{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PQMHZSOBODRJIPGK2FCPC7TBEP","short_pith_number":"pith:PQMHZSOB","canonical_record":{"source":{"id":"2004.12817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-27T14:00:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b02b63fa052653892cba0e1a3e8c19a4a54a9cbce8dbe67f58d23b360e11856b","abstract_canon_sha256":"422f5aad401556e8767af031e464ca38fc53792dc78712c9fc3b074c70ea05e4"},"schema_version":"1.0"},"canonical_sha256":"7c187cc9c170e2943ccad144f17e6123e6762901eaf3f2083493dfdf11020c4d","source":{"kind":"arxiv","id":"2004.12817","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.12817","created_at":"2026-07-05T00:58:27Z"},{"alias_kind":"arxiv_version","alias_value":"2004.12817v1","created_at":"2026-07-05T00:58:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12817","created_at":"2026-07-05T00:58:27Z"},{"alias_kind":"pith_short_12","alias_value":"PQMHZSOBODRJ","created_at":"2026-07-05T00:58:27Z"},{"alias_kind":"pith_short_16","alias_value":"PQMHZSOBODRJIPGK","created_at":"2026-07-05T00:58:27Z"},{"alias_kind":"pith_short_8","alias_value":"PQMHZSOB","created_at":"2026-07-05T00:58:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PQMHZSOBODRJIPGK2FCPC7TBEP","target":"record","payload":{"canonical_record":{"source":{"id":"2004.12817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-27T14:00:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b02b63fa052653892cba0e1a3e8c19a4a54a9cbce8dbe67f58d23b360e11856b","abstract_canon_sha256":"422f5aad401556e8767af031e464ca38fc53792dc78712c9fc3b074c70ea05e4"},"schema_version":"1.0"},"canonical_sha256":"7c187cc9c170e2943ccad144f17e6123e6762901eaf3f2083493dfdf11020c4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:27.434055Z","signature_b64":"hyVSnXKX2RtnqgghXt5B6Lbk0aBF0z0Rot0ccRyM6fPUtE0ijHg64+S7jGq1jjrrZTq1b+xAQ4UuMoW4SOv+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c187cc9c170e2943ccad144f17e6123e6762901eaf3f2083493dfdf11020c4d","last_reissued_at":"2026-07-05T00:58:27.433612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:27.433612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.12817","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":"2026-07-05T00:58:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lm88GyHIs6f1wUPSbbjVcCcC3LpapXWSVd3aSqfBN8xZ1hn8ZZZIenf2QyhbptlgrdhqV9Oq17jjKJ3Dgc2qDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:57:03.866664Z"},"content_sha256":"13e0a8aba948687c228ba718b9557c7f064f2d4cb750fcaaef5393bd597ae2c1","schema_version":"1.0","event_id":"sha256:13e0a8aba948687c228ba718b9557c7f064f2d4cb750fcaaef5393bd597ae2c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PQMHZSOBODRJIPGK2FCPC7TBEP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hao Sun, Hongzhi Liu, Jianfeng Lu, Kaitao Song, Tao Qin, Tie-Yan Liu, Xu Tan","submitted_at":"2020-04-27T14:00:09Z","abstract_excerpt":"While pre-training and fine-tuning, e.g., BERT~\\citep{devlin2018bert}, GPT-2~\\citep{radford2019language}, have achieved great success in language understanding and generation tasks, the pre-trained models are usually too big for online deployment in terms of both memory cost and inference speed, which hinders them from practical online usage. In this paper, we propose LightPAFF, a Lightweight Pre-training And Fine-tuning Framework that leverages two-stage knowledge distillation to transfer knowledge from a big teacher model to a lightweight student model in both pre-training and fine-tuning st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12817","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/2004.12817/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":"2026-07-05T00:58:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pqczb3yBaKga/pn73GsR13z0iOJ5YDTcFWdXgO/WNv0Jj9QgGLgwig9eAA2dm1NiywVRlGf9g6XeZi2RWzd+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:57:03.867209Z"},"content_sha256":"4d149bc9df7941067c04ed7b9b53d838111f0f3064361ae9d1d33a024c349e85","schema_version":"1.0","event_id":"sha256:4d149bc9df7941067c04ed7b9b53d838111f0f3064361ae9d1d33a024c349e85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQMHZSOBODRJIPGK2FCPC7TBEP/bundle.json","state_url":"https://pith.science/pith/PQMHZSOBODRJIPGK2FCPC7TBEP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQMHZSOBODRJIPGK2FCPC7TBEP/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":"2026-08-09T03:57:03Z","links":{"resolver":"https://pith.science/pith/PQMHZSOBODRJIPGK2FCPC7TBEP","bundle":"https://pith.science/pith/PQMHZSOBODRJIPGK2FCPC7TBEP/bundle.json","state":"https://pith.science/pith/PQMHZSOBODRJIPGK2FCPC7TBEP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQMHZSOBODRJIPGK2FCPC7TBEP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PQMHZSOBODRJIPGK2FCPC7TBEP","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":"422f5aad401556e8767af031e464ca38fc53792dc78712c9fc3b074c70ea05e4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-27T14:00:09Z","title_canon_sha256":"b02b63fa052653892cba0e1a3e8c19a4a54a9cbce8dbe67f58d23b360e11856b"},"schema_version":"1.0","source":{"id":"2004.12817","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.12817","created_at":"2026-07-05T00:58:27Z"},{"alias_kind":"arxiv_version","alias_value":"2004.12817v1","created_at":"2026-07-05T00:58:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12817","created_at":"2026-07-05T00:58:27Z"},{"alias_kind":"pith_short_12","alias_value":"PQMHZSOBODRJ","created_at":"2026-07-05T00:58:27Z"},{"alias_kind":"pith_short_16","alias_value":"PQMHZSOBODRJIPGK","created_at":"2026-07-05T00:58:27Z"},{"alias_kind":"pith_short_8","alias_value":"PQMHZSOB","created_at":"2026-07-05T00:58:27Z"}],"graph_snapshots":[{"event_id":"sha256:4d149bc9df7941067c04ed7b9b53d838111f0f3064361ae9d1d33a024c349e85","target":"graph","created_at":"2026-07-05T00:58:27Z","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/2004.12817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While pre-training and fine-tuning, e.g., BERT~\\citep{devlin2018bert}, GPT-2~\\citep{radford2019language}, have achieved great success in language understanding and generation tasks, the pre-trained models are usually too big for online deployment in terms of both memory cost and inference speed, which hinders them from practical online usage. In this paper, we propose LightPAFF, a Lightweight Pre-training And Fine-tuning Framework that leverages two-stage knowledge distillation to transfer knowledge from a big teacher model to a lightweight student model in both pre-training and fine-tuning st","authors_text":"Hao Sun, Hongzhi Liu, Jianfeng Lu, Kaitao Song, Tao Qin, Tie-Yan Liu, Xu Tan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-27T14:00:09Z","title":"LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12817","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":"sha256:13e0a8aba948687c228ba718b9557c7f064f2d4cb750fcaaef5393bd597ae2c1","target":"record","created_at":"2026-07-05T00:58:27Z","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":"422f5aad401556e8767af031e464ca38fc53792dc78712c9fc3b074c70ea05e4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-27T14:00:09Z","title_canon_sha256":"b02b63fa052653892cba0e1a3e8c19a4a54a9cbce8dbe67f58d23b360e11856b"},"schema_version":"1.0","source":{"id":"2004.12817","kind":"arxiv","version":1}},"canonical_sha256":"7c187cc9c170e2943ccad144f17e6123e6762901eaf3f2083493dfdf11020c4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c187cc9c170e2943ccad144f17e6123e6762901eaf3f2083493dfdf11020c4d","first_computed_at":"2026-07-05T00:58:27.433612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:58:27.433612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hyVSnXKX2RtnqgghXt5B6Lbk0aBF0z0Rot0ccRyM6fPUtE0ijHg64+S7jGq1jjrrZTq1b+xAQ4UuMoW4SOv+AA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:58:27.434055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.12817","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13e0a8aba948687c228ba718b9557c7f064f2d4cb750fcaaef5393bd597ae2c1","sha256:4d149bc9df7941067c04ed7b9b53d838111f0f3064361ae9d1d33a024c349e85"],"state_sha256":"0ae7bd575c647cc178b5cc3f6ccec6dfba5938b51dc345a2edee1f9f6c677430"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mOufH60qdgwURpcha4MsUy9B4dT6oyuJAXJzN0GtyKpgn3cn5koTOKn14io8fENEmbL0rB2Zye7LqJdDPmToAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:57:03.872586Z","bundle_sha256":"4079919b13b1246a0a28250e3ddc110e3aeba96f99af58da988e4ad067007058"}}