{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:P7UOF2LHZBCEGMBDWX2THMFWBI","short_pith_number":"pith:P7UOF2LH","schema_version":"1.0","canonical_sha256":"7fe8e2e967c844433023b5f533b0b60a3fc9376aba0f7a1ffd0d23966f521430","source":{"kind":"arxiv","id":"2201.11665","version":3},"attestation_state":"computed","paper":{"title":"Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Gabriel Kreiman, Giorgia Dellaferrera","submitted_at":"2022-01-27T17:12:05Z","abstract_excerpt":"Supervised learning in artificial neural networks typically relies on backpropagation, where the weights are updated based on the error-function gradients and sequentially propagated from the output layer to the input layer. Although this approach has proven effective in a wide domain of applications, it lacks biological plausibility in many regards, including the weight symmetry problem, the dependence of learning on non-local signals, the freezing of neural activity during error propagation, and the update locking problem. Alternative training schemes have been introduced, including sign sym"},"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":"2201.11665","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-01-27T17:12:05Z","cross_cats_sorted":[],"title_canon_sha256":"6fcdf621eb166bf67f2b42356f68a5aa9fee275815c6b71f7df213eb2e1000b5","abstract_canon_sha256":"f9089ee575fa4a9344fe07e5480a2a6e9fd044e16359b189d987e8275a7a17ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:59.059431Z","signature_b64":"LjNHvOIF4o+nkWQdq/wm21/wy2hCZpklq5H3ZmyaT0jHlB8KadMHJuWc+3cwSl0iDRVyRZDFgpQp5gW+NbT+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fe8e2e967c844433023b5f533b0b60a3fc9376aba0f7a1ffd0d23966f521430","last_reissued_at":"2026-07-05T06:16:59.059004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:59.059004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Gabriel Kreiman, Giorgia Dellaferrera","submitted_at":"2022-01-27T17:12:05Z","abstract_excerpt":"Supervised learning in artificial neural networks typically relies on backpropagation, where the weights are updated based on the error-function gradients and sequentially propagated from the output layer to the input layer. Although this approach has proven effective in a wide domain of applications, it lacks biological plausibility in many regards, including the weight symmetry problem, the dependence of learning on non-local signals, the freezing of neural activity during error propagation, and the update locking problem. Alternative training schemes have been introduced, including sign sym"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11665","kind":"arxiv","version":3},"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/2201.11665/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":"2201.11665","created_at":"2026-07-05T06:16:59.059058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11665v3","created_at":"2026-07-05T06:16:59.059058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11665","created_at":"2026-07-05T06:16:59.059058+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7UOF2LHZBCE","created_at":"2026-07-05T06:16:59.059058+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7UOF2LHZBCEGMBD","created_at":"2026-07-05T06:16:59.059058+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7UOF2LH","created_at":"2026-07-05T06:16:59.059058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06461","citing_title":"Energy-Efficient Supervised Learning with a Binary Stochastic Forward-Forward Algorithm","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7UOF2LHZBCEGMBDWX2THMFWBI","json":"https://pith.science/pith/P7UOF2LHZBCEGMBDWX2THMFWBI.json","graph_json":"https://pith.science/api/pith-number/P7UOF2LHZBCEGMBDWX2THMFWBI/graph.json","events_json":"https://pith.science/api/pith-number/P7UOF2LHZBCEGMBDWX2THMFWBI/events.json","paper":"https://pith.science/paper/P7UOF2LH"},"agent_actions":{"view_html":"https://pith.science/pith/P7UOF2LHZBCEGMBDWX2THMFWBI","download_json":"https://pith.science/pith/P7UOF2LHZBCEGMBDWX2THMFWBI.json","view_paper":"https://pith.science/paper/P7UOF2LH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11665&json=true","fetch_graph":"https://pith.science/api/pith-number/P7UOF2LHZBCEGMBDWX2THMFWBI/graph.json","fetch_events":"https://pith.science/api/pith-number/P7UOF2LHZBCEGMBDWX2THMFWBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7UOF2LHZBCEGMBDWX2THMFWBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7UOF2LHZBCEGMBDWX2THMFWBI/action/storage_attestation","attest_author":"https://pith.science/pith/P7UOF2LHZBCEGMBDWX2THMFWBI/action/author_attestation","sign_citation":"https://pith.science/pith/P7UOF2LHZBCEGMBDWX2THMFWBI/action/citation_signature","submit_replication":"https://pith.science/pith/P7UOF2LHZBCEGMBDWX2THMFWBI/action/replication_record"}},"created_at":"2026-07-05T06:16:59.059058+00:00","updated_at":"2026-07-05T06:16:59.059058+00:00"}