{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5D334NPEHHOZKOH34UGMEGNC66","short_pith_number":"pith:5D334NPE","canonical_record":{"source":{"id":"2605.12732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2026-05-12T20:34:25Z","cross_cats_sorted":[],"title_canon_sha256":"a5f7b5f594506491b3cbd6219f9f2c9cec0e6255dfe2f888ba5018159a54ac37","abstract_canon_sha256":"e06a5297389ee85fe2703016c423cffda78852c197728493a557f08538f484d9"},"schema_version":"1.0"},"canonical_sha256":"e8f7be35e439dd9538fbe50cc219a2f78a0e99636dd17a7ab7470dda841d1499","source":{"kind":"arxiv","id":"2605.12732","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12732","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12732v1","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12732","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"5D334NPEHHOZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"5D334NPEHHOZKOH3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"5D334NPE","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5D334NPEHHOZKOH34UGMEGNC66","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2026-05-12T20:34:25Z","cross_cats_sorted":[],"title_canon_sha256":"a5f7b5f594506491b3cbd6219f9f2c9cec0e6255dfe2f888ba5018159a54ac37","abstract_canon_sha256":"e06a5297389ee85fe2703016c423cffda78852c197728493a557f08538f484d9"},"schema_version":"1.0"},"canonical_sha256":"e8f7be35e439dd9538fbe50cc219a2f78a0e99636dd17a7ab7470dda841d1499","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:49.230566Z","signature_b64":"JUatS6Ic0QQU66UlKwoAHE81bxJXao4wdMxSCIEgnkoItLBQg2Ix4prdgdOt9TPAshOw1PMc0efmPheglvGvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8f7be35e439dd9538fbe50cc219a2f78a0e99636dd17a7ab7470dda841d1499","last_reissued_at":"2026-05-18T03:09:49.229738Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:49.229738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12732","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":"2026-05-18T03:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tah/DlsAjixZk3cEpRlqFCSxAvpNFDEkDxMlQPt/nm6O/LbwRSPsQG0c/dmG37gVUwxSpmE8TnF4niuHC6NKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:16:13.280328Z"},"content_sha256":"ee7013a10c3963a049d0fb27a1595ecec17966c0bae4fe7a7382ca08ed893ae3","schema_version":"1.0","event_id":"sha256:ee7013a10c3963a049d0fb27a1595ecec17966c0bae4fe7a7382ca08ed893ae3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5D334NPEHHOZKOH34UGMEGNC66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predictive Coding Light+: learning to predict visual sequences with spike timing-dependent plasticity and synaptic delays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Spiking neural networks learn recurrent excitatory connections with delays to maintain recent past and predict future visual sequences.","cross_cats":[],"primary_cat":"q-bio.NC","authors_text":"Antony W. N'dri, C\\'eline Teuli\\`ere, Jochen Triesch, Thomas Barbier","submitted_at":"2026-05-12T20:34:25Z","abstract_excerpt":"The ability to predict the future is of great value for biological and artificial cognitive systems alike. However, successfully predicting the future typically requires maintaining a memory of the recent past. It is currently unclear how biological or artificial spiking neural networks can learn to maintain past sensory information to help predict the future. Here we propose Predictive Coding Light+ (PCL+), a spiking neural network architecture for unsupervised sequence processing that learns recurrent excitatory connections with delays to enable short-term retention of information. We show t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our work shows how spiking neural networks can learn recurrent excitatory connections with delays to maintain a record of the recent past and successfully predict the future.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That spike timing-dependent plasticity applied to recurrent connections with delays is sufficient to learn and maintain the necessary short-term memory traces for accurate future prediction without additional mechanisms or labeled supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PCL+ spiking network learns recurrent connections with delays via STDP to retain recent visual inputs and predict future ones, reproducing cortical sequence learning and filling missing data in gesture recognition.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Spiking neural networks learn recurrent excitatory connections with delays to maintain recent past and predict future visual sequences.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a4eafe336bb497539b5b2fd8a567d1f3b753a53379a7af7b584fba7be989ca3b"},"source":{"id":"2605.12732","kind":"arxiv","version":1},"verdict":{"id":"caad092c-262c-463e-92d6-3d1cb902ccef","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:41:44.713269Z","strongest_claim":"our work shows how spiking neural networks can learn recurrent excitatory connections with delays to maintain a record of the recent past and successfully predict the future.","one_line_summary":"PCL+ spiking network learns recurrent connections with delays via STDP to retain recent visual inputs and predict future ones, reproducing cortical sequence learning and filling missing data in gesture recognition.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That spike timing-dependent plasticity applied to recurrent connections with delays is sufficient to learn and maintain the necessary short-term memory traces for accurate future prediction without additional mechanisms or labeled supervision.","pith_extraction_headline":"Spiking neural networks learn recurrent excitatory connections with delays to maintain recent past and predict future visual sequences."},"references":{"count":42,"sample":[{"doi":"","year":2017,"title":"A low power, fully event-based ges- ture recognition system","work_id":"fc904603-2b7a-421d-b157-10eed164aace","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Working models of working memory","work_id":"48390593-afbd-4e73-a0db-7909d38262fd","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Spike timing-based unsupervised learning of orienta- tion, disparity, and motion representations in a spiking neural network","work_id":"dc77248c-103d-4a09-95f1-ea21cf67f759","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"PIX2NVS: Parame- terized conversion of pixel-domain video frames to neu- romorphic vision streams","work_id":"a5ac6313-e6b6-41ef-a336-70baf26b2177","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2003,"title":"Persistent ac- tivity in the prefrontal cortex during working memory","work_id":"e3fe3386-1445-431a-ac06-f71dd1545fcf","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":42,"snapshot_sha256":"c92f486107979c9565712281a6f677079091572de8d8952e8e24445571595f54","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":"caad092c-262c-463e-92d6-3d1cb902ccef"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7pgswy+DBZoWStznIN4rss5HZ6Mt7s623I0MVo5h+NsqetBhQJZ9n4Njx7MuXQFVdjoBYg7Zqs2xfMeHiGzNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:16:13.281300Z"},"content_sha256":"cacfe11d9014f58de8ed781a7dcfc35ce9ee5ad983319e281eec68e9399d91b7","schema_version":"1.0","event_id":"sha256:cacfe11d9014f58de8ed781a7dcfc35ce9ee5ad983319e281eec68e9399d91b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5D334NPEHHOZKOH34UGMEGNC66/bundle.json","state_url":"https://pith.science/pith/5D334NPEHHOZKOH34UGMEGNC66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5D334NPEHHOZKOH34UGMEGNC66/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":"2026-05-30T15:16:13Z","links":{"resolver":"https://pith.science/pith/5D334NPEHHOZKOH34UGMEGNC66","bundle":"https://pith.science/pith/5D334NPEHHOZKOH34UGMEGNC66/bundle.json","state":"https://pith.science/pith/5D334NPEHHOZKOH34UGMEGNC66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5D334NPEHHOZKOH34UGMEGNC66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5D334NPEHHOZKOH34UGMEGNC66","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":"e06a5297389ee85fe2703016c423cffda78852c197728493a557f08538f484d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2026-05-12T20:34:25Z","title_canon_sha256":"a5f7b5f594506491b3cbd6219f9f2c9cec0e6255dfe2f888ba5018159a54ac37"},"schema_version":"1.0","source":{"id":"2605.12732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12732","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12732v1","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12732","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"5D334NPEHHOZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"5D334NPEHHOZKOH3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"5D334NPE","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:cacfe11d9014f58de8ed781a7dcfc35ce9ee5ad983319e281eec68e9399d91b7","target":"graph","created_at":"2026-05-18T03:09:49Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"our work shows how spiking neural networks can learn recurrent excitatory connections with delays to maintain a record of the recent past and successfully predict the future."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That spike timing-dependent plasticity applied to recurrent connections with delays is sufficient to learn and maintain the necessary short-term memory traces for accurate future prediction without additional mechanisms or labeled supervision."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PCL+ spiking network learns recurrent connections with delays via STDP to retain recent visual inputs and predict future ones, reproducing cortical sequence learning and filling missing data in gesture recognition."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Spiking neural networks learn recurrent excitatory connections with delays to maintain recent past and predict future visual sequences."}],"snapshot_sha256":"a4eafe336bb497539b5b2fd8a567d1f3b753a53379a7af7b584fba7be989ca3b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The ability to predict the future is of great value for biological and artificial cognitive systems alike. However, successfully predicting the future typically requires maintaining a memory of the recent past. It is currently unclear how biological or artificial spiking neural networks can learn to maintain past sensory information to help predict the future. Here we propose Predictive Coding Light+ (PCL+), a spiking neural network architecture for unsupervised sequence processing that learns recurrent excitatory connections with delays to enable short-term retention of information. We show t","authors_text":"Antony W. N'dri, C\\'eline Teuli\\`ere, Jochen Triesch, Thomas Barbier","cross_cats":[],"headline":"Spiking neural networks learn recurrent excitatory connections with delays to maintain recent past and predict future visual sequences.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2026-05-12T20:34:25Z","title":"Predictive Coding Light+: learning to predict visual sequences with spike timing-dependent plasticity and synaptic delays"},"references":{"count":42,"internal_anchors":0,"resolved_work":42,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A low power, fully event-based ges- ture recognition system","work_id":"fc904603-2b7a-421d-b157-10eed164aace","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Working models of working memory","work_id":"48390593-afbd-4e73-a0db-7909d38262fd","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Spike timing-based unsupervised learning of orienta- tion, disparity, and motion representations in a spiking neural network","work_id":"dc77248c-103d-4a09-95f1-ea21cf67f759","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"PIX2NVS: Parame- terized conversion of pixel-domain video frames to neu- romorphic vision streams","work_id":"a5ac6313-e6b6-41ef-a336-70baf26b2177","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Persistent ac- tivity in the prefrontal cortex during working memory","work_id":"e3fe3386-1445-431a-ac06-f71dd1545fcf","year":2003}],"snapshot_sha256":"c92f486107979c9565712281a6f677079091572de8d8952e8e24445571595f54"},"source":{"id":"2605.12732","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:41:44.713269Z","id":"caad092c-262c-463e-92d6-3d1cb902ccef","model_set":{"reader":"grok-4.3"},"one_line_summary":"PCL+ spiking network learns recurrent connections with delays via STDP to retain recent visual inputs and predict future ones, reproducing cortical sequence learning and filling missing data in gesture recognition.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Spiking neural networks learn recurrent excitatory connections with delays to maintain recent past and predict future visual sequences.","strongest_claim":"our work shows how spiking neural networks can learn recurrent excitatory connections with delays to maintain a record of the recent past and successfully predict the future.","weakest_assumption":"That spike timing-dependent plasticity applied to recurrent connections with delays is sufficient to learn and maintain the necessary short-term memory traces for accurate future prediction without additional mechanisms or labeled supervision."}},"verdict_id":"caad092c-262c-463e-92d6-3d1cb902ccef"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ee7013a10c3963a049d0fb27a1595ecec17966c0bae4fe7a7382ca08ed893ae3","target":"record","created_at":"2026-05-18T03:09:49Z","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":"e06a5297389ee85fe2703016c423cffda78852c197728493a557f08538f484d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2026-05-12T20:34:25Z","title_canon_sha256":"a5f7b5f594506491b3cbd6219f9f2c9cec0e6255dfe2f888ba5018159a54ac37"},"schema_version":"1.0","source":{"id":"2605.12732","kind":"arxiv","version":1}},"canonical_sha256":"e8f7be35e439dd9538fbe50cc219a2f78a0e99636dd17a7ab7470dda841d1499","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8f7be35e439dd9538fbe50cc219a2f78a0e99636dd17a7ab7470dda841d1499","first_computed_at":"2026-05-18T03:09:49.229738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:49.229738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JUatS6Ic0QQU66UlKwoAHE81bxJXao4wdMxSCIEgnkoItLBQg2Ix4prdgdOt9TPAshOw1PMc0efmPheglvGvDw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:49.230566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee7013a10c3963a049d0fb27a1595ecec17966c0bae4fe7a7382ca08ed893ae3","sha256:cacfe11d9014f58de8ed781a7dcfc35ce9ee5ad983319e281eec68e9399d91b7"],"state_sha256":"6bfe4dd29057e19a489c31a6b1069b4c1e10e46f684450cff54d3c4395e27bb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CKMOFztraXa6BP92wnoB2hQ+16LQBCV1qKvaWcJC8cFmi0rViiEvVw550xhEYFueevaISF6+tUyiH8/FPJKHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T15:16:13.285625Z","bundle_sha256":"85ff14873e876c1ef6dff5363c7cb241fba417ca42f004541990e2b44ded6f7c"}}