{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ISO3GE5X6PYHVKOZTRDAC73IM6","short_pith_number":"pith:ISO3GE5X","schema_version":"1.0","canonical_sha256":"449db313b7f3f07aa9d99c46017f68679af225afdd3af2227e896542dba854fc","source":{"kind":"arxiv","id":"2302.14112","version":2},"attestation_state":"computed","paper":{"title":"Injectivity of ReLU networks: perspectives from statistical physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","stat.ML"],"primary_cat":"cond-mat.dis-nn","authors_text":"Afonso S. Bandeira, Antoine Maillard, David Belius, Ivan Dokmani\\'c, Shuta Nakajima","submitted_at":"2023-02-27T19:51:42Z","abstract_excerpt":"When can the input of a ReLU neural network be inferred from its output? In other words, when is the network injective? We consider a single layer, $x \\mapsto \\mathrm{ReLU}(Wx)$, with a random Gaussian $m \\times n$ matrix $W$, in a high-dimensional setting where $n, m \\to \\infty$. Recent work connects this problem to spherical integral geometry giving rise to a conjectured sharp injectivity threshold for $\\alpha = \\frac{m}{n}$ by studying the expected Euler characteristic of a certain random set. We adopt a different perspective and show that injectivity is equivalent to a property of the grou"},"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":"2302.14112","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2023-02-27T19:51:42Z","cross_cats_sorted":["cs.LG","math.PR","stat.ML"],"title_canon_sha256":"c87e0c11bdcdc3ede70be70282ee0c18caf93196d067dd854cfc60f0b3b8e0a2","abstract_canon_sha256":"2023913d9e705d54997c74bccedcf5fd17dff2ee756412780b7516c36dcd840c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:10.712679Z","signature_b64":"lgUelcUMqg05+G4XisHWPG1RKRZiA7ZCGNwDbhs6yDqQ7guxCiaIFuPL+3JzH5qGdPLt8n3H2j5oM/UNqKogAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"449db313b7f3f07aa9d99c46017f68679af225afdd3af2227e896542dba854fc","last_reissued_at":"2026-07-05T09:48:10.712217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:10.712217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Injectivity of ReLU networks: perspectives from statistical physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","stat.ML"],"primary_cat":"cond-mat.dis-nn","authors_text":"Afonso S. Bandeira, Antoine Maillard, David Belius, Ivan Dokmani\\'c, Shuta Nakajima","submitted_at":"2023-02-27T19:51:42Z","abstract_excerpt":"When can the input of a ReLU neural network be inferred from its output? In other words, when is the network injective? We consider a single layer, $x \\mapsto \\mathrm{ReLU}(Wx)$, with a random Gaussian $m \\times n$ matrix $W$, in a high-dimensional setting where $n, m \\to \\infty$. Recent work connects this problem to spherical integral geometry giving rise to a conjectured sharp injectivity threshold for $\\alpha = \\frac{m}{n}$ by studying the expected Euler characteristic of a certain random set. We adopt a different perspective and show that injectivity is equivalent to a property of the grou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14112","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/2302.14112/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":"2302.14112","created_at":"2026-07-05T09:48:10.712266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14112v2","created_at":"2026-07-05T09:48:10.712266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14112","created_at":"2026-07-05T09:48:10.712266+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISO3GE5X6PYH","created_at":"2026-07-05T09:48:10.712266+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISO3GE5X6PYHVKOZ","created_at":"2026-07-05T09:48:10.712266+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISO3GE5X","created_at":"2026-07-05T09:48:10.712266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19677","citing_title":"Deep ReLU networks -- injectivity capacity upper bounds","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISO3GE5X6PYHVKOZTRDAC73IM6","json":"https://pith.science/pith/ISO3GE5X6PYHVKOZTRDAC73IM6.json","graph_json":"https://pith.science/api/pith-number/ISO3GE5X6PYHVKOZTRDAC73IM6/graph.json","events_json":"https://pith.science/api/pith-number/ISO3GE5X6PYHVKOZTRDAC73IM6/events.json","paper":"https://pith.science/paper/ISO3GE5X"},"agent_actions":{"view_html":"https://pith.science/pith/ISO3GE5X6PYHVKOZTRDAC73IM6","download_json":"https://pith.science/pith/ISO3GE5X6PYHVKOZTRDAC73IM6.json","view_paper":"https://pith.science/paper/ISO3GE5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14112&json=true","fetch_graph":"https://pith.science/api/pith-number/ISO3GE5X6PYHVKOZTRDAC73IM6/graph.json","fetch_events":"https://pith.science/api/pith-number/ISO3GE5X6PYHVKOZTRDAC73IM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISO3GE5X6PYHVKOZTRDAC73IM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISO3GE5X6PYHVKOZTRDAC73IM6/action/storage_attestation","attest_author":"https://pith.science/pith/ISO3GE5X6PYHVKOZTRDAC73IM6/action/author_attestation","sign_citation":"https://pith.science/pith/ISO3GE5X6PYHVKOZTRDAC73IM6/action/citation_signature","submit_replication":"https://pith.science/pith/ISO3GE5X6PYHVKOZTRDAC73IM6/action/replication_record"}},"created_at":"2026-07-05T09:48:10.712266+00:00","updated_at":"2026-07-05T09:48:10.712266+00:00"}