{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6NLMC2NSLLV3X3GPL7TQO33OKF","short_pith_number":"pith:6NLMC2NS","schema_version":"1.0","canonical_sha256":"f356c169b25aebbbeccf5fe7076f6e51462a8ff7ef2190f8a8510b1bd8020f43","source":{"kind":"arxiv","id":"1809.09349","version":4},"attestation_state":"computed","paper":{"title":"The jamming transition as a paradigm to understand the loss landscape of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Giulio Biroli, Levent Sagun, Marco Baity-Jesi, Mario Geiger, Matthieu Wyart, Stefano Spigler, St\\'ephane d'Ascoli","submitted_at":"2018-09-25T07:15:27Z","abstract_excerpt":"Deep learning has been immensely successful at a variety of tasks, ranging from classification to AI. Learning corresponds to fitting training data, which is implemented by descending a very high-dimensional loss function. Understanding under which conditions neural networks do not get stuck in poor minima of the loss, and how the landscape of that loss evolves as depth is increased remains a challenge. Here we predict, and test empirically, an analogy between this landscape and the energy landscape of repulsive ellipses. We argue that in FC networks a phase transition delimits the over- and u"},"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":"1809.09349","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2018-09-25T07:15:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b91abad3f26c09c9c362cc4f34a3cfcca76adfb1456d138c56bca82664c40b58","abstract_canon_sha256":"6d371ec2481e79da8c2c2e192acf0071ba9221ef90996baf645bfc26d6a6cb2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:34.373669Z","signature_b64":"UYRSmJfARRhsRS5BAB8qvFFBqCEuxVErPksfDUct2/naiHL/5fzR2w50NFuauvR2BKlt60WOuOcos5/AHv4DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f356c169b25aebbbeccf5fe7076f6e51462a8ff7ef2190f8a8510b1bd8020f43","last_reissued_at":"2026-05-17T23:40:34.372953Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:34.372953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The jamming transition as a paradigm to understand the loss landscape of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Giulio Biroli, Levent Sagun, Marco Baity-Jesi, Mario Geiger, Matthieu Wyart, Stefano Spigler, St\\'ephane d'Ascoli","submitted_at":"2018-09-25T07:15:27Z","abstract_excerpt":"Deep learning has been immensely successful at a variety of tasks, ranging from classification to AI. Learning corresponds to fitting training data, which is implemented by descending a very high-dimensional loss function. Understanding under which conditions neural networks do not get stuck in poor minima of the loss, and how the landscape of that loss evolves as depth is increased remains a challenge. Here we predict, and test empirically, an analogy between this landscape and the energy landscape of repulsive ellipses. We argue that in FC networks a phase transition delimits the over- and u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09349","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1809.09349","created_at":"2026-05-17T23:40:34.373096+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.09349v4","created_at":"2026-05-17T23:40:34.373096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09349","created_at":"2026-05-17T23:40:34.373096+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NLMC2NSLLV3","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NLMC2NSLLV3X3GP","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NLMC2NS","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23591","citing_title":"Asymmetric Scaling Laws from Sparse Features","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NLMC2NSLLV3X3GPL7TQO33OKF","json":"https://pith.science/pith/6NLMC2NSLLV3X3GPL7TQO33OKF.json","graph_json":"https://pith.science/api/pith-number/6NLMC2NSLLV3X3GPL7TQO33OKF/graph.json","events_json":"https://pith.science/api/pith-number/6NLMC2NSLLV3X3GPL7TQO33OKF/events.json","paper":"https://pith.science/paper/6NLMC2NS"},"agent_actions":{"view_html":"https://pith.science/pith/6NLMC2NSLLV3X3GPL7TQO33OKF","download_json":"https://pith.science/pith/6NLMC2NSLLV3X3GPL7TQO33OKF.json","view_paper":"https://pith.science/paper/6NLMC2NS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.09349&json=true","fetch_graph":"https://pith.science/api/pith-number/6NLMC2NSLLV3X3GPL7TQO33OKF/graph.json","fetch_events":"https://pith.science/api/pith-number/6NLMC2NSLLV3X3GPL7TQO33OKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NLMC2NSLLV3X3GPL7TQO33OKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NLMC2NSLLV3X3GPL7TQO33OKF/action/storage_attestation","attest_author":"https://pith.science/pith/6NLMC2NSLLV3X3GPL7TQO33OKF/action/author_attestation","sign_citation":"https://pith.science/pith/6NLMC2NSLLV3X3GPL7TQO33OKF/action/citation_signature","submit_replication":"https://pith.science/pith/6NLMC2NSLLV3X3GPL7TQO33OKF/action/replication_record"}},"created_at":"2026-05-17T23:40:34.373096+00:00","updated_at":"2026-05-17T23:40:34.373096+00:00"}