{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6T7YJ5NSNHWJ2NA6HIJMQ2XYUT","short_pith_number":"pith:6T7YJ5NS","canonical_record":{"source":{"id":"2306.02666","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-06-05T08:01:50Z","cross_cats_sorted":["math.AG","math.FA","math.OC"],"title_canon_sha256":"84e71db97069b31f406d8a595c94678342a2601b3ee50ed04e565a93d4a3325e","abstract_canon_sha256":"20e234da8b09f5246f462e0a18cc20832e799cb62be44c02ff41a316884a145f"},"schema_version":"1.0"},"canonical_sha256":"f4ff84f5b269ec9d341e3a12c86af8a4dcb9f22a789ffc98e3dba9330e4e3355","source":{"kind":"arxiv","id":"2306.02666","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02666","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02666v2","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02666","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"6T7YJ5NSNHWJ","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"6T7YJ5NSNHWJ2NA6","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"6T7YJ5NS","created_at":"2026-07-05T07:20:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6T7YJ5NSNHWJ2NA6HIJMQ2XYUT","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02666","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-06-05T08:01:50Z","cross_cats_sorted":["math.AG","math.FA","math.OC"],"title_canon_sha256":"84e71db97069b31f406d8a595c94678342a2601b3ee50ed04e565a93d4a3325e","abstract_canon_sha256":"20e234da8b09f5246f462e0a18cc20832e799cb62be44c02ff41a316884a145f"},"schema_version":"1.0"},"canonical_sha256":"f4ff84f5b269ec9d341e3a12c86af8a4dcb9f22a789ffc98e3dba9330e4e3355","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:08.756826Z","signature_b64":"FXYRj1aBIyhHbc00L13ZVaPlvO2TcxUNiT1Yjr3kV7H/QHL3nM10eRNsB4QxgM63wHLPtom1F9eG8TAUazGjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4ff84f5b269ec9d341e3a12c86af8a4dcb9f22a789ffc98e3dba9330e4e3355","last_reissued_at":"2026-07-05T07:20:08.756389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:08.756389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02666","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":"2026-07-05T07:20:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gVrMD+q/wHJKERsBjKZaocSyu/wG7OoDPsWfdevxJOx5XwkCKvzvca5dYlYTKl1Pgvrfc/x9/ok5ZSdBw0g5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T09:49:13.187108Z"},"content_sha256":"1cf369bcddb304d0b89e857578efb63eaeaa0129a9119c13400756e91a36e930","schema_version":"1.0","event_id":"sha256:1cf369bcddb304d0b89e857578efb63eaeaa0129a9119c13400756e91a36e930"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6T7YJ5NSNHWJ2NA6HIJMQ2XYUT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Does a sparse ReLU network training problem always admit an optimum?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AG","math.FA","math.OC"],"primary_cat":"cs.NE","authors_text":"Elisa Riccietti (OCKHAM), OCKHAM), Quoc-Tung Le (LIP, R\\'emi Gribonval (OCKHAM)","submitted_at":"2023-06-05T08:01:50Z","abstract_excerpt":"Given a training set, a loss function, and a neural network architecture, it is often taken for granted that optimal network parameters exist, and a common practice is to apply available optimization algorithms to search for them. In this work, we show that the existence of an optimal solution is not always guaranteed, especially in the context of {\\em sparse} ReLU neural networks. In particular, we first show that optimization problems involving deep networks with certain sparsity patterns do not always have optimal parameters, and that optimization algorithms may then  diverge. Via a new top"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02666","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/2306.02666/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":"2026-07-05T07:20:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ZND/RwgBfX9JoQ7p0OhMgApn5h0iDp7uirL9eoxP8bp8J039YLYVs/t/NHilEirmacMRhhaJSLVggghY4lVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T09:49:13.188039Z"},"content_sha256":"977abaab18fc43bb2e63cdc72aab61168ac1f9b53b97a5f270cabce485c16b1d","schema_version":"1.0","event_id":"sha256:977abaab18fc43bb2e63cdc72aab61168ac1f9b53b97a5f270cabce485c16b1d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6T7YJ5NSNHWJ2NA6HIJMQ2XYUT/bundle.json","state_url":"https://pith.science/pith/6T7YJ5NSNHWJ2NA6HIJMQ2XYUT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6T7YJ5NSNHWJ2NA6HIJMQ2XYUT/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":"2026-08-11T09:49:13Z","links":{"resolver":"https://pith.science/pith/6T7YJ5NSNHWJ2NA6HIJMQ2XYUT","bundle":"https://pith.science/pith/6T7YJ5NSNHWJ2NA6HIJMQ2XYUT/bundle.json","state":"https://pith.science/pith/6T7YJ5NSNHWJ2NA6HIJMQ2XYUT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6T7YJ5NSNHWJ2NA6HIJMQ2XYUT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6T7YJ5NSNHWJ2NA6HIJMQ2XYUT","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":"20e234da8b09f5246f462e0a18cc20832e799cb62be44c02ff41a316884a145f","cross_cats_sorted":["math.AG","math.FA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-06-05T08:01:50Z","title_canon_sha256":"84e71db97069b31f406d8a595c94678342a2601b3ee50ed04e565a93d4a3325e"},"schema_version":"1.0","source":{"id":"2306.02666","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02666","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02666v2","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02666","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"6T7YJ5NSNHWJ","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"6T7YJ5NSNHWJ2NA6","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"6T7YJ5NS","created_at":"2026-07-05T07:20:08Z"}],"graph_snapshots":[{"event_id":"sha256:977abaab18fc43bb2e63cdc72aab61168ac1f9b53b97a5f270cabce485c16b1d","target":"graph","created_at":"2026-07-05T07:20:08Z","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/2306.02666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given a training set, a loss function, and a neural network architecture, it is often taken for granted that optimal network parameters exist, and a common practice is to apply available optimization algorithms to search for them. In this work, we show that the existence of an optimal solution is not always guaranteed, especially in the context of {\\em sparse} ReLU neural networks. In particular, we first show that optimization problems involving deep networks with certain sparsity patterns do not always have optimal parameters, and that optimization algorithms may then  diverge. Via a new top","authors_text":"Elisa Riccietti (OCKHAM), OCKHAM), Quoc-Tung Le (LIP, R\\'emi Gribonval (OCKHAM)","cross_cats":["math.AG","math.FA","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-06-05T08:01:50Z","title":"Does a sparse ReLU network training problem always admit an optimum?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02666","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":"sha256:1cf369bcddb304d0b89e857578efb63eaeaa0129a9119c13400756e91a36e930","target":"record","created_at":"2026-07-05T07:20:08Z","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":"20e234da8b09f5246f462e0a18cc20832e799cb62be44c02ff41a316884a145f","cross_cats_sorted":["math.AG","math.FA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-06-05T08:01:50Z","title_canon_sha256":"84e71db97069b31f406d8a595c94678342a2601b3ee50ed04e565a93d4a3325e"},"schema_version":"1.0","source":{"id":"2306.02666","kind":"arxiv","version":2}},"canonical_sha256":"f4ff84f5b269ec9d341e3a12c86af8a4dcb9f22a789ffc98e3dba9330e4e3355","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4ff84f5b269ec9d341e3a12c86af8a4dcb9f22a789ffc98e3dba9330e4e3355","first_computed_at":"2026-07-05T07:20:08.756389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:08.756389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FXYRj1aBIyhHbc00L13ZVaPlvO2TcxUNiT1Yjr3kV7H/QHL3nM10eRNsB4QxgM63wHLPtom1F9eG8TAUazGjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:08.756826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02666","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cf369bcddb304d0b89e857578efb63eaeaa0129a9119c13400756e91a36e930","sha256:977abaab18fc43bb2e63cdc72aab61168ac1f9b53b97a5f270cabce485c16b1d"],"state_sha256":"6be3fea38c5208099f4b8106ff3424163d877bb62d9d43219ed9575928fbf387"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"et7Hc1mEziy0qopON+Dqy/DBMfsfbAo5mGocUQBArfeW/dBUA3s+YDy5Ut5cWYHGZQh22m/M8Vkx/4tzJI0NDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T09:49:13.194120Z","bundle_sha256":"cd687decd2a992d2b6dbb9bcb50107cb1bdc3a18a3ed5879b6e077abada4db5b"}}