{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IZFHX2B5VHUNPGSZ7C55PZ7CSV","short_pith_number":"pith:IZFHX2B5","schema_version":"1.0","canonical_sha256":"464a7be83da9e8d79a59f8bbd7e7e295584526bf4e633c6a2eda9a67b86d6d10","source":{"kind":"arxiv","id":"2504.08415","version":1},"attestation_state":"computed","paper":{"title":"Constrained Machine Learning Through Hyperspherical Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gaetano Signorelli, Michele Lombardi","submitted_at":"2025-04-11T10:19:49Z","abstract_excerpt":"The problem of ensuring constraints satisfaction on the output of machine learning models is critical for many applications, especially in safety-critical domains. Modern approaches rely on penalty-based methods at training time, which do not guarantee to avoid constraints violations; or constraint-specific model architectures (e.g., for monotonocity); or on output projection, which requires to solve an optimization problem that might be computationally demanding. We present the Hypersherical Constrained Representation, a novel method to enforce constraints in the output space for convex and b"},"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":"2504.08415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-11T10:19:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"900f43a53dc7f3be2122c38ddc9af16c1d05977b2e8fcf79b9bb621d0c07e503","abstract_canon_sha256":"f005239127402b0290654fc1ff62beee17d3f0edf3ae73b0015901bac48bb82c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:48.890453Z","signature_b64":"42Ie9TQf1gmQ/02N0XRVbLGhTaKgEX+voZVZW3zmfA7ttVK1aQ8o6COAjZ1ljDAqBq2/mevxEwxxAv8y9fxjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"464a7be83da9e8d79a59f8bbd7e7e295584526bf4e633c6a2eda9a67b86d6d10","last_reissued_at":"2026-07-05T10:47:48.889983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:48.889983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Machine Learning Through Hyperspherical Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gaetano Signorelli, Michele Lombardi","submitted_at":"2025-04-11T10:19:49Z","abstract_excerpt":"The problem of ensuring constraints satisfaction on the output of machine learning models is critical for many applications, especially in safety-critical domains. Modern approaches rely on penalty-based methods at training time, which do not guarantee to avoid constraints violations; or constraint-specific model architectures (e.g., for monotonocity); or on output projection, which requires to solve an optimization problem that might be computationally demanding. We present the Hypersherical Constrained Representation, a novel method to enforce constraints in the output space for convex and b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08415","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/2504.08415/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":"2504.08415","created_at":"2026-07-05T10:47:48.890040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08415v1","created_at":"2026-07-05T10:47:48.890040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08415","created_at":"2026-07-05T10:47:48.890040+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZFHX2B5VHUN","created_at":"2026-07-05T10:47:48.890040+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZFHX2B5VHUNPGSZ","created_at":"2026-07-05T10:47:48.890040+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZFHX2B5","created_at":"2026-07-05T10:47:48.890040+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/IZFHX2B5VHUNPGSZ7C55PZ7CSV","json":"https://pith.science/pith/IZFHX2B5VHUNPGSZ7C55PZ7CSV.json","graph_json":"https://pith.science/api/pith-number/IZFHX2B5VHUNPGSZ7C55PZ7CSV/graph.json","events_json":"https://pith.science/api/pith-number/IZFHX2B5VHUNPGSZ7C55PZ7CSV/events.json","paper":"https://pith.science/paper/IZFHX2B5"},"agent_actions":{"view_html":"https://pith.science/pith/IZFHX2B5VHUNPGSZ7C55PZ7CSV","download_json":"https://pith.science/pith/IZFHX2B5VHUNPGSZ7C55PZ7CSV.json","view_paper":"https://pith.science/paper/IZFHX2B5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08415&json=true","fetch_graph":"https://pith.science/api/pith-number/IZFHX2B5VHUNPGSZ7C55PZ7CSV/graph.json","fetch_events":"https://pith.science/api/pith-number/IZFHX2B5VHUNPGSZ7C55PZ7CSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZFHX2B5VHUNPGSZ7C55PZ7CSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZFHX2B5VHUNPGSZ7C55PZ7CSV/action/storage_attestation","attest_author":"https://pith.science/pith/IZFHX2B5VHUNPGSZ7C55PZ7CSV/action/author_attestation","sign_citation":"https://pith.science/pith/IZFHX2B5VHUNPGSZ7C55PZ7CSV/action/citation_signature","submit_replication":"https://pith.science/pith/IZFHX2B5VHUNPGSZ7C55PZ7CSV/action/replication_record"}},"created_at":"2026-07-05T10:47:48.890040+00:00","updated_at":"2026-07-05T10:47:48.890040+00:00"}