{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4Z7ABGPPEWCNOGVN2L32BDLWRW","short_pith_number":"pith:4Z7ABGPP","schema_version":"1.0","canonical_sha256":"e67e0099ef2584d71aadd2f7a08d768d826f520d3e45ddbce830819ed5275c87","source":{"kind":"arxiv","id":"2106.06984","version":1},"attestation_state":"computed","paper":{"title":"A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ruihao Gong, Shi Gu, Shikuang Deng, Xin Dong, Yuhang Li","submitted_at":"2021-06-13T13:20:12Z","abstract_excerpt":"Spiking Neural Network (SNN) has been recognized as one of the next generation of neural networks. Conventionally, SNN can be converted from a pre-trained ANN by only replacing the ReLU activation to spike activation while keeping the parameters intact. Perhaps surprisingly, in this work we show that a proper way to calibrate the parameters during the conversion of ANN to SNN can bring significant improvements. We introduce SNN Calibration, a cheap but extraordinarily effective method by leveraging the knowledge within a pre-trained Artificial Neural Network (ANN). Starting by analyzing the co"},"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":"2106.06984","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-13T13:20:12Z","cross_cats_sorted":[],"title_canon_sha256":"39c6e18fc692b2860ef291cfde3f44d3d142df9f06d3bffd5ffd234ba9d2fa23","abstract_canon_sha256":"e18820ff89230b1176b083a362a0ab311edfc7713b9ac58be7c854694fdd7573"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:43.222151Z","signature_b64":"n25Zy+cIx9QBCxsCYy2/StMbU4Oy6/c/xsH/fNwbJw9ZCdUcV0nNhPRB9WiOqh+FVhewbttT8awqGlKFuf52BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e67e0099ef2584d71aadd2f7a08d768d826f520d3e45ddbce830819ed5275c87","last_reissued_at":"2026-07-05T02:48:43.221578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:43.221578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ruihao Gong, Shi Gu, Shikuang Deng, Xin Dong, Yuhang Li","submitted_at":"2021-06-13T13:20:12Z","abstract_excerpt":"Spiking Neural Network (SNN) has been recognized as one of the next generation of neural networks. Conventionally, SNN can be converted from a pre-trained ANN by only replacing the ReLU activation to spike activation while keeping the parameters intact. Perhaps surprisingly, in this work we show that a proper way to calibrate the parameters during the conversion of ANN to SNN can bring significant improvements. We introduce SNN Calibration, a cheap but extraordinarily effective method by leveraging the knowledge within a pre-trained Artificial Neural Network (ANN). Starting by analyzing the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06984","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/2106.06984/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":"2106.06984","created_at":"2026-07-05T02:48:43.221640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06984v1","created_at":"2026-07-05T02:48:43.221640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06984","created_at":"2026-07-05T02:48:43.221640+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Z7ABGPPEWCN","created_at":"2026-07-05T02:48:43.221640+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Z7ABGPPEWCNOGVN","created_at":"2026-07-05T02:48:43.221640+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Z7ABGPP","created_at":"2026-07-05T02:48:43.221640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.16552","citing_title":"QKFormer: Hierarchical Spiking Transformer using Q-K Attention","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Z7ABGPPEWCNOGVN2L32BDLWRW","json":"https://pith.science/pith/4Z7ABGPPEWCNOGVN2L32BDLWRW.json","graph_json":"https://pith.science/api/pith-number/4Z7ABGPPEWCNOGVN2L32BDLWRW/graph.json","events_json":"https://pith.science/api/pith-number/4Z7ABGPPEWCNOGVN2L32BDLWRW/events.json","paper":"https://pith.science/paper/4Z7ABGPP"},"agent_actions":{"view_html":"https://pith.science/pith/4Z7ABGPPEWCNOGVN2L32BDLWRW","download_json":"https://pith.science/pith/4Z7ABGPPEWCNOGVN2L32BDLWRW.json","view_paper":"https://pith.science/paper/4Z7ABGPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06984&json=true","fetch_graph":"https://pith.science/api/pith-number/4Z7ABGPPEWCNOGVN2L32BDLWRW/graph.json","fetch_events":"https://pith.science/api/pith-number/4Z7ABGPPEWCNOGVN2L32BDLWRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Z7ABGPPEWCNOGVN2L32BDLWRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Z7ABGPPEWCNOGVN2L32BDLWRW/action/storage_attestation","attest_author":"https://pith.science/pith/4Z7ABGPPEWCNOGVN2L32BDLWRW/action/author_attestation","sign_citation":"https://pith.science/pith/4Z7ABGPPEWCNOGVN2L32BDLWRW/action/citation_signature","submit_replication":"https://pith.science/pith/4Z7ABGPPEWCNOGVN2L32BDLWRW/action/replication_record"}},"created_at":"2026-07-05T02:48:43.221640+00:00","updated_at":"2026-07-05T02:48:43.221640+00:00"}