{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SLQG3KRPS6FWAVIGO3X5IFVEQQ","short_pith_number":"pith:SLQG3KRP","schema_version":"1.0","canonical_sha256":"92e06daa2f978b60550676efd416a48409beb9fc1e70ce29281900e0b03d44dc","source":{"kind":"arxiv","id":"2503.00268","version":1},"attestation_state":"computed","paper":{"title":"Input Specific Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.NE"],"primary_cat":"cs.LG","authors_text":"Asghar A. Jadoon, D. Thomas Seidl, Jan N. Fuhg, Reese E. Jones","submitted_at":"2025-03-01T00:57:16Z","abstract_excerpt":"The black-box nature of neural networks limits the ability to encode or impose specific structural relationships between inputs and outputs. While various studies have introduced architectures that ensure the network's output adheres to a particular form in relation to certain inputs, the majority of these approaches impose constraints on only a single set of inputs. This paper introduces a novel neural network architecture, termed the Input Specific Neural Network (ISNN), which extends this concept by allowing scalar-valued outputs to be subject to multiple constraints. Specifically, the ISNN"},"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":"2503.00268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-01T00:57:16Z","cross_cats_sorted":["cs.AI","cs.CE","cs.NE"],"title_canon_sha256":"7c42ccd1a959d0a838ebf3f6a8889b553a5625779e5a0a66843f8800816b208e","abstract_canon_sha256":"3838f1bcfb8d7bd2087131db795c8aa2c3b5fe6d50369b1b75a1f07830979eb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:19.914025Z","signature_b64":"8nA31dUOIZQwmUYhp8GUIrZQF1GV4KzZuw21R0BewWbZs0HBxf72VKorUmkYvdptsuPCvz2pE+2SoK4Dg09DCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92e06daa2f978b60550676efd416a48409beb9fc1e70ce29281900e0b03d44dc","last_reissued_at":"2026-07-05T10:22:19.913588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:19.913588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Input Specific Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.NE"],"primary_cat":"cs.LG","authors_text":"Asghar A. Jadoon, D. Thomas Seidl, Jan N. Fuhg, Reese E. Jones","submitted_at":"2025-03-01T00:57:16Z","abstract_excerpt":"The black-box nature of neural networks limits the ability to encode or impose specific structural relationships between inputs and outputs. While various studies have introduced architectures that ensure the network's output adheres to a particular form in relation to certain inputs, the majority of these approaches impose constraints on only a single set of inputs. This paper introduces a novel neural network architecture, termed the Input Specific Neural Network (ISNN), which extends this concept by allowing scalar-valued outputs to be subject to multiple constraints. Specifically, the ISNN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00268","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/2503.00268/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":"2503.00268","created_at":"2026-07-05T10:22:19.913655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00268v1","created_at":"2026-07-05T10:22:19.913655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00268","created_at":"2026-07-05T10:22:19.913655+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLQG3KRPS6FW","created_at":"2026-07-05T10:22:19.913655+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLQG3KRPS6FWAVIG","created_at":"2026-07-05T10:22:19.913655+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLQG3KRP","created_at":"2026-07-05T10:22:19.913655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17242","citing_title":"Differentiable neural network representation of multi-well, locally-convex potentials","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SLQG3KRPS6FWAVIGO3X5IFVEQQ","json":"https://pith.science/pith/SLQG3KRPS6FWAVIGO3X5IFVEQQ.json","graph_json":"https://pith.science/api/pith-number/SLQG3KRPS6FWAVIGO3X5IFVEQQ/graph.json","events_json":"https://pith.science/api/pith-number/SLQG3KRPS6FWAVIGO3X5IFVEQQ/events.json","paper":"https://pith.science/paper/SLQG3KRP"},"agent_actions":{"view_html":"https://pith.science/pith/SLQG3KRPS6FWAVIGO3X5IFVEQQ","download_json":"https://pith.science/pith/SLQG3KRPS6FWAVIGO3X5IFVEQQ.json","view_paper":"https://pith.science/paper/SLQG3KRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00268&json=true","fetch_graph":"https://pith.science/api/pith-number/SLQG3KRPS6FWAVIGO3X5IFVEQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SLQG3KRPS6FWAVIGO3X5IFVEQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLQG3KRPS6FWAVIGO3X5IFVEQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLQG3KRPS6FWAVIGO3X5IFVEQQ/action/storage_attestation","attest_author":"https://pith.science/pith/SLQG3KRPS6FWAVIGO3X5IFVEQQ/action/author_attestation","sign_citation":"https://pith.science/pith/SLQG3KRPS6FWAVIGO3X5IFVEQQ/action/citation_signature","submit_replication":"https://pith.science/pith/SLQG3KRPS6FWAVIGO3X5IFVEQQ/action/replication_record"}},"created_at":"2026-07-05T10:22:19.913655+00:00","updated_at":"2026-07-05T10:22:19.913655+00:00"}