{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JBMCIOEFEVJZP72MHQEF2K2UNX","short_pith_number":"pith:JBMCIOEF","canonical_record":{"source":{"id":"2002.11985","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T09:20:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"60c72e5ca38141302ac8571ff8d06860d9a91a978f6f2a17bdc345b08a1ff00b","abstract_canon_sha256":"3f8f91da4cc746c935db2b0891af9fb43720bc83be265ef4e420f05ec0904c91"},"schema_version":"1.0"},"canonical_sha256":"4858243885255397ff4c3c085d2b546dc252114a82eba0af072519a4cb08370b","source":{"kind":"arxiv","id":"2002.11985","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11985","created_at":"2026-07-05T03:17:44Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11985v2","created_at":"2026-07-05T03:17:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11985","created_at":"2026-07-05T03:17:44Z"},{"alias_kind":"pith_short_12","alias_value":"JBMCIOEFEVJZ","created_at":"2026-07-05T03:17:44Z"},{"alias_kind":"pith_short_16","alias_value":"JBMCIOEFEVJZP72M","created_at":"2026-07-05T03:17:44Z"},{"alias_kind":"pith_short_8","alias_value":"JBMCIOEF","created_at":"2026-07-05T03:17:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JBMCIOEFEVJZP72MHQEF2K2UNX","target":"record","payload":{"canonical_record":{"source":{"id":"2002.11985","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T09:20:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"60c72e5ca38141302ac8571ff8d06860d9a91a978f6f2a17bdc345b08a1ff00b","abstract_canon_sha256":"3f8f91da4cc746c935db2b0891af9fb43720bc83be265ef4e420f05ec0904c91"},"schema_version":"1.0"},"canonical_sha256":"4858243885255397ff4c3c085d2b546dc252114a82eba0af072519a4cb08370b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:44.378769Z","signature_b64":"pVXc83P2qI+dd2Lh6w8uTD4v1RtTa3GsBoaSIzFMZRNE5I/sQWlrsbkfMxEsuzXg5c+q1wmzp6xJ+YWREfWXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4858243885255397ff4c3c085d2b546dc252114a82eba0af072519a4cb08370b","last_reissued_at":"2026-07-05T03:17:44.378348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:44.378348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.11985","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":"2026-07-05T03:17:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yYqWQ1NFzxDypa8rwvkYPYn63P6qm2SL/CAEcHNdu4AIw+/ZBFIH0DFs+keSLfiAfsPlUoiLWCXg+jt2V0vXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:53:12.669480Z"},"content_sha256":"70e011dcb8f8b49ffdea80d589a997f481fd46e57083869cec96052a17bc22c4","schema_version":"1.0","event_id":"sha256:70e011dcb8f8b49ffdea80d589a997f481fd46e57083869cec96052a17bc22c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JBMCIOEFEVJZP72MHQEF2K2UNX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Deming Chen, Hassan Sajjad, Marianne Winslett, Mohammad Ali Khan, Prakhar Ganesh, Preslav Nakov, Xin Lou, Yao Chen, Yin Yang","submitted_at":"2020-02-27T09:20:31Z","abstract_excerpt":"Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and computation-intensive to suit low-capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted a lot of research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compressio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11985","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/2002.11985/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":"2026-07-05T03:17:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pYBLBSu3sSXhR2mObxU3fQJ3twO9ZehBsO3jdLiwT31urBDH8bRIlyPhZHWlJhIrZpPnkB8lOK9AwOdH6OJVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:53:12.669860Z"},"content_sha256":"cc865740f86f3eb4fa30dfb62a67f10c031fcedd6783ad4cb61ca20ad29312be","schema_version":"1.0","event_id":"sha256:cc865740f86f3eb4fa30dfb62a67f10c031fcedd6783ad4cb61ca20ad29312be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/bundle.json","state_url":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/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":"2026-07-08T14:53:12Z","links":{"resolver":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX","bundle":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/bundle.json","state":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JBMCIOEFEVJZP72MHQEF2K2UNX","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":"3f8f91da4cc746c935db2b0891af9fb43720bc83be265ef4e420f05ec0904c91","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T09:20:31Z","title_canon_sha256":"60c72e5ca38141302ac8571ff8d06860d9a91a978f6f2a17bdc345b08a1ff00b"},"schema_version":"1.0","source":{"id":"2002.11985","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11985","created_at":"2026-07-05T03:17:44Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11985v2","created_at":"2026-07-05T03:17:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11985","created_at":"2026-07-05T03:17:44Z"},{"alias_kind":"pith_short_12","alias_value":"JBMCIOEFEVJZ","created_at":"2026-07-05T03:17:44Z"},{"alias_kind":"pith_short_16","alias_value":"JBMCIOEFEVJZP72M","created_at":"2026-07-05T03:17:44Z"},{"alias_kind":"pith_short_8","alias_value":"JBMCIOEF","created_at":"2026-07-05T03:17:44Z"}],"graph_snapshots":[{"event_id":"sha256:cc865740f86f3eb4fa30dfb62a67f10c031fcedd6783ad4cb61ca20ad29312be","target":"graph","created_at":"2026-07-05T03:17:44Z","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/2002.11985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and computation-intensive to suit low-capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted a lot of research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compressio","authors_text":"Deming Chen, Hassan Sajjad, Marianne Winslett, Mohammad Ali Khan, Prakhar Ganesh, Preslav Nakov, Xin Lou, Yao Chen, Yin Yang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T09:20:31Z","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11985","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":"sha256:70e011dcb8f8b49ffdea80d589a997f481fd46e57083869cec96052a17bc22c4","target":"record","created_at":"2026-07-05T03:17:44Z","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":"3f8f91da4cc746c935db2b0891af9fb43720bc83be265ef4e420f05ec0904c91","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T09:20:31Z","title_canon_sha256":"60c72e5ca38141302ac8571ff8d06860d9a91a978f6f2a17bdc345b08a1ff00b"},"schema_version":"1.0","source":{"id":"2002.11985","kind":"arxiv","version":2}},"canonical_sha256":"4858243885255397ff4c3c085d2b546dc252114a82eba0af072519a4cb08370b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4858243885255397ff4c3c085d2b546dc252114a82eba0af072519a4cb08370b","first_computed_at":"2026-07-05T03:17:44.378348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:17:44.378348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pVXc83P2qI+dd2Lh6w8uTD4v1RtTa3GsBoaSIzFMZRNE5I/sQWlrsbkfMxEsuzXg5c+q1wmzp6xJ+YWREfWXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:17:44.378769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.11985","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70e011dcb8f8b49ffdea80d589a997f481fd46e57083869cec96052a17bc22c4","sha256:cc865740f86f3eb4fa30dfb62a67f10c031fcedd6783ad4cb61ca20ad29312be"],"state_sha256":"343c54140163175f133a12943f928612c6c857a1dfb1a66e02aa43be3b9f7b81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wYoYdl5zFUJ3mWLVAuiLSR7kPcp9EzfHQl/acIMkLfj/iQlJingNz1iABI31TxipEWkB56SDwfpnSI9imNFKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T14:53:12.672483Z","bundle_sha256":"c2dde9d8621af2aa24fb3c5cb83703b5a5a4621c34b15891ce65f5d8dbc59261"}}