{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WRQINHTQJSBFK2QZ7NDBYVLAZX","short_pith_number":"pith:WRQINHTQ","schema_version":"1.0","canonical_sha256":"b460869e704c82556a19fb461c5560cdde6091c939444c956a43667f0cc2cb3b","source":{"kind":"arxiv","id":"2604.12254","version":2},"attestation_state":"computed","paper":{"title":"SpanKey: Dynamic Key Space Conditioning for Neural Network Access Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SpanKey gates neural network inference by conditioning activations on keys from a defined low-dimensional subspace.","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"WenBin Yan","submitted_at":"2026-04-14T04:01:34Z","abstract_excerpt":"SpanKey is a lightweight way to gate inference without encrypting weights or chasing leaderboard accuracy on gated inference. The idea is to condition activations on secret keys. A basis matrix $B$ defines a low-dimensional key subspace $Span(B)$; during training we sample coefficients $\\alpha$ and form keys $k=\\alpha^\\top B$, then inject them into intermediate activations with additive or multiplicative maps and strength $\\gamma$. Valid keys lie in $Span(B)$; invalid keys are sampled outside that subspace. We make three points. (i) Mechanism: subspace key injection and a multi-layer design sp"},"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":"2604.12254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-04-14T04:01:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c2e115dbdf0834b2c5db3dc7e4c6d2d63f85a3fcf3c1cf1d5034dea866930118","abstract_canon_sha256":"f501051a18f26d8c65a0b78929e5b204998bee6b6bb6bf11e749990433694ffc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:11.159018Z","signature_b64":"DATWux0eP+jo/ZROZ3e5WZlLkjiDuJ5EhqmG2dvoQ7wEABDqFz1er4RtyoQ2uN+K9osd105LLKIzb3PkYrePBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b460869e704c82556a19fb461c5560cdde6091c939444c956a43667f0cc2cb3b","last_reissued_at":"2026-05-20T00:03:11.158193Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:11.158193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpanKey: Dynamic Key Space Conditioning for Neural Network Access Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SpanKey gates neural network inference by conditioning activations on keys from a defined low-dimensional subspace.","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"WenBin Yan","submitted_at":"2026-04-14T04:01:34Z","abstract_excerpt":"SpanKey is a lightweight way to gate inference without encrypting weights or chasing leaderboard accuracy on gated inference. The idea is to condition activations on secret keys. A basis matrix $B$ defines a low-dimensional key subspace $Span(B)$; during training we sample coefficients $\\alpha$ and form keys $k=\\alpha^\\top B$, then inject them into intermediate activations with additive or multiplicative maps and strength $\\gamma$. Valid keys lie in $Span(B)$; invalid keys are sampled outside that subspace. We make three points. (i) Mechanism: subspace key injection and a multi-layer design sp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Subspace key injection with multi-layer design, together with deny losses and margin-tail diagnostics, enables practical key-based gating of neural network inference, as demonstrated by CIFAR-10 ResNet-18 runs and MNIST ablations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the network does not absorb the key signal into its weights in a way that collapses separation between valid and invalid keys at deployment scale, despite the analytical Beta-energy split and margin diagnostics provided.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SpanKey injects keys from a learned subspace into network activations via additive or multiplicative maps to enable key-based access control for neural network inference.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SpanKey gates neural network inference by conditioning activations on keys from a defined low-dimensional subspace.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"62f76804eabf2e507acf835b0c3ca516278b181c8ecc5b9be102a528ec5c21e7"},"source":{"id":"2604.12254","kind":"arxiv","version":2},"verdict":{"id":"1bb38d14-2076-4f4e-b1b0-c0babc128d08","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:54:32.601623Z","strongest_claim":"Subspace key injection with multi-layer design, together with deny losses and margin-tail diagnostics, enables practical key-based gating of neural network inference, as demonstrated by CIFAR-10 ResNet-18 runs and MNIST ablations.","one_line_summary":"SpanKey injects keys from a learned subspace into network activations via additive or multiplicative maps to enable key-based access control for neural network inference.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the network does not absorb the key signal into its weights in a way that collapses separation between valid and invalid keys at deployment scale, despite the analytical Beta-energy split and margin diagnostics provided.","pith_extraction_headline":"SpanKey gates neural network inference by conditioning activations on keys from a defined low-dimensional subspace."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.12254/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":"2604.12254","created_at":"2026-05-20T00:03:11.158309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.12254v2","created_at":"2026-05-20T00:03:11.158309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.12254","created_at":"2026-05-20T00:03:11.158309+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRQINHTQJSBF","created_at":"2026-05-20T00:03:11.158309+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRQINHTQJSBFK2QZ","created_at":"2026-05-20T00:03:11.158309+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRQINHTQ","created_at":"2026-05-20T00:03:11.158309+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/WRQINHTQJSBFK2QZ7NDBYVLAZX","json":"https://pith.science/pith/WRQINHTQJSBFK2QZ7NDBYVLAZX.json","graph_json":"https://pith.science/api/pith-number/WRQINHTQJSBFK2QZ7NDBYVLAZX/graph.json","events_json":"https://pith.science/api/pith-number/WRQINHTQJSBFK2QZ7NDBYVLAZX/events.json","paper":"https://pith.science/paper/WRQINHTQ"},"agent_actions":{"view_html":"https://pith.science/pith/WRQINHTQJSBFK2QZ7NDBYVLAZX","download_json":"https://pith.science/pith/WRQINHTQJSBFK2QZ7NDBYVLAZX.json","view_paper":"https://pith.science/paper/WRQINHTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.12254&json=true","fetch_graph":"https://pith.science/api/pith-number/WRQINHTQJSBFK2QZ7NDBYVLAZX/graph.json","fetch_events":"https://pith.science/api/pith-number/WRQINHTQJSBFK2QZ7NDBYVLAZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRQINHTQJSBFK2QZ7NDBYVLAZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRQINHTQJSBFK2QZ7NDBYVLAZX/action/storage_attestation","attest_author":"https://pith.science/pith/WRQINHTQJSBFK2QZ7NDBYVLAZX/action/author_attestation","sign_citation":"https://pith.science/pith/WRQINHTQJSBFK2QZ7NDBYVLAZX/action/citation_signature","submit_replication":"https://pith.science/pith/WRQINHTQJSBFK2QZ7NDBYVLAZX/action/replication_record"}},"created_at":"2026-05-20T00:03:11.158309+00:00","updated_at":"2026-05-20T00:03:11.158309+00:00"}