{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QKAJXZ5X4W4FZ6GBD4U45XVIKJ","short_pith_number":"pith:QKAJXZ5X","canonical_record":{"source":{"id":"2509.06636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-09-08T12:54:30Z","cross_cats_sorted":[],"title_canon_sha256":"fdd08e1476555ca2a8ccfad3672c14f4b5b1eed66b451fd09e24af79b69f2e6d","abstract_canon_sha256":"2f604b023224b46079262a3d67f5468e48f9b316b12330ab34eb9a0ec94e4465"},"schema_version":"1.0"},"canonical_sha256":"82809be7b7e5b85cf8c11f29cedea8525da09d8636b0f6119d954ac1de611d23","source":{"kind":"arxiv","id":"2509.06636","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06636","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06636v1","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06636","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"QKAJXZ5X4W4F","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"QKAJXZ5X4W4FZ6GB","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"QKAJXZ5X","created_at":"2026-07-05T12:06:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QKAJXZ5X4W4FZ6GBD4U45XVIKJ","target":"record","payload":{"canonical_record":{"source":{"id":"2509.06636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-09-08T12:54:30Z","cross_cats_sorted":[],"title_canon_sha256":"fdd08e1476555ca2a8ccfad3672c14f4b5b1eed66b451fd09e24af79b69f2e6d","abstract_canon_sha256":"2f604b023224b46079262a3d67f5468e48f9b316b12330ab34eb9a0ec94e4465"},"schema_version":"1.0"},"canonical_sha256":"82809be7b7e5b85cf8c11f29cedea8525da09d8636b0f6119d954ac1de611d23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:39.527755Z","signature_b64":"ecP3X9QUH32g4RivZQ0NSu3BVbSGZK2Y5hubaWi3rvsgPCasBwqzmW6dtpYq6zlWRh0jdibXwXV3tCWvrDjUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82809be7b7e5b85cf8c11f29cedea8525da09d8636b0f6119d954ac1de611d23","last_reissued_at":"2026-07-05T12:06:39.527286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:39.527286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.06636","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rKnSODtqf1d5meOKu0lp4IhcIw+z0+rFwvrtvRz9fPIlGyMwVPdBBnyCiyWC6QS43r+v6C6y8TvnPItTGZ3bCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:21:56.519075Z"},"content_sha256":"eb4e50bedb58f617abaeb4c6ac04fa9b66a2cd119dcd89bd316d9a3caf94b563","schema_version":"1.0","event_id":"sha256:eb4e50bedb58f617abaeb4c6ac04fa9b66a2cd119dcd89bd316d9a3caf94b563"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QKAJXZ5X4W4FZ6GBD4U45XVIKJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Full Integer Arithmetic Online Training for Spiking Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Guangzhi Tang, Ismael Gomez","submitted_at":"2025-09-08T12:54:30Z","abstract_excerpt":"Spiking Neural Networks (SNNs) are promising for neuromorphic computing due to their biological plausibility and energy efficiency. However, training methods like Backpropagation Through Time (BPTT) and Real Time Recurrent Learning (RTRL) remain computationally intensive. This work introduces an integer-only, online training algorithm using a mixed-precision approach to improve efficiency and reduce memory usage by over 60%. The method replaces floating-point operations with integer arithmetic to enable hardware-friendly implementation. It generalizes to Convolutional and Recurrent SNNs (CSNNs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06636","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/2509.06636/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":"2026-07-05T12:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9GKPDzeE+NMCDW6uQZx9LrCcKQnF+yUPZjQWn9mDnnOEtewbBkg9qlWhMjDLmFi1WRe/ysQfAPlaU73JDuR7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:21:56.519846Z"},"content_sha256":"0e01a69aac2280a9378ba6358dd6d1ff1464fffffeec850a17bb9bd2a90e114a","schema_version":"1.0","event_id":"sha256:0e01a69aac2280a9378ba6358dd6d1ff1464fffffeec850a17bb9bd2a90e114a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QKAJXZ5X4W4FZ6GBD4U45XVIKJ/bundle.json","state_url":"https://pith.science/pith/QKAJXZ5X4W4FZ6GBD4U45XVIKJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QKAJXZ5X4W4FZ6GBD4U45XVIKJ/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":"2026-08-18T22:21:56Z","links":{"resolver":"https://pith.science/pith/QKAJXZ5X4W4FZ6GBD4U45XVIKJ","bundle":"https://pith.science/pith/QKAJXZ5X4W4FZ6GBD4U45XVIKJ/bundle.json","state":"https://pith.science/pith/QKAJXZ5X4W4FZ6GBD4U45XVIKJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QKAJXZ5X4W4FZ6GBD4U45XVIKJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QKAJXZ5X4W4FZ6GBD4U45XVIKJ","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":"2f604b023224b46079262a3d67f5468e48f9b316b12330ab34eb9a0ec94e4465","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-09-08T12:54:30Z","title_canon_sha256":"fdd08e1476555ca2a8ccfad3672c14f4b5b1eed66b451fd09e24af79b69f2e6d"},"schema_version":"1.0","source":{"id":"2509.06636","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06636","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06636v1","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06636","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"QKAJXZ5X4W4F","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"QKAJXZ5X4W4FZ6GB","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"QKAJXZ5X","created_at":"2026-07-05T12:06:39Z"}],"graph_snapshots":[{"event_id":"sha256:0e01a69aac2280a9378ba6358dd6d1ff1464fffffeec850a17bb9bd2a90e114a","target":"graph","created_at":"2026-07-05T12:06:39Z","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/2509.06636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spiking Neural Networks (SNNs) are promising for neuromorphic computing due to their biological plausibility and energy efficiency. However, training methods like Backpropagation Through Time (BPTT) and Real Time Recurrent Learning (RTRL) remain computationally intensive. This work introduces an integer-only, online training algorithm using a mixed-precision approach to improve efficiency and reduce memory usage by over 60%. The method replaces floating-point operations with integer arithmetic to enable hardware-friendly implementation. It generalizes to Convolutional and Recurrent SNNs (CSNNs","authors_text":"Guangzhi Tang, Ismael Gomez","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-09-08T12:54:30Z","title":"Full Integer Arithmetic Online Training for Spiking Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06636","kind":"arxiv","version":1},"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:eb4e50bedb58f617abaeb4c6ac04fa9b66a2cd119dcd89bd316d9a3caf94b563","target":"record","created_at":"2026-07-05T12:06:39Z","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":"2f604b023224b46079262a3d67f5468e48f9b316b12330ab34eb9a0ec94e4465","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-09-08T12:54:30Z","title_canon_sha256":"fdd08e1476555ca2a8ccfad3672c14f4b5b1eed66b451fd09e24af79b69f2e6d"},"schema_version":"1.0","source":{"id":"2509.06636","kind":"arxiv","version":1}},"canonical_sha256":"82809be7b7e5b85cf8c11f29cedea8525da09d8636b0f6119d954ac1de611d23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82809be7b7e5b85cf8c11f29cedea8525da09d8636b0f6119d954ac1de611d23","first_computed_at":"2026-07-05T12:06:39.527286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:39.527286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ecP3X9QUH32g4RivZQ0NSu3BVbSGZK2Y5hubaWi3rvsgPCasBwqzmW6dtpYq6zlWRh0jdibXwXV3tCWvrDjUAg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:39.527755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06636","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb4e50bedb58f617abaeb4c6ac04fa9b66a2cd119dcd89bd316d9a3caf94b563","sha256:0e01a69aac2280a9378ba6358dd6d1ff1464fffffeec850a17bb9bd2a90e114a"],"state_sha256":"2fd09965bb7c1f1c41ec13edc78feb55930a32ddef657b86fc4ca02bded78a7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ujxUrh5I0BabTFChQpprR8ouj7jeO9oFm9JylfBovCw1hErJiC5mUjGr/7DeU9nZuFWj6qqT/aMgvZ1ZvzzaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T22:21:56.527860Z","bundle_sha256":"f2c401d9a336ccd3606e5e5be15ae378653c729deb48d2b1500b6f448d9ec4f8"}}