{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SAV25KUYI7VDJR7VEURBK2ADLL","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":"5fbfc3b3baf1ce1544e3d161b54de717a903d0e89293ca15f2224d62786f9004","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-22T13:20:14Z","title_canon_sha256":"91ba5cb864283a2b9b674ba978d9620e75f0440fbeaa2fc0a2dbc5a5db93e591"},"schema_version":"1.0","source":{"id":"2106.11740","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11740","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11740v2","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11740","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"SAV25KUYI7VD","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"SAV25KUYI7VDJR7V","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"SAV25KUY","created_at":"2026-07-05T02:52:17Z"}],"graph_snapshots":[{"event_id":"sha256:651444ec8e0778de6813e7592e1f1a7f4b52c441d9b22f6ad13117103e99ec35","target":"graph","created_at":"2026-07-05T02:52:17Z","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/2106.11740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern pre-trained language models are mostly built upon backbones stacking self-attention and feed-forward layers in an interleaved order. In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by exploiting layer variety from two aspects: the layer type set and the layer order. Specifically, besides the original self-attention and feed-forward layers, we introduce convolution into the layer type set, which is experimentally found beneficial to pre-trained models. Furthermore, beyond the original interleaved order, we explore more layer orders to discover m","authors_text":"Fei Chen, Jiashi Feng, Qibin Hou, Weihao Yu, Zihang Jiang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-22T13:20:14Z","title":"LV-BERT: Exploiting Layer Variety for BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11740","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":"sha256:387c0b976e4d040ea1c446685919c5d3298755feae89315d8ad48680873bb166","target":"record","created_at":"2026-07-05T02:52:17Z","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":"5fbfc3b3baf1ce1544e3d161b54de717a903d0e89293ca15f2224d62786f9004","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-22T13:20:14Z","title_canon_sha256":"91ba5cb864283a2b9b674ba978d9620e75f0440fbeaa2fc0a2dbc5a5db93e591"},"schema_version":"1.0","source":{"id":"2106.11740","kind":"arxiv","version":2}},"canonical_sha256":"902baeaa9847ea34c7f525221568035adaaf6ef0bdd8460eb0b7d3d5f69da01c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"902baeaa9847ea34c7f525221568035adaaf6ef0bdd8460eb0b7d3d5f69da01c","first_computed_at":"2026-07-05T02:52:17.015154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:17.015154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9VFF553+DdrvT7d+gp1I0eaQAbDrhe9/0js3hkeyWyQQuO/+k8O3SFzOXCIi4pwpkmOByoI7aLMUn5bIkD4OCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:17.015575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.11740","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:387c0b976e4d040ea1c446685919c5d3298755feae89315d8ad48680873bb166","sha256:651444ec8e0778de6813e7592e1f1a7f4b52c441d9b22f6ad13117103e99ec35"],"state_sha256":"82e12fd90026646b33d106502650c0994251f0bdf968476ea3a30cd6990bfe1f"}