{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F5ELXJQQCSW6FECS7BZPOBSYTE","short_pith_number":"pith:F5ELXJQQ","schema_version":"1.0","canonical_sha256":"2f48bba61014ade29052f872f70658990aae30d8c7e5cc46be1b3b4ea3ccde96","source":{"kind":"arxiv","id":"2507.06461","version":1},"attestation_state":"computed","paper":{"title":"Energy-Efficient Supervised Learning with a Binary Stochastic Forward-Forward Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Joseph G. Makin, Risi Jaiswal, Supriyo Datta","submitted_at":"2025-07-09T00:29:06Z","abstract_excerpt":"Reducing energy consumption has become a pressing need for modern machine learning, which has achieved many of its most impressive results by scaling to larger and more energy-consumptive neural networks. Unfortunately, the main algorithm for training such networks, backpropagation, poses significant challenges for custom hardware accelerators, due to both its serial dependencies and the memory footprint needed to store forward activations for the backward pass. Alternatives to backprop, although less effective, do exist; here the main computational bottleneck becomes matrix multiplication. In"},"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":"2507.06461","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T00:29:06Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"59dab094a8eb6c052698aad2bf8b0b296cd364ebe0c0c4e0ce6f51cb396cd096","abstract_canon_sha256":"9f81076f26a097e60c2de0655d40bfecd858be3290bc7c2135535cdc742688a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:16.356777Z","signature_b64":"WZBrSY6t+4uJbfHjyG3GGlCjW+NZuvTfyvd+0coh0NMNFRMcvgoth/LFxEjT0pLF6rbkCY3mPFiIA+E+PnIvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f48bba61014ade29052f872f70658990aae30d8c7e5cc46be1b3b4ea3ccde96","last_reissued_at":"2026-07-05T11:34:16.356393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:16.356393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-Efficient Supervised Learning with a Binary Stochastic Forward-Forward Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Joseph G. Makin, Risi Jaiswal, Supriyo Datta","submitted_at":"2025-07-09T00:29:06Z","abstract_excerpt":"Reducing energy consumption has become a pressing need for modern machine learning, which has achieved many of its most impressive results by scaling to larger and more energy-consumptive neural networks. Unfortunately, the main algorithm for training such networks, backpropagation, poses significant challenges for custom hardware accelerators, due to both its serial dependencies and the memory footprint needed to store forward activations for the backward pass. Alternatives to backprop, although less effective, do exist; here the main computational bottleneck becomes matrix multiplication. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06461","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/2507.06461/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":"2507.06461","created_at":"2026-07-05T11:34:16.356452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06461v1","created_at":"2026-07-05T11:34:16.356452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06461","created_at":"2026-07-05T11:34:16.356452+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5ELXJQQCSW6","created_at":"2026-07-05T11:34:16.356452+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5ELXJQQCSW6FECS","created_at":"2026-07-05T11:34:16.356452+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5ELXJQQ","created_at":"2026-07-05T11:34:16.356452+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/F5ELXJQQCSW6FECS7BZPOBSYTE","json":"https://pith.science/pith/F5ELXJQQCSW6FECS7BZPOBSYTE.json","graph_json":"https://pith.science/api/pith-number/F5ELXJQQCSW6FECS7BZPOBSYTE/graph.json","events_json":"https://pith.science/api/pith-number/F5ELXJQQCSW6FECS7BZPOBSYTE/events.json","paper":"https://pith.science/paper/F5ELXJQQ"},"agent_actions":{"view_html":"https://pith.science/pith/F5ELXJQQCSW6FECS7BZPOBSYTE","download_json":"https://pith.science/pith/F5ELXJQQCSW6FECS7BZPOBSYTE.json","view_paper":"https://pith.science/paper/F5ELXJQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06461&json=true","fetch_graph":"https://pith.science/api/pith-number/F5ELXJQQCSW6FECS7BZPOBSYTE/graph.json","fetch_events":"https://pith.science/api/pith-number/F5ELXJQQCSW6FECS7BZPOBSYTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5ELXJQQCSW6FECS7BZPOBSYTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5ELXJQQCSW6FECS7BZPOBSYTE/action/storage_attestation","attest_author":"https://pith.science/pith/F5ELXJQQCSW6FECS7BZPOBSYTE/action/author_attestation","sign_citation":"https://pith.science/pith/F5ELXJQQCSW6FECS7BZPOBSYTE/action/citation_signature","submit_replication":"https://pith.science/pith/F5ELXJQQCSW6FECS7BZPOBSYTE/action/replication_record"}},"created_at":"2026-07-05T11:34:16.356452+00:00","updated_at":"2026-07-05T11:34:16.356452+00:00"}