{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7DIBYEVAQRS6YFC4B7BJ24NR3Y","short_pith_number":"pith:7DIBYEVA","schema_version":"1.0","canonical_sha256":"f8d01c12a08465ec145c0fc29d71b1de1c4534a31b9c4ad094434a472d80346b","source":{"kind":"arxiv","id":"2308.15122","version":4},"attestation_state":"computed","paper":{"title":"SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cenyuan Zhang, Changze Lv, Chenxi Gu, Jianhan Xu, Tianlong Li, Xiaoqing Zheng, Xuanjing Huang, Zixuan Ling","submitted_at":"2023-08-29T08:41:16Z","abstract_excerpt":"Spiking neural networks (SNNs) offer a promising avenue to implement deep neural networks in a more energy-efficient way. However, the network architectures of existing SNNs for language tasks are still simplistic and relatively shallow, and deep architectures have not been fully explored, resulting in a significant performance gap compared to mainstream transformer-based networks such as BERT. To this end, we improve a recently-proposed spiking Transformer (i.e., Spikformer) to make it possible to process language tasks and propose a two-stage knowledge distillation method for training it, wh"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.15122","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-29T08:41:16Z","cross_cats_sorted":[],"title_canon_sha256":"f323a4a1c0303075c3729f3f3adc22e771aaf7d01ffb15a61b62a00202eb6ffc","abstract_canon_sha256":"f5f89d68be270e5dc0c67614a7334c120cb477a1dfa5f431b376a28ce59491b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:44.675722Z","signature_b64":"0n+BsU06VpcE9Suyz8+CFa26eHz9RyD9rV3bnQwQFSiPnz6omvN8cLKzO+tR5NCx7ZhCJ8w9xRm7/elaUUehCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8d01c12a08465ec145c0fc29d71b1de1c4534a31b9c4ad094434a472d80346b","last_reissued_at":"2026-07-05T07:47:44.675147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:44.675147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cenyuan Zhang, Changze Lv, Chenxi Gu, Jianhan Xu, Tianlong Li, Xiaoqing Zheng, Xuanjing Huang, Zixuan Ling","submitted_at":"2023-08-29T08:41:16Z","abstract_excerpt":"Spiking neural networks (SNNs) offer a promising avenue to implement deep neural networks in a more energy-efficient way. However, the network architectures of existing SNNs for language tasks are still simplistic and relatively shallow, and deep architectures have not been fully explored, resulting in a significant performance gap compared to mainstream transformer-based networks such as BERT. To this end, we improve a recently-proposed spiking Transformer (i.e., Spikformer) to make it possible to process language tasks and propose a two-stage knowledge distillation method for training it, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15122","kind":"arxiv","version":4},"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/2308.15122/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.15122","created_at":"2026-07-05T07:47:44.675217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15122v4","created_at":"2026-07-05T07:47:44.675217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15122","created_at":"2026-07-05T07:47:44.675217+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DIBYEVAQRS6","created_at":"2026-07-05T07:47:44.675217+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DIBYEVAQRS6YFC4","created_at":"2026-07-05T07:47:44.675217+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DIBYEVA","created_at":"2026-07-05T07:47:44.675217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12059","citing_title":"Attention by Synchronization in Coupled Oscillator Networks","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23796","citing_title":"UniSpike: Accelerating Spiking Neural Networks on Neuromorphic Systems via Eliminating Address Redundancy","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17674","citing_title":"SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20289","citing_title":"Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04595","citing_title":"SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00679","citing_title":"QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13859","citing_title":"BiSpikCLM: A Spiking Language Model integrating Softmax-Free Spiking Attention and Spike-Aware Alignment Distillation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11321","citing_title":"Winner-Take-All Spiking Transformer for Language Modeling","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12365","citing_title":"Adaptive Spiking Neurons for Vision and Language Modeling","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DIBYEVAQRS6YFC4B7BJ24NR3Y","json":"https://pith.science/pith/7DIBYEVAQRS6YFC4B7BJ24NR3Y.json","graph_json":"https://pith.science/api/pith-number/7DIBYEVAQRS6YFC4B7BJ24NR3Y/graph.json","events_json":"https://pith.science/api/pith-number/7DIBYEVAQRS6YFC4B7BJ24NR3Y/events.json","paper":"https://pith.science/paper/7DIBYEVA"},"agent_actions":{"view_html":"https://pith.science/pith/7DIBYEVAQRS6YFC4B7BJ24NR3Y","download_json":"https://pith.science/pith/7DIBYEVAQRS6YFC4B7BJ24NR3Y.json","view_paper":"https://pith.science/paper/7DIBYEVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15122&json=true","fetch_graph":"https://pith.science/api/pith-number/7DIBYEVAQRS6YFC4B7BJ24NR3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/7DIBYEVAQRS6YFC4B7BJ24NR3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DIBYEVAQRS6YFC4B7BJ24NR3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DIBYEVAQRS6YFC4B7BJ24NR3Y/action/storage_attestation","attest_author":"https://pith.science/pith/7DIBYEVAQRS6YFC4B7BJ24NR3Y/action/author_attestation","sign_citation":"https://pith.science/pith/7DIBYEVAQRS6YFC4B7BJ24NR3Y/action/citation_signature","submit_replication":"https://pith.science/pith/7DIBYEVAQRS6YFC4B7BJ24NR3Y/action/replication_record"}},"created_at":"2026-07-05T07:47:44.675217+00:00","updated_at":"2026-07-05T07:47:44.675217+00:00"}