{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OOVPW54CROBRCREK74E4QE7I3U","short_pith_number":"pith:OOVPW54C","schema_version":"1.0","canonical_sha256":"73aafb77828b8311448aff09c813e8dd169dd670360563dcaeec883a9de0963d","source":{"kind":"arxiv","id":"2606.06539","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Yucheng Chen","submitted_at":"2026-06-04T04:01:01Z","abstract_excerpt":"Forward-Forward (FF) learning [Hinton, 2022] replaces backpropagation with strictly layer-local goodness updates. Recent FF-CNN work has narrowed the gap to BP on 32x32 benchmarks, raising the question of whether layer-local training is becoming a viable alternative at realistic scale. To probe this rigorously, we develop DTG-FF -- dynamic temperature goodness, decoupled normalization, and multi-layer fusion -- as an instrument that sets FF-family state of the art across nine real-data benchmarks (91.8% CIFAR-10 and the first FF baseline at ImageNet-100 224x224), and use it to audit how far la"},"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":"2606.06539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T04:01:01Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"513bfdd9ee3d44cc0ed72b4035feaae46f6de0351a09014577e218b5713a7105","abstract_canon_sha256":"7d88f65676105f72c73fb3401a4541b8cfb5ec3dd80269304f2e50e38944bd0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T00:03:41.622987Z","signature_b64":"OnX6IRGsNzSCZ5iDvWTa8qiWDiPZIC2E1EIqOWLVSRupsLbfrXC9pYNeTPOHTsIod26t7nNAicXzcPZfJlhzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73aafb77828b8311448aff09c813e8dd169dd670360563dcaeec883a9de0963d","last_reissued_at":"2026-06-08T00:03:41.622212Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T00:03:41.622212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Yucheng Chen","submitted_at":"2026-06-04T04:01:01Z","abstract_excerpt":"Forward-Forward (FF) learning [Hinton, 2022] replaces backpropagation with strictly layer-local goodness updates. Recent FF-CNN work has narrowed the gap to BP on 32x32 benchmarks, raising the question of whether layer-local training is becoming a viable alternative at realistic scale. To probe this rigorously, we develop DTG-FF -- dynamic temperature goodness, decoupled normalization, and multi-layer fusion -- as an instrument that sets FF-family state of the art across nine real-data benchmarks (91.8% CIFAR-10 and the first FF baseline at ImageNet-100 224x224), and use it to audit how far la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06539","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/2606.06539/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":"2606.06539","created_at":"2026-06-08T00:03:41.622336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06539v1","created_at":"2026-06-08T00:03:41.622336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06539","created_at":"2026-06-08T00:03:41.622336+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOVPW54CROBR","created_at":"2026-06-08T00:03:41.622336+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOVPW54CROBRCREK","created_at":"2026-06-08T00:03:41.622336+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOVPW54C","created_at":"2026-06-08T00:03:41.622336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOVPW54CROBRCREK74E4QE7I3U","json":"https://pith.science/pith/OOVPW54CROBRCREK74E4QE7I3U.json","graph_json":"https://pith.science/api/pith-number/OOVPW54CROBRCREK74E4QE7I3U/graph.json","events_json":"https://pith.science/api/pith-number/OOVPW54CROBRCREK74E4QE7I3U/events.json","paper":"https://pith.science/paper/OOVPW54C"},"agent_actions":{"view_html":"https://pith.science/pith/OOVPW54CROBRCREK74E4QE7I3U","download_json":"https://pith.science/pith/OOVPW54CROBRCREK74E4QE7I3U.json","view_paper":"https://pith.science/paper/OOVPW54C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06539&json=true","fetch_graph":"https://pith.science/api/pith-number/OOVPW54CROBRCREK74E4QE7I3U/graph.json","fetch_events":"https://pith.science/api/pith-number/OOVPW54CROBRCREK74E4QE7I3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOVPW54CROBRCREK74E4QE7I3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOVPW54CROBRCREK74E4QE7I3U/action/storage_attestation","attest_author":"https://pith.science/pith/OOVPW54CROBRCREK74E4QE7I3U/action/author_attestation","sign_citation":"https://pith.science/pith/OOVPW54CROBRCREK74E4QE7I3U/action/citation_signature","submit_replication":"https://pith.science/pith/OOVPW54CROBRCREK74E4QE7I3U/action/replication_record"}},"created_at":"2026-06-08T00:03:41.622336+00:00","updated_at":"2026-06-08T00:03:41.622336+00:00"}