{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IYLGLJYMTPSNDNATWK5ED56MWN","short_pith_number":"pith:IYLGLJYM","schema_version":"1.0","canonical_sha256":"461665a70c9be4d1b413b2ba41f7ccb34326460b947845baa0fe1e6a1f34baf7","source":{"kind":"arxiv","id":"2306.14817","version":1},"attestation_state":"computed","paper":{"title":"Black holes and the loss landscape in machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"hep-th","authors_text":"Pranav Kumar, Swapnamay Mondal, Taniya Mandal","submitted_at":"2023-06-26T16:22:33Z","abstract_excerpt":"Understanding the loss landscape is an important problem in machine learning. One key feature of the loss function, common to many neural network architectures, is the presence of exponentially many low lying local minima. Physical systems with similar energy landscapes may provide useful insights. In this work, we point out that black holes naturally give rise to such landscapes, owing to the existence of black hole entropy. For definiteness, we consider 1/8 BPS black holes in $\\mathcal{N} = 8$ string theory. These provide an infinite family of potential landscapes arising in the microscopic "},"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":"2306.14817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-th","submitted_at":"2023-06-26T16:22:33Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bea5957bae686778461e9117a4bafe03425eda2d755578b083f94800b71d93c0","abstract_canon_sha256":"590c3a86b170fb6f05bbfa77aaa4a349eae828fee46e4e1fe88728710fd56814"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:54.736190Z","signature_b64":"lDD51Gji7mIzeBBIyq3tAtsCT0//DK78piWKqKCTXp+mPyyagGMFpCPRukTJEKQ10ve/dHNgX7ygoUIq/MSoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"461665a70c9be4d1b413b2ba41f7ccb34326460b947845baa0fe1e6a1f34baf7","last_reissued_at":"2026-07-05T07:14:54.735701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:54.735701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Black holes and the loss landscape in machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"hep-th","authors_text":"Pranav Kumar, Swapnamay Mondal, Taniya Mandal","submitted_at":"2023-06-26T16:22:33Z","abstract_excerpt":"Understanding the loss landscape is an important problem in machine learning. One key feature of the loss function, common to many neural network architectures, is the presence of exponentially many low lying local minima. Physical systems with similar energy landscapes may provide useful insights. In this work, we point out that black holes naturally give rise to such landscapes, owing to the existence of black hole entropy. For definiteness, we consider 1/8 BPS black holes in $\\mathcal{N} = 8$ string theory. These provide an infinite family of potential landscapes arising in the microscopic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14817","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/2306.14817/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":"2306.14817","created_at":"2026-07-05T07:14:54.735759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14817v1","created_at":"2026-07-05T07:14:54.735759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14817","created_at":"2026-07-05T07:14:54.735759+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYLGLJYMTPSN","created_at":"2026-07-05T07:14:54.735759+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYLGLJYMTPSNDNAT","created_at":"2026-07-05T07:14:54.735759+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYLGLJYM","created_at":"2026-07-05T07:14:54.735759+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/IYLGLJYMTPSNDNATWK5ED56MWN","json":"https://pith.science/pith/IYLGLJYMTPSNDNATWK5ED56MWN.json","graph_json":"https://pith.science/api/pith-number/IYLGLJYMTPSNDNATWK5ED56MWN/graph.json","events_json":"https://pith.science/api/pith-number/IYLGLJYMTPSNDNATWK5ED56MWN/events.json","paper":"https://pith.science/paper/IYLGLJYM"},"agent_actions":{"view_html":"https://pith.science/pith/IYLGLJYMTPSNDNATWK5ED56MWN","download_json":"https://pith.science/pith/IYLGLJYMTPSNDNATWK5ED56MWN.json","view_paper":"https://pith.science/paper/IYLGLJYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14817&json=true","fetch_graph":"https://pith.science/api/pith-number/IYLGLJYMTPSNDNATWK5ED56MWN/graph.json","fetch_events":"https://pith.science/api/pith-number/IYLGLJYMTPSNDNATWK5ED56MWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYLGLJYMTPSNDNATWK5ED56MWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYLGLJYMTPSNDNATWK5ED56MWN/action/storage_attestation","attest_author":"https://pith.science/pith/IYLGLJYMTPSNDNATWK5ED56MWN/action/author_attestation","sign_citation":"https://pith.science/pith/IYLGLJYMTPSNDNATWK5ED56MWN/action/citation_signature","submit_replication":"https://pith.science/pith/IYLGLJYMTPSNDNATWK5ED56MWN/action/replication_record"}},"created_at":"2026-07-05T07:14:54.735759+00:00","updated_at":"2026-07-05T07:14:54.735759+00:00"}