{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VBK5UU2RX4S5LYUGSTASEG53RN","short_pith_number":"pith:VBK5UU2R","canonical_record":{"source":{"id":"2111.05754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-10T15:52:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d9353a08822984bf3a2aba9ea5885b8934e43810b8bf51544b00c619f6d2070b","abstract_canon_sha256":"4c4d419cc668f0752a0271152397979149a9f7a052645ae0473d7bb6b2a93341"},"schema_version":"1.0"},"canonical_sha256":"a855da5351bf25d5e28694c1221bbb8b5cff99a96724390b258df6eddebfba6b","source":{"kind":"arxiv","id":"2111.05754","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.05754","created_at":"2026-07-05T03:30:47Z"},{"alias_kind":"arxiv_version","alias_value":"2111.05754v1","created_at":"2026-07-05T03:30:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05754","created_at":"2026-07-05T03:30:47Z"},{"alias_kind":"pith_short_12","alias_value":"VBK5UU2RX4S5","created_at":"2026-07-05T03:30:47Z"},{"alias_kind":"pith_short_16","alias_value":"VBK5UU2RX4S5LYUG","created_at":"2026-07-05T03:30:47Z"},{"alias_kind":"pith_short_8","alias_value":"VBK5UU2R","created_at":"2026-07-05T03:30:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VBK5UU2RX4S5LYUGSTASEG53RN","target":"record","payload":{"canonical_record":{"source":{"id":"2111.05754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-10T15:52:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d9353a08822984bf3a2aba9ea5885b8934e43810b8bf51544b00c619f6d2070b","abstract_canon_sha256":"4c4d419cc668f0752a0271152397979149a9f7a052645ae0473d7bb6b2a93341"},"schema_version":"1.0"},"canonical_sha256":"a855da5351bf25d5e28694c1221bbb8b5cff99a96724390b258df6eddebfba6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:47.781433Z","signature_b64":"v44Oiu3PPqrAQLE8AtAsunTBV+0TJyzVwSgGay+KeC7eXgJyQVlww7eoYC8WU9jjCETl5njU7/FbZS6gFdn4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a855da5351bf25d5e28694c1221bbb8b5cff99a96724390b258df6eddebfba6b","last_reissued_at":"2026-07-05T03:30:47.780902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:47.780902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.05754","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":"2026-07-05T03:30:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7++6rs6DdkZ9cEnoH13Bqi2IAjDuCYmQsiimhS5AAJGfu9sVUBNCBxxykdOIwpw8jHI9ic2H6Tt4oPgDn+FTBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T18:07:57.793171Z"},"content_sha256":"a0f5f3f3ca8ef493c28a6a8466ee1a74fc7f5ae35d8ab67d1b42d04311786b2d","schema_version":"1.0","event_id":"sha256:a0f5f3f3ca8ef493c28a6a8466ee1a74fc7f5ae35d8ab67d1b42d04311786b2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VBK5UU2RX4S5LYUGSTASEG53RN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prune Once for All: Sparse Pre-Trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ariel Larey, Guy Boudoukh, Haihao Shen, Moshe Wasserblat, Ofir Zafrir","submitted_at":"2021-11-10T15:52:40Z","abstract_excerpt":"Transformer-based language models are applied to a wide range of applications in natural language processing. However, they are inefficient and difficult to deploy. In recent years, many compression algorithms have been proposed to increase the implementation efficiency of large Transformer-based models on target hardware. In this work we present a new method for training sparse pre-trained Transformer language models by integrating weight pruning and model distillation. These sparse pre-trained models can be used to transfer learning for a wide range of tasks while maintaining their sparsity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05754","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/2111.05754/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":"2026-07-05T03:30:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQ5rFmzZw62tPag3ukOz5O1Y7X4OpMatj1mbFD9zt7CIKOodDxN6Uy4ayXmbsFE5JOcANb6XqB8Iz/CEydaEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T18:07:57.793587Z"},"content_sha256":"f6135d06bb0c0de3056957ce9a6e164d1b8fdf9314c4c9aff6dcdd2ad88cebab","schema_version":"1.0","event_id":"sha256:f6135d06bb0c0de3056957ce9a6e164d1b8fdf9314c4c9aff6dcdd2ad88cebab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN/bundle.json","state_url":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBK5UU2RX4S5LYUGSTASEG53RN/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":"2026-07-11T18:07:57Z","links":{"resolver":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN","bundle":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN/bundle.json","state":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBK5UU2RX4S5LYUGSTASEG53RN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VBK5UU2RX4S5LYUGSTASEG53RN","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":"4c4d419cc668f0752a0271152397979149a9f7a052645ae0473d7bb6b2a93341","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-10T15:52:40Z","title_canon_sha256":"d9353a08822984bf3a2aba9ea5885b8934e43810b8bf51544b00c619f6d2070b"},"schema_version":"1.0","source":{"id":"2111.05754","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.05754","created_at":"2026-07-05T03:30:47Z"},{"alias_kind":"arxiv_version","alias_value":"2111.05754v1","created_at":"2026-07-05T03:30:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05754","created_at":"2026-07-05T03:30:47Z"},{"alias_kind":"pith_short_12","alias_value":"VBK5UU2RX4S5","created_at":"2026-07-05T03:30:47Z"},{"alias_kind":"pith_short_16","alias_value":"VBK5UU2RX4S5LYUG","created_at":"2026-07-05T03:30:47Z"},{"alias_kind":"pith_short_8","alias_value":"VBK5UU2R","created_at":"2026-07-05T03:30:47Z"}],"graph_snapshots":[{"event_id":"sha256:f6135d06bb0c0de3056957ce9a6e164d1b8fdf9314c4c9aff6dcdd2ad88cebab","target":"graph","created_at":"2026-07-05T03:30:47Z","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/2111.05754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based language models are applied to a wide range of applications in natural language processing. However, they are inefficient and difficult to deploy. In recent years, many compression algorithms have been proposed to increase the implementation efficiency of large Transformer-based models on target hardware. In this work we present a new method for training sparse pre-trained Transformer language models by integrating weight pruning and model distillation. These sparse pre-trained models can be used to transfer learning for a wide range of tasks while maintaining their sparsity ","authors_text":"Ariel Larey, Guy Boudoukh, Haihao Shen, Moshe Wasserblat, Ofir Zafrir","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-10T15:52:40Z","title":"Prune Once for All: Sparse Pre-Trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05754","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:a0f5f3f3ca8ef493c28a6a8466ee1a74fc7f5ae35d8ab67d1b42d04311786b2d","target":"record","created_at":"2026-07-05T03:30:47Z","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":"4c4d419cc668f0752a0271152397979149a9f7a052645ae0473d7bb6b2a93341","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-10T15:52:40Z","title_canon_sha256":"d9353a08822984bf3a2aba9ea5885b8934e43810b8bf51544b00c619f6d2070b"},"schema_version":"1.0","source":{"id":"2111.05754","kind":"arxiv","version":1}},"canonical_sha256":"a855da5351bf25d5e28694c1221bbb8b5cff99a96724390b258df6eddebfba6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a855da5351bf25d5e28694c1221bbb8b5cff99a96724390b258df6eddebfba6b","first_computed_at":"2026-07-05T03:30:47.780902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:30:47.780902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v44Oiu3PPqrAQLE8AtAsunTBV+0TJyzVwSgGay+KeC7eXgJyQVlww7eoYC8WU9jjCETl5njU7/FbZS6gFdn4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:30:47.781433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.05754","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0f5f3f3ca8ef493c28a6a8466ee1a74fc7f5ae35d8ab67d1b42d04311786b2d","sha256:f6135d06bb0c0de3056957ce9a6e164d1b8fdf9314c4c9aff6dcdd2ad88cebab"],"state_sha256":"88367444d01d622c4d13d8987c1ffbe53bde582e2ff36f063bc11941d8bacb2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4tlRaBbYZtyQBTMWAKwQhoXxnC1DFU/2Qy870T/sh488al9PA/oiI4n1ULPWTqHWh8nm8KPLYJd5UYWgfhwiAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T18:07:57.796134Z","bundle_sha256":"99b6459f0b877b2f08a79691e18b546a2ba511e24a3b83bf6edeac9c8d289cb0"}}