab2020615a52d21e20","schema_version":"1.0","event_id":"sha256:a428e1b48c767ea7b5173efe76e68dce88353cf5e55b23ab2020615a52d21e20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3GKBKLGQO43F2VS4YEH3M32IQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongyin Tang, Jiahao Liu, Jie Tang, Jingang Wang, Keqing He, Peng Zhang, Shicheng Tan, Shu Zhao, Weng Lam Tam, Wenwen Gong, Yang Yang, Yuanchun Wang","submitted_at":"2023-06-11T09:17:21Z","abstract_excerpt":"Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment on various devices. However, the deployment of knowledge distillation systems faces great challenges in real-world industrial-strength applications, which require the use of complex distillation methods on even larger-scale PLMs (over 10B), limited by memory on GPUs and the switching of methods. To overcome these challenges, we propose GKD, a general knowledge distillation framework that supports distillation on lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06629","kind":"arxiv","version":1},"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/2306.06629/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":"2026-07-05T06:19:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14my5zdZcrq7BHXT3BqCxQz5ySQiy1iSvSQd/sDELtg1SIdo7z9aHL2C+9Wsfg7KJ1bBkmN4jLquXejZRiNrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:20:48.556348Z"},"content_sha256":"36b5be60be37203f72ce008723faac8a72883aff71350cd2b2da2eeb09e4f81a","schema_version":"1.0","event_id":"sha256:36b5be60be37203f72ce008723faac8a72883aff71350cd2b2da2eeb09e4f81a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GKBKLGQO43F2VS4YEH3M32IQH/bundle.json","state_url":"https://pith.science/pith/3GKBKLGQO43F2VS4YEH3M32IQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GKBKLGQO43F2VS4YEH3M32IQH/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":"2026-08-05T01:20:48Z","links":{"resolver":"https://pith.science/pith/3GKBKLGQO43F2VS4YEH3M32IQH","bundle":"https://pith.science/pith/3GKBKLGQO43F2VS4YEH3M32IQH/bundle.json","state":"https://pith.science/pith/3GKBKLGQO43F2VS4YEH3M32IQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GKBKLGQO43F2VS4YEH3M32IQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3GKBKLGQO43F2VS4YEH3M32IQH","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":"dbfb96fce14a7e315118e57e4fbe9bf111e4345a5f4ccbdf157ec4be0a6981c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-11T09:17:21Z","title_canon_sha256":"2306e41db846efc7a099573bbf91d6673855b23368e8416e6d17a810b301e0ac"},"schema_version":"1.0","source":{"id":"2306.06629","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06629","created_at":"2026-07-05T06:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06629v1","created_at":"2026-07-05T06:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06629","created_at":"2026-07-05T06:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"3GKBKLGQO43F","created_at":"2026-07-05T06:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"3GKBKLGQO43F2VS4","created_at":"2026-07-05T06:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"3GKBKLGQ","created_at":"2026-07-05T06:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:36b5be60be37203f72ce008723faac8a72883aff71350cd2b2da2eeb09e4f81a","target":"graph","created_at":"2026-07-05T06:19:27Z","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/2306.06629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment on various devices. However, the deployment of knowledge distillation systems faces great challenges in real-world industrial-strength applications, which require the use of complex distillation methods on even larger-scale PLMs (over 10B), limited by memory on GPUs and the switching of methods. To overcome these challenges, we propose GKD, a general knowledge distillation framework that supports distillation on lar","authors_text":"Hongyin Tang, Jiahao Liu, Jie Tang, Jingang Wang, Keqing He, Peng Zhang, Shicheng Tan, Shu Zhao, Weng Lam Tam, Wenwen Gong, Yang Yang, Yuanchun Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-11T09:17:21Z","title":"GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06629","kind":"arxiv","version":1},"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:a428e1b48c767ea7b5173efe76e68dce88353cf5e55b23ab2020615a52d21e20","target":"record","created_at":"2026-07-05T06:19:27Z","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":"dbfb96fce14a7e315118e57e4fbe9bf111e4345a5f4ccbdf157ec4be0a6981c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-11T09:17:21Z","title_canon_sha256":"2306e41db846efc7a099573bbf91d6673855b23368e8416e6d17a810b301e0ac"},"schema_version":"1.0","source":{"id":"2306.06629","kind":"arxiv","version":1}},"canonical_sha256":"d994152cd077365d565cc10fb66f4881c8ab97211fe6859c51b6d7b39f3a76ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d994152cd077365d565cc10fb66f4881c8ab97211fe6859c51b6d7b39f3a76ab","first_computed_at":"2026-07-05T06:19:27.064416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:27.064416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xf6nB1hfYFsdQy85jemqrvSG9/hEoibhYZmN6rFGEqOFWqKMHotxjwMGJhZDHUCEyZ3x0SIwH+15XkSMFB7iBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:27.064907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.06629","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a428e1b48c767ea7b5173efe76e68dce88353cf5e55b23ab2020615a52d21e20","sha256:36b5be60be37203f72ce008723faac8a72883aff71350cd2b2da2eeb09e4f81a"],"state_sha256":"106cd9d93ad4a203e4828f9a1cf18408a3d054fd836d6efe08590c81ef717fe8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OadlLEXOpGIjSJDd9E9mn0NWV2mzDJWnvOgSjSzx6vfnWuyU1A21xhyezYALuiU8+fdhKXTBwHQtDdOSGtGECA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:20:48.565930Z","bundle_sha256":"83fd410c539fd311c7e61ca586b2da21127f294545b577f70b0ddde857b08307"}}