{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RCFTMNWOLPOIOIIK4DE6BSTDEB","short_pith_number":"pith:RCFTMNWO","schema_version":"1.0","canonical_sha256":"888b3636ce5bdc87210ae0c9e0ca63205bba3bd1597952328e14d3e17db3b871","source":{"kind":"arxiv","id":"1902.00730","version":1},"attestation_state":"computed","paper":{"title":"Self-Binarizing Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fayez Lahoud, Pablo M\\'arquez-Neila, Radhakrishna Achanta, Sabine S\\\"usstrunk","submitted_at":"2019-02-02T14:48:16Z","abstract_excerpt":"We present a method to train self-binarizing neural networks, that is, networks that evolve their weights and activations during training to become binary. To obtain similar binary networks, existing methods rely on the sign activation function. This function, however, has no gradients for non-zero values, which makes standard backpropagation impossible. To circumvent the difficulty of training a network relying on the sign activation function, these methods alternate between floating-point and binary representations of the network during training, which is sub-optimal and inefficient. We appr"},"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":"1902.00730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-02T14:48:16Z","cross_cats_sorted":[],"title_canon_sha256":"8f577d90126f41e14616fa1006bbc15989032cb9f16c3bf5e25624ca8deddb85","abstract_canon_sha256":"dd791b059eecf33b30eef57d425a2b60c0d8b1fd3f765b23584cd1f5f2296356"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:52.330935Z","signature_b64":"tJej5/wN0s6mIKnccNSC6w4EOjy05Lqa5Vd75HfjuLwisG8mfI+UauzRees9SfPfHVWz+030YP+hqNcUKby0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"888b3636ce5bdc87210ae0c9e0ca63205bba3bd1597952328e14d3e17db3b871","last_reissued_at":"2026-05-17T23:54:52.330525Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:52.330525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Binarizing Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fayez Lahoud, Pablo M\\'arquez-Neila, Radhakrishna Achanta, Sabine S\\\"usstrunk","submitted_at":"2019-02-02T14:48:16Z","abstract_excerpt":"We present a method to train self-binarizing neural networks, that is, networks that evolve their weights and activations during training to become binary. To obtain similar binary networks, existing methods rely on the sign activation function. This function, however, has no gradients for non-zero values, which makes standard backpropagation impossible. To circumvent the difficulty of training a network relying on the sign activation function, these methods alternate between floating-point and binary representations of the network during training, which is sub-optimal and inefficient. We appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00730","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":""},"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":"1902.00730","created_at":"2026-05-17T23:54:52.330586+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00730v1","created_at":"2026-05-17T23:54:52.330586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00730","created_at":"2026-05-17T23:54:52.330586+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCFTMNWOLPOI","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCFTMNWOLPOIOIIK","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCFTMNWO","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11558","citing_title":"A Composite Activation Function for Learning Stable Binary Representations","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCFTMNWOLPOIOIIK4DE6BSTDEB","json":"https://pith.science/pith/RCFTMNWOLPOIOIIK4DE6BSTDEB.json","graph_json":"https://pith.science/api/pith-number/RCFTMNWOLPOIOIIK4DE6BSTDEB/graph.json","events_json":"https://pith.science/api/pith-number/RCFTMNWOLPOIOIIK4DE6BSTDEB/events.json","paper":"https://pith.science/paper/RCFTMNWO"},"agent_actions":{"view_html":"https://pith.science/pith/RCFTMNWOLPOIOIIK4DE6BSTDEB","download_json":"https://pith.science/pith/RCFTMNWOLPOIOIIK4DE6BSTDEB.json","view_paper":"https://pith.science/paper/RCFTMNWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00730&json=true","fetch_graph":"https://pith.science/api/pith-number/RCFTMNWOLPOIOIIK4DE6BSTDEB/graph.json","fetch_events":"https://pith.science/api/pith-number/RCFTMNWOLPOIOIIK4DE6BSTDEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCFTMNWOLPOIOIIK4DE6BSTDEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCFTMNWOLPOIOIIK4DE6BSTDEB/action/storage_attestation","attest_author":"https://pith.science/pith/RCFTMNWOLPOIOIIK4DE6BSTDEB/action/author_attestation","sign_citation":"https://pith.science/pith/RCFTMNWOLPOIOIIK4DE6BSTDEB/action/citation_signature","submit_replication":"https://pith.science/pith/RCFTMNWOLPOIOIIK4DE6BSTDEB/action/replication_record"}},"created_at":"2026-05-17T23:54:52.330586+00:00","updated_at":"2026-05-17T23:54:52.330586+00:00"}