{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CVUXKR5NBQQDRHPAXCYJAVTYAI","short_pith_number":"pith:CVUXKR5N","canonical_record":{"source":{"id":"2405.02267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-03T17:34:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0f0fe4033ebce03f803b226e81844b111b78cdd7a17fac9284a1fd80bb291cea","abstract_canon_sha256":"192a5a847435139c189d52c44b0357bb1064db342051b190a9e07d81e583352c"},"schema_version":"1.0"},"canonical_sha256":"15697547ad0c20389de0b8b0905678022ee90c35ba58f6f0db839ca217cd32a6","source":{"kind":"arxiv","id":"2405.02267","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02267","created_at":"2026-07-05T08:59:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02267v2","created_at":"2026-07-05T08:59:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02267","created_at":"2026-07-05T08:59:09Z"},{"alias_kind":"pith_short_12","alias_value":"CVUXKR5NBQQD","created_at":"2026-07-05T08:59:09Z"},{"alias_kind":"pith_short_16","alias_value":"CVUXKR5NBQQDRHPA","created_at":"2026-07-05T08:59:09Z"},{"alias_kind":"pith_short_8","alias_value":"CVUXKR5N","created_at":"2026-07-05T08:59:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CVUXKR5NBQQDRHPAXCYJAVTYAI","target":"record","payload":{"canonical_record":{"source":{"id":"2405.02267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-03T17:34:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0f0fe4033ebce03f803b226e81844b111b78cdd7a17fac9284a1fd80bb291cea","abstract_canon_sha256":"192a5a847435139c189d52c44b0357bb1064db342051b190a9e07d81e583352c"},"schema_version":"1.0"},"canonical_sha256":"15697547ad0c20389de0b8b0905678022ee90c35ba58f6f0db839ca217cd32a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:09.269946Z","signature_b64":"lhXqDqR1uA5MAaKRgNv7POy/vyDp8Egs0aS2YC/ABZst7oyJxqhn9w+5IzvqPgVsft2eBwnkKBqhxEb930qlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15697547ad0c20389de0b8b0905678022ee90c35ba58f6f0db839ca217cd32a6","last_reissued_at":"2026-07-05T08:59:09.269444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:09.269444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.02267","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":"2026-07-05T08:59:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ch1W4tzX4S086u6+WFX7psvFK8TYVmO15hnZdNCmG6fMqb5GanHN5ijpmsHPcHi9Lc+1wOe/qMr4OR++GKtxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:43:20.608976Z"},"content_sha256":"d44ea7f174e5468308e6cc24ab2254ef2cb2e2b92b463a2d1e0b20ed1c67bd4d","schema_version":"1.0","event_id":"sha256:d44ea7f174e5468308e6cc24ab2254ef2cb2e2b92b463a2d1e0b20ed1c67bd4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CVUXKR5NBQQDRHPAXCYJAVTYAI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structural Pruning of Pre-trained Language Models via Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Aaron Klein, Cedric Archambeau, Jacek Golebiowski, Valerio Perrone, Xingchen Ma","submitted_at":"2024-05-03T17:34:57Z","abstract_excerpt":"Pre-trained language models (PLM), for example BERT or RoBERTa, mark the state-of-the-art for natural language understanding task when fine-tuned on labeled data. However, their large size poses challenges in deploying them for inference in real-world applications, due to significant GPU memory requirements and high inference latency. This paper explores neural architecture search (NAS) for structural pruning to find sub-parts of the fine-tuned network that optimally trade-off efficiency, for example in terms of model size or latency, and generalization performance. We also show how we can uti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02267","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/2405.02267/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":"2026-07-05T08:59:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8bxrgzKCprfCfWP8kMs17smF3KIkTzx11R0gkwB84JC/u5nEO50ClQdI96OydBEV4TzzYU7mA/bY5wyF9AjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:43:20.609733Z"},"content_sha256":"659cf2e3e0c2a5bb3257ddb1bcfa454366669fce2747f216d82be500e1a9e3ba","schema_version":"1.0","event_id":"sha256:659cf2e3e0c2a5bb3257ddb1bcfa454366669fce2747f216d82be500e1a9e3ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CVUXKR5NBQQDRHPAXCYJAVTYAI/bundle.json","state_url":"https://pith.science/pith/CVUXKR5NBQQDRHPAXCYJAVTYAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CVUXKR5NBQQDRHPAXCYJAVTYAI/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":"2026-08-07T20:43:20Z","links":{"resolver":"https://pith.science/pith/CVUXKR5NBQQDRHPAXCYJAVTYAI","bundle":"https://pith.science/pith/CVUXKR5NBQQDRHPAXCYJAVTYAI/bundle.json","state":"https://pith.science/pith/CVUXKR5NBQQDRHPAXCYJAVTYAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CVUXKR5NBQQDRHPAXCYJAVTYAI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CVUXKR5NBQQDRHPAXCYJAVTYAI","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":"192a5a847435139c189d52c44b0357bb1064db342051b190a9e07d81e583352c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-03T17:34:57Z","title_canon_sha256":"0f0fe4033ebce03f803b226e81844b111b78cdd7a17fac9284a1fd80bb291cea"},"schema_version":"1.0","source":{"id":"2405.02267","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02267","created_at":"2026-07-05T08:59:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02267v2","created_at":"2026-07-05T08:59:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02267","created_at":"2026-07-05T08:59:09Z"},{"alias_kind":"pith_short_12","alias_value":"CVUXKR5NBQQD","created_at":"2026-07-05T08:59:09Z"},{"alias_kind":"pith_short_16","alias_value":"CVUXKR5NBQQDRHPA","created_at":"2026-07-05T08:59:09Z"},{"alias_kind":"pith_short_8","alias_value":"CVUXKR5N","created_at":"2026-07-05T08:59:09Z"}],"graph_snapshots":[{"event_id":"sha256:659cf2e3e0c2a5bb3257ddb1bcfa454366669fce2747f216d82be500e1a9e3ba","target":"graph","created_at":"2026-07-05T08:59:09Z","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/2405.02267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models (PLM), for example BERT or RoBERTa, mark the state-of-the-art for natural language understanding task when fine-tuned on labeled data. However, their large size poses challenges in deploying them for inference in real-world applications, due to significant GPU memory requirements and high inference latency. This paper explores neural architecture search (NAS) for structural pruning to find sub-parts of the fine-tuned network that optimally trade-off efficiency, for example in terms of model size or latency, and generalization performance. We also show how we can uti","authors_text":"Aaron Klein, Cedric Archambeau, Jacek Golebiowski, Valerio Perrone, Xingchen Ma","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-03T17:34:57Z","title":"Structural Pruning of Pre-trained Language Models via Neural Architecture Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02267","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:d44ea7f174e5468308e6cc24ab2254ef2cb2e2b92b463a2d1e0b20ed1c67bd4d","target":"record","created_at":"2026-07-05T08:59:09Z","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":"192a5a847435139c189d52c44b0357bb1064db342051b190a9e07d81e583352c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-03T17:34:57Z","title_canon_sha256":"0f0fe4033ebce03f803b226e81844b111b78cdd7a17fac9284a1fd80bb291cea"},"schema_version":"1.0","source":{"id":"2405.02267","kind":"arxiv","version":2}},"canonical_sha256":"15697547ad0c20389de0b8b0905678022ee90c35ba58f6f0db839ca217cd32a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15697547ad0c20389de0b8b0905678022ee90c35ba58f6f0db839ca217cd32a6","first_computed_at":"2026-07-05T08:59:09.269444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:09.269444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lhXqDqR1uA5MAaKRgNv7POy/vyDp8Egs0aS2YC/ABZst7oyJxqhn9w+5IzvqPgVsft2eBwnkKBqhxEb930qlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:09.269946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02267","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d44ea7f174e5468308e6cc24ab2254ef2cb2e2b92b463a2d1e0b20ed1c67bd4d","sha256:659cf2e3e0c2a5bb3257ddb1bcfa454366669fce2747f216d82be500e1a9e3ba"],"state_sha256":"b2d92c412f87111040be1b53f2c2bd054391692b4de2c6b023ad61da5c655687"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wuTlrMbIU2ydntAdNYIYfdaALAvxAvywTUCWOfAe1WmeRSiskkkVxtPrBELXDs2wt9Ot7hYEqmkGxzaNhaKNBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:43:20.615417Z","bundle_sha256":"5f55d69a98676d7aeb1e6cf8de1723fc2abfa19bfe3844f09c3fcbfdc482cbba"}}