{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IV5NPF2QXKIA5G5SEHK6GWZAVU","short_pith_number":"pith:IV5NPF2Q","schema_version":"1.0","canonical_sha256":"457ad79750ba900e9bb221d5e35b20ad0daf18d959869646160ebae9f22472ad","source":{"kind":"arxiv","id":"1810.11750","version":2},"attestation_state":"computed","paper":{"title":"Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiayuan Gu, John Hopcroft, Kun He, Liwei Wang, Lunjia Hu, Yue Wu, Zhiqiang Hu","submitted_at":"2018-10-28T02:27:31Z","abstract_excerpt":"It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory and systematic approach quantitatively characterizing what representations do deep neural networks learn. In this work, we move a tiny step towards a theory and better understanding of the representations. Specifically, we study a simpler problem: How similar are the representations learned by two networks with identical architecture but trained from different initializations. We develop a rigorous theory based on the "},"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":"1810.11750","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-28T02:27:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ddb1a13aea11a5e79320fadfd5ec75a4a40e647f6770b906f9ffa3132416aa1a","abstract_canon_sha256":"bd4b1494e069c57c855eb14ec37fd066188eb2a23d200eaf5e7f5f91f71ad63c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:38.042822Z","signature_b64":"6psPVqRu4ZZ8GEvPyxr2hmQPtcJaP4XWLlFbqVOOp+VF1Ov+hRU6x0EyUM5eUxNxvaVW6qESUeumaQEu/tufDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457ad79750ba900e9bb221d5e35b20ad0daf18d959869646160ebae9f22472ad","last_reissued_at":"2026-05-17T23:59:38.042226Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:38.042226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiayuan Gu, John Hopcroft, Kun He, Liwei Wang, Lunjia Hu, Yue Wu, Zhiqiang Hu","submitted_at":"2018-10-28T02:27:31Z","abstract_excerpt":"It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory and systematic approach quantitatively characterizing what representations do deep neural networks learn. In this work, we move a tiny step towards a theory and better understanding of the representations. Specifically, we study a simpler problem: How similar are the representations learned by two networks with identical architecture but trained from different initializations. We develop a rigorous theory based on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11750","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":""},"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":"1810.11750","created_at":"2026-05-17T23:59:38.042330+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.11750v2","created_at":"2026-05-17T23:59:38.042330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11750","created_at":"2026-05-17T23:59:38.042330+00:00"},{"alias_kind":"pith_short_12","alias_value":"IV5NPF2QXKIA","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IV5NPF2QXKIA5G5S","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IV5NPF2Q","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06501","citing_title":"Computing with Canonical Microcircuits","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IV5NPF2QXKIA5G5SEHK6GWZAVU","json":"https://pith.science/pith/IV5NPF2QXKIA5G5SEHK6GWZAVU.json","graph_json":"https://pith.science/api/pith-number/IV5NPF2QXKIA5G5SEHK6GWZAVU/graph.json","events_json":"https://pith.science/api/pith-number/IV5NPF2QXKIA5G5SEHK6GWZAVU/events.json","paper":"https://pith.science/paper/IV5NPF2Q"},"agent_actions":{"view_html":"https://pith.science/pith/IV5NPF2QXKIA5G5SEHK6GWZAVU","download_json":"https://pith.science/pith/IV5NPF2QXKIA5G5SEHK6GWZAVU.json","view_paper":"https://pith.science/paper/IV5NPF2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.11750&json=true","fetch_graph":"https://pith.science/api/pith-number/IV5NPF2QXKIA5G5SEHK6GWZAVU/graph.json","fetch_events":"https://pith.science/api/pith-number/IV5NPF2QXKIA5G5SEHK6GWZAVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IV5NPF2QXKIA5G5SEHK6GWZAVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IV5NPF2QXKIA5G5SEHK6GWZAVU/action/storage_attestation","attest_author":"https://pith.science/pith/IV5NPF2QXKIA5G5SEHK6GWZAVU/action/author_attestation","sign_citation":"https://pith.science/pith/IV5NPF2QXKIA5G5SEHK6GWZAVU/action/citation_signature","submit_replication":"https://pith.science/pith/IV5NPF2QXKIA5G5SEHK6GWZAVU/action/replication_record"}},"created_at":"2026-05-17T23:59:38.042330+00:00","updated_at":"2026-05-17T23:59:38.042330+00:00"}