{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BLUT7JGUYUTRQ62V4PYEYP56NQ","short_pith_number":"pith:BLUT7JGU","schema_version":"1.0","canonical_sha256":"0ae93fa4d4c527187b55e3f04c3fbe6c3f86cf0fa2663adc6bdf0ee691752f3b","source":{"kind":"arxiv","id":"2605.18804","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Salar Beigzad, Vansh Verma","submitted_at":"2026-05-11T15:15:40Z","abstract_excerpt":"We propose Adaptive Multi-Scale Goodness Aggregation (AMSGA), a novel extension of the Forward-Forward (FF) algorithm designed to improve stability, robustness, and generalization in local-learning neural networks. AMSGA addresses several limitations of the original FF framework by introducing multi-scale goodness aggregation across local, intermediate, and global representations; adaptive curriculum-guided hard negative mining; layer-dependent adaptive thresholds; and a warm-up cosine annealing learning-rate schedule for improved optimization stability. Together, these modifications strengthe"},"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":"2605.18804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T15:15:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8736c063dc77bb4996274be525b07afdfd21870cc6d0864230d51a1f13449c9","abstract_canon_sha256":"fd4fd992859e0c2c8ba9e6b332aa5b9abcf9ec830aa2f04abee6922cd85b5da1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:23.350025Z","signature_b64":"NtN3r9E6fLjC4Crp8Jl/EzCUJ1dPNkclU+tDjO7GGP6rDlYvYMR9WJ5AjH7G+u5lAwdQCpYXnUcgCXUyn2kjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ae93fa4d4c527187b55e3f04c3fbe6c3f86cf0fa2663adc6bdf0ee691752f3b","last_reissued_at":"2026-05-20T00:06:23.349169Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:23.349169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Salar Beigzad, Vansh Verma","submitted_at":"2026-05-11T15:15:40Z","abstract_excerpt":"We propose Adaptive Multi-Scale Goodness Aggregation (AMSGA), a novel extension of the Forward-Forward (FF) algorithm designed to improve stability, robustness, and generalization in local-learning neural networks. AMSGA addresses several limitations of the original FF framework by introducing multi-scale goodness aggregation across local, intermediate, and global representations; adaptive curriculum-guided hard negative mining; layer-dependent adaptive thresholds; and a warm-up cosine annealing learning-rate schedule for improved optimization stability. Together, these modifications strengthe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18804","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/2605.18804/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":"2605.18804","created_at":"2026-05-20T00:06:23.349337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18804v1","created_at":"2026-05-20T00:06:23.349337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18804","created_at":"2026-05-20T00:06:23.349337+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLUT7JGUYUTR","created_at":"2026-05-20T00:06:23.349337+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLUT7JGUYUTRQ62V","created_at":"2026-05-20T00:06:23.349337+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLUT7JGU","created_at":"2026-05-20T00:06:23.349337+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/BLUT7JGUYUTRQ62V4PYEYP56NQ","json":"https://pith.science/pith/BLUT7JGUYUTRQ62V4PYEYP56NQ.json","graph_json":"https://pith.science/api/pith-number/BLUT7JGUYUTRQ62V4PYEYP56NQ/graph.json","events_json":"https://pith.science/api/pith-number/BLUT7JGUYUTRQ62V4PYEYP56NQ/events.json","paper":"https://pith.science/paper/BLUT7JGU"},"agent_actions":{"view_html":"https://pith.science/pith/BLUT7JGUYUTRQ62V4PYEYP56NQ","download_json":"https://pith.science/pith/BLUT7JGUYUTRQ62V4PYEYP56NQ.json","view_paper":"https://pith.science/paper/BLUT7JGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18804&json=true","fetch_graph":"https://pith.science/api/pith-number/BLUT7JGUYUTRQ62V4PYEYP56NQ/graph.json","fetch_events":"https://pith.science/api/pith-number/BLUT7JGUYUTRQ62V4PYEYP56NQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLUT7JGUYUTRQ62V4PYEYP56NQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLUT7JGUYUTRQ62V4PYEYP56NQ/action/storage_attestation","attest_author":"https://pith.science/pith/BLUT7JGUYUTRQ62V4PYEYP56NQ/action/author_attestation","sign_citation":"https://pith.science/pith/BLUT7JGUYUTRQ62V4PYEYP56NQ/action/citation_signature","submit_replication":"https://pith.science/pith/BLUT7JGUYUTRQ62V4PYEYP56NQ/action/replication_record"}},"created_at":"2026-05-20T00:06:23.349337+00:00","updated_at":"2026-05-20T00:06:23.349337+00:00"}