{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZQN7KISTWDAZX44SM7CJMZWCRC","short_pith_number":"pith:ZQN7KIST","canonical_record":{"source":{"id":"2605.18557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T15:37:28Z","cross_cats_sorted":["cs.NE","q-bio.NC"],"title_canon_sha256":"449b17cf5afa6e9ce59af839a84bc52ab0227aeef69d10e8a124beb020ad1d62","abstract_canon_sha256":"6512a879f480f1790816f1f9be117e4a607adc9367c7acab357374d35f8a99be"},"schema_version":"1.0"},"canonical_sha256":"cc1bf52253b0c19bf39267c49666c2888e7b958e6a0746f6b49babcff621b6f5","source":{"kind":"arxiv","id":"2605.18557","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18557","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18557v1","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18557","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZQN7KISTWDAZ","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZQN7KISTWDAZX44S","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZQN7KIST","created_at":"2026-05-20T00:06:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZQN7KISTWDAZX44SM7CJMZWCRC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T15:37:28Z","cross_cats_sorted":["cs.NE","q-bio.NC"],"title_canon_sha256":"449b17cf5afa6e9ce59af839a84bc52ab0227aeef69d10e8a124beb020ad1d62","abstract_canon_sha256":"6512a879f480f1790816f1f9be117e4a607adc9367c7acab357374d35f8a99be"},"schema_version":"1.0"},"canonical_sha256":"cc1bf52253b0c19bf39267c49666c2888e7b958e6a0746f6b49babcff621b6f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:07.616540Z","signature_b64":"SL67B4cBBG8JK6o9cTLxaTk0gKnIBzO+CX3DjfflaJA3EvreiwqzoJtv8GU2W/fOz43H9rdhgnuLik7YVKLpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc1bf52253b0c19bf39267c49666c2888e7b958e6a0746f6b49babcff621b6f5","last_reissued_at":"2026-05-20T00:06:07.615599Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:07.615599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18557","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":"2026-05-20T00:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4SPap2m97LSP890h4Sc7HedtK736ks/vlJLzG2QOVtHMNI9jd5DSCvFAQt3WMRgKKp1wnnQDNQIqunKKPbAmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:58:30.160824Z"},"content_sha256":"8f5f1734ea479f12ba92f5e283919a5999f2624bccbc08b3c8b6815dbab42d1d","schema_version":"1.0","event_id":"sha256:8f5f1734ea479f12ba92f5e283919a5999f2624bccbc08b3c8b6815dbab42d1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZQN7KISTWDAZX44SM7CJMZWCRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.NE","q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Ariane Delrocq, Guillaume Bellec, Wulfram Gerstner, Wu S. Zihan","submitted_at":"2026-05-18T15:37:28Z","abstract_excerpt":"The brain learns abstract representations of high-dimensional sensory input, but the plasticity rules that enable such learning are unknown. We study biologically plausible algorithms on the Random Hierarchy Model (RHM), an artificial dataset designed to investigate how deep neural networks learn the intrinsic hierarchical structure of high-dimensional data. We focus on two types of local learning rules that avoid both a long convergence time and the use of a symmetric error network. The first type uses direct feedback signals to approximate error propagation from the output layer. The second "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18557","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/2605.18557/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.372456Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"afcc3ff736743f51af51ad8ff9565834c03d4a14cc68345ebaa7a9eb9ffd08d6"},"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":"2026-05-20T00:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gs2aiEs9DpBc+9FMulbT15JypTCGljEXIMFrwWLdoagswkaD6k0Bpmyrcvx+9A+5EP+ATDAzuE0UFFuy/4WaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:58:30.161221Z"},"content_sha256":"7675b5cdc4e84bb1abbbcfdd05ca51bca7277aa5c958296e6bc7d5dc6b42ff6b","schema_version":"1.0","event_id":"sha256:7675b5cdc4e84bb1abbbcfdd05ca51bca7277aa5c958296e6bc7d5dc6b42ff6b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:ZQN7KISTWDAZX44SM7CJMZWCRC","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.1612.09057.arXiv:1612.09057) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Deep Learning and Hierarchal Generative Models. URL:http://arxiv.org/abs/1612.09057, doi:10.48550/arXiv.1612. 09057. arXiv:1612.09057 [cs]. Nøkland, A.,","arxiv_id":"2605.18557","detector":"doi_compliance","evidence":{"ref_index":13,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Deep Learning and Hierarchal Generative Models. URL:http://arxiv.org/abs/1612.09057, doi:10.48550/arXiv.1612. 09057. arXiv:1612.09057 [cs]. Nøkland, A.,","reconstructed_doi":"10.48550/arXiv.1612.09057.arXiv:1612.09057"},"severity":"advisory","ref_index":13,"audited_at":"2026-05-20T13:02:22.576656Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.1612.09057.arXiv:1612.09057","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"295728c40622cb898298c4cd670bfdd3706cd3bbca0d9701ae0d58f861415091","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":5150,"payload_sha256":"bd23631b641590efd844396353d2438e5cc7238ec5890671a835452f096d6337","signature_b64":"5f7xHFt9CudtM97OD9/f0vVBhURtsLnQWaAKi5qPcgILQuyjUxg4MwYU5CRFy54NQlaMg8eENlbteIJF4i8pCA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T13:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K+eSP8Z7LyLwPMfatILC7SAHK6bGp/uUTLuk4bv2gQu1IFRS46sTqlbdOTTDc5HI2W4Qh/UuImaqPtG81bu+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:58:30.162376Z"},"content_sha256":"8caffc7a4428f07c9660bb35aba6deb136316065bc4186def34a4a016756a847","schema_version":"1.0","event_id":"sha256:8caffc7a4428f07c9660bb35aba6deb136316065bc4186def34a4a016756a847"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQN7KISTWDAZX44SM7CJMZWCRC/bundle.json","state_url":"https://pith.science/pith/ZQN7KISTWDAZX44SM7CJMZWCRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQN7KISTWDAZX44SM7CJMZWCRC/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":"2026-05-21T09:58:30Z","links":{"resolver":"https://pith.science/pith/ZQN7KISTWDAZX44SM7CJMZWCRC","bundle":"https://pith.science/pith/ZQN7KISTWDAZX44SM7CJMZWCRC/bundle.json","state":"https://pith.science/pith/ZQN7KISTWDAZX44SM7CJMZWCRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQN7KISTWDAZX44SM7CJMZWCRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZQN7KISTWDAZX44SM7CJMZWCRC","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6512a879f480f1790816f1f9be117e4a607adc9367c7acab357374d35f8a99be","cross_cats_sorted":["cs.NE","q-bio.NC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T15:37:28Z","title_canon_sha256":"449b17cf5afa6e9ce59af839a84bc52ab0227aeef69d10e8a124beb020ad1d62"},"schema_version":"1.0","source":{"id":"2605.18557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18557","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18557v1","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18557","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZQN7KISTWDAZ","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZQN7KISTWDAZX44S","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZQN7KIST","created_at":"2026-05-20T00:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:7675b5cdc4e84bb1abbbcfdd05ca51bca7277aa5c958296e6bc7d5dc6b42ff6b","target":"graph","created_at":"2026-05-20T00:06:07Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.372456Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18557/integrity.json","findings":[],"snapshot_sha256":"afcc3ff736743f51af51ad8ff9565834c03d4a14cc68345ebaa7a9eb9ffd08d6","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The brain learns abstract representations of high-dimensional sensory input, but the plasticity rules that enable such learning are unknown. We study biologically plausible algorithms on the Random Hierarchy Model (RHM), an artificial dataset designed to investigate how deep neural networks learn the intrinsic hierarchical structure of high-dimensional data. We focus on two types of local learning rules that avoid both a long convergence time and the use of a symmetric error network. The first type uses direct feedback signals to approximate error propagation from the output layer. The second ","authors_text":"Ariane Delrocq, Guillaume Bellec, Wulfram Gerstner, Wu S. Zihan","cross_cats":["cs.NE","q-bio.NC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T15:37:28Z","title":"Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18557","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":"sha256:8f5f1734ea479f12ba92f5e283919a5999f2624bccbc08b3c8b6815dbab42d1d","target":"record","created_at":"2026-05-20T00:06:07Z","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":"6512a879f480f1790816f1f9be117e4a607adc9367c7acab357374d35f8a99be","cross_cats_sorted":["cs.NE","q-bio.NC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T15:37:28Z","title_canon_sha256":"449b17cf5afa6e9ce59af839a84bc52ab0227aeef69d10e8a124beb020ad1d62"},"schema_version":"1.0","source":{"id":"2605.18557","kind":"arxiv","version":1}},"canonical_sha256":"cc1bf52253b0c19bf39267c49666c2888e7b958e6a0746f6b49babcff621b6f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc1bf52253b0c19bf39267c49666c2888e7b958e6a0746f6b49babcff621b6f5","first_computed_at":"2026-05-20T00:06:07.615599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:07.615599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SL67B4cBBG8JK6o9cTLxaTk0gKnIBzO+CX3DjfflaJA3EvreiwqzoJtv8GU2W/fOz43H9rdhgnuLik7YVKLpBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:07.616540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f5f1734ea479f12ba92f5e283919a5999f2624bccbc08b3c8b6815dbab42d1d","sha256:7675b5cdc4e84bb1abbbcfdd05ca51bca7277aa5c958296e6bc7d5dc6b42ff6b","sha256:8caffc7a4428f07c9660bb35aba6deb136316065bc4186def34a4a016756a847"],"state_sha256":"2ae80371fe1e89d647309c43b934b9000a772b31e344ce4d7d7de55ba7ecb6b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0hheNBCMz/+jW4SZA544GVsc5TOd0+5didSEFaJZicC3tMFYMJaA28/Hl8P9HfZ6yrZ1BKnqKLk9/PetSd1TBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T09:58:30.164621Z","bundle_sha256":"308d613394126ba269983628c903d12461995bbf61c7616d8c97ae87516d3616"}}