{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EBMPAIH7MA4ST4CTZAUIRHBBXL","short_pith_number":"pith:EBMPAIH7","schema_version":"1.0","canonical_sha256":"2058f020ff603929f053c828889c21bae576101c3afe2016bd2c9f247055cea6","source":{"kind":"arxiv","id":"2205.10121","version":1},"attestation_state":"computed","paper":{"title":"Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Shi Gu, Shikuang Deng, Xin Dong, Yuhang Li","submitted_at":"2022-05-06T18:22:09Z","abstract_excerpt":"Spiking Neural Network (SNN), originating from the neural behavior in biology, has been recognized as one of the next-generation neural networks. Conventionally, SNNs can be obtained by converting from pre-trained Artificial Neural Networks (ANNs) by replacing the non-linear activation with spiking neurons without changing the parameters. In this work, we argue that simply copying and pasting the weights of ANN to SNN inevitably results in activation mismatch, especially for ANNs that are trained with batch normalization (BN) layers. To tackle the activation mismatch issue, we first provide a "},"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":"2205.10121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2022-05-06T18:22:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0cf037955684afb20cd4c047dcfeaffe3ccf0f3591ce4e0b1676cc60bfd897d1","abstract_canon_sha256":"a2e71e4c56a8b7c582338201901b5d75e73864a5e05efcdc58d62e736c283987"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:03.602567Z","signature_b64":"8EufmAmzUofv6opMsGTefzKPn62XGBkHT8J+C1jr4cYj5C8g/4Ym4OuqOMbld1Iw3YeG92ewe9AMXseQUQpXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2058f020ff603929f053c828889c21bae576101c3afe2016bd2c9f247055cea6","last_reissued_at":"2026-07-05T04:25:03.602085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:03.602085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Shi Gu, Shikuang Deng, Xin Dong, Yuhang Li","submitted_at":"2022-05-06T18:22:09Z","abstract_excerpt":"Spiking Neural Network (SNN), originating from the neural behavior in biology, has been recognized as one of the next-generation neural networks. Conventionally, SNNs can be obtained by converting from pre-trained Artificial Neural Networks (ANNs) by replacing the non-linear activation with spiking neurons without changing the parameters. In this work, we argue that simply copying and pasting the weights of ANN to SNN inevitably results in activation mismatch, especially for ANNs that are trained with batch normalization (BN) layers. To tackle the activation mismatch issue, we first provide a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10121","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/2205.10121/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":"2205.10121","created_at":"2026-07-05T04:25:03.602187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10121v1","created_at":"2026-07-05T04:25:03.602187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10121","created_at":"2026-07-05T04:25:03.602187+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBMPAIH7MA4S","created_at":"2026-07-05T04:25:03.602187+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBMPAIH7MA4ST4CT","created_at":"2026-07-05T04:25:03.602187+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBMPAIH7","created_at":"2026-07-05T04:25:03.602187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14520","citing_title":"Quantization Meets Spikes: Nearly Lossless Conversion at the First Timestep via Polarity Multi-Spike Mapping","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBMPAIH7MA4ST4CTZAUIRHBBXL","json":"https://pith.science/pith/EBMPAIH7MA4ST4CTZAUIRHBBXL.json","graph_json":"https://pith.science/api/pith-number/EBMPAIH7MA4ST4CTZAUIRHBBXL/graph.json","events_json":"https://pith.science/api/pith-number/EBMPAIH7MA4ST4CTZAUIRHBBXL/events.json","paper":"https://pith.science/paper/EBMPAIH7"},"agent_actions":{"view_html":"https://pith.science/pith/EBMPAIH7MA4ST4CTZAUIRHBBXL","download_json":"https://pith.science/pith/EBMPAIH7MA4ST4CTZAUIRHBBXL.json","view_paper":"https://pith.science/paper/EBMPAIH7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10121&json=true","fetch_graph":"https://pith.science/api/pith-number/EBMPAIH7MA4ST4CTZAUIRHBBXL/graph.json","fetch_events":"https://pith.science/api/pith-number/EBMPAIH7MA4ST4CTZAUIRHBBXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBMPAIH7MA4ST4CTZAUIRHBBXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBMPAIH7MA4ST4CTZAUIRHBBXL/action/storage_attestation","attest_author":"https://pith.science/pith/EBMPAIH7MA4ST4CTZAUIRHBBXL/action/author_attestation","sign_citation":"https://pith.science/pith/EBMPAIH7MA4ST4CTZAUIRHBBXL/action/citation_signature","submit_replication":"https://pith.science/pith/EBMPAIH7MA4ST4CTZAUIRHBBXL/action/replication_record"}},"created_at":"2026-07-05T04:25:03.602187+00:00","updated_at":"2026-07-05T04:25:03.602187+00:00"}