{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E6RXDC64YNIFHUTDZMYQGWCCFG","short_pith_number":"pith:E6RXDC64","canonical_record":{"source":{"id":"2501.02010","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T12:10:17Z","cross_cats_sorted":[],"title_canon_sha256":"97ea4cbf2f23cca14b5852134f918838f460b385be2dce4a2d780c0637789f2b","abstract_canon_sha256":"9ab0eea5dae8aadf5e2ccbf0cc059fcd923a9f844a3cb46e3e1349333e3da80c"},"schema_version":"1.0"},"canonical_sha256":"27a3718bdcc35053d263cb310358422996dbcc358531ff9c850e248bcc208d8d","source":{"kind":"arxiv","id":"2501.02010","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02010","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02010v2","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02010","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_12","alias_value":"E6RXDC64YNIF","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_16","alias_value":"E6RXDC64YNIFHUTD","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_8","alias_value":"E6RXDC64","created_at":"2026-07-05T10:16:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E6RXDC64YNIFHUTDZMYQGWCCFG","target":"record","payload":{"canonical_record":{"source":{"id":"2501.02010","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T12:10:17Z","cross_cats_sorted":[],"title_canon_sha256":"97ea4cbf2f23cca14b5852134f918838f460b385be2dce4a2d780c0637789f2b","abstract_canon_sha256":"9ab0eea5dae8aadf5e2ccbf0cc059fcd923a9f844a3cb46e3e1349333e3da80c"},"schema_version":"1.0"},"canonical_sha256":"27a3718bdcc35053d263cb310358422996dbcc358531ff9c850e248bcc208d8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:40.784356Z","signature_b64":"RGTuEt2zHohTNNn/RPM0OgvmdXYANEjEWn/zTiRr5h6PMkq5tu2fqtYE4Psk9qbVyM3PCFsmfiIvx1WS9kuvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27a3718bdcc35053d263cb310358422996dbcc358531ff9c850e248bcc208d8d","last_reissued_at":"2026-07-05T10:16:40.783915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:40.783915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.02010","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P10TURx0Ix9VkQeuC7XUbZPFIOSZqjuZTQS+yZXFAbdiLrh7ahJXq8TinNkpfSMZTN5UzLSrStiSykpoQWcVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:31:22.431894Z"},"content_sha256":"807644a466aafbc05cb1747c32df9fd8377317f8db83f26d5d0e4a3cc9a4364e","schema_version":"1.0","event_id":"sha256:807644a466aafbc05cb1747c32df9fd8377317f8db83f26d5d0e4a3cc9a4364e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E6RXDC64YNIFHUTDZMYQGWCCFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explainable Neural Networks with Guarantees: A Sparse Estimation Approach","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antoine Ledent, Peng Liu","submitted_at":"2025-01-02T12:10:17Z","abstract_excerpt":"Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability. Our model, termed SparXnet, is designed as a linear combination of a sparse set of jointly learned features, each derived from a different trainable function applied to a single 1-dimensional input feature. Leveraging the ability to learn arbitrarily comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02010","kind":"arxiv","version":2},"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/2501.02010/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qw/Ai+EDPpEtzoTTPIJ1DTmkVYfEO9XdlIHhGj+IGxB86b8PYXA8rfiGZ70TSn0keafsTEHmSAr3cYiVC3EmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:31:22.432794Z"},"content_sha256":"b21b2f236ab8e26f19358729b46ec8a713223c118dd4b27889cfea3d2e8c1027","schema_version":"1.0","event_id":"sha256:b21b2f236ab8e26f19358729b46ec8a713223c118dd4b27889cfea3d2e8c1027"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E6RXDC64YNIFHUTDZMYQGWCCFG/bundle.json","state_url":"https://pith.science/pith/E6RXDC64YNIFHUTDZMYQGWCCFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E6RXDC64YNIFHUTDZMYQGWCCFG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T11:31:22Z","links":{"resolver":"https://pith.science/pith/E6RXDC64YNIFHUTDZMYQGWCCFG","bundle":"https://pith.science/pith/E6RXDC64YNIFHUTDZMYQGWCCFG/bundle.json","state":"https://pith.science/pith/E6RXDC64YNIFHUTDZMYQGWCCFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E6RXDC64YNIFHUTDZMYQGWCCFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E6RXDC64YNIFHUTDZMYQGWCCFG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9ab0eea5dae8aadf5e2ccbf0cc059fcd923a9f844a3cb46e3e1349333e3da80c","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T12:10:17Z","title_canon_sha256":"97ea4cbf2f23cca14b5852134f918838f460b385be2dce4a2d780c0637789f2b"},"schema_version":"1.0","source":{"id":"2501.02010","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02010","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02010v2","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02010","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_12","alias_value":"E6RXDC64YNIF","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_16","alias_value":"E6RXDC64YNIFHUTD","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_8","alias_value":"E6RXDC64","created_at":"2026-07-05T10:16:40Z"}],"graph_snapshots":[{"event_id":"sha256:b21b2f236ab8e26f19358729b46ec8a713223c118dd4b27889cfea3d2e8c1027","target":"graph","created_at":"2026-07-05T10:16:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.02010/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability. Our model, termed SparXnet, is designed as a linear combination of a sparse set of jointly learned features, each derived from a different trainable function applied to a single 1-dimensional input feature. Leveraging the ability to learn arbitrarily comp","authors_text":"Antoine Ledent, Peng Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T12:10:17Z","title":"Explainable Neural Networks with Guarantees: A Sparse Estimation Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02010","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:807644a466aafbc05cb1747c32df9fd8377317f8db83f26d5d0e4a3cc9a4364e","target":"record","created_at":"2026-07-05T10:16:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9ab0eea5dae8aadf5e2ccbf0cc059fcd923a9f844a3cb46e3e1349333e3da80c","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T12:10:17Z","title_canon_sha256":"97ea4cbf2f23cca14b5852134f918838f460b385be2dce4a2d780c0637789f2b"},"schema_version":"1.0","source":{"id":"2501.02010","kind":"arxiv","version":2}},"canonical_sha256":"27a3718bdcc35053d263cb310358422996dbcc358531ff9c850e248bcc208d8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27a3718bdcc35053d263cb310358422996dbcc358531ff9c850e248bcc208d8d","first_computed_at":"2026-07-05T10:16:40.783915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:40.783915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RGTuEt2zHohTNNn/RPM0OgvmdXYANEjEWn/zTiRr5h6PMkq5tu2fqtYE4Psk9qbVyM3PCFsmfiIvx1WS9kuvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:40.784356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02010","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:807644a466aafbc05cb1747c32df9fd8377317f8db83f26d5d0e4a3cc9a4364e","sha256:b21b2f236ab8e26f19358729b46ec8a713223c118dd4b27889cfea3d2e8c1027"],"state_sha256":"547ac4344a98ade75264baf011afe15972efc0012680fca6d195c66133db0edc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9sMXB99iwnsQHg0sLtF7U9IfIvPX7keW/oKsH7G4X44056t7WMykjs7oMDeyza1pB9CIcseGl40B0SXNHCKaBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T11:31:22.505563Z","bundle_sha256":"624303f1151dedd0ffaf7a8422d34bfcc66685e189f0e7c3b23a137e764bfa0b"}}