{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:M7KIF4XUWFD6VVQJLSEKV72MWR","short_pith_number":"pith:M7KIF4XU","schema_version":"1.0","canonical_sha256":"67d482f2f4b147ead6095c88aaff4cb46a2a8095805ca7f780f84bef62fd4268","source":{"kind":"arxiv","id":"1908.02831","version":1},"attestation_state":"computed","paper":{"title":"Visualizing the PHATE of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam S. Charles, Gal Mishne, Scott Gigante, Smita Krishnaswamy","submitted_at":"2019-08-07T20:53:30Z","abstract_excerpt":"Understanding why and how certain neural networks outperform others is key to guiding future development of network architectures and optimization methods. To this end, we introduce a novel visualization algorithm that reveals the internal geometry of such networks: Multislice PHATE (M-PHATE), the first method designed explicitly to visualize how a neural network's hidden representations of data evolve throughout the course of training. We demonstrate that our visualization provides intuitive, detailed summaries of the learning dynamics beyond simple global measures (i.e., validation loss and "},"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":"1908.02831","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-07T20:53:30Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"9fe6a26862f46763da42c8d8eda1f705c3baf9f010a41b71f102fbbc2a95643b","abstract_canon_sha256":"13e7ba8fed8f60c588b7bb15223c01e589f182ddff2874f2743cc5be635faa08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:06.585647Z","signature_b64":"47I+L80ajpQPQGArzFPbOITZpUspj5amAf9l6VGhXIJswI3inlbinCSMTheaa3466Bu0nxL/Kq6oFgSuXCQWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67d482f2f4b147ead6095c88aaff4cb46a2a8095805ca7f780f84bef62fd4268","last_reissued_at":"2026-07-05T00:23:06.585232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:06.585232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visualizing the PHATE of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam S. Charles, Gal Mishne, Scott Gigante, Smita Krishnaswamy","submitted_at":"2019-08-07T20:53:30Z","abstract_excerpt":"Understanding why and how certain neural networks outperform others is key to guiding future development of network architectures and optimization methods. To this end, we introduce a novel visualization algorithm that reveals the internal geometry of such networks: Multislice PHATE (M-PHATE), the first method designed explicitly to visualize how a neural network's hidden representations of data evolve throughout the course of training. We demonstrate that our visualization provides intuitive, detailed summaries of the learning dynamics beyond simple global measures (i.e., validation loss and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02831","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/1908.02831/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":"1908.02831","created_at":"2026-07-05T00:23:06.585288+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.02831v1","created_at":"2026-07-05T00:23:06.585288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02831","created_at":"2026-07-05T00:23:06.585288+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7KIF4XUWFD6","created_at":"2026-07-05T00:23:06.585288+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7KIF4XUWFD6VVQJ","created_at":"2026-07-05T00:23:06.585288+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7KIF4XU","created_at":"2026-07-05T00:23:06.585288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15901","citing_title":"From Layers to Networks: Comparing Neural Representations via Diffusion Geometry","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7KIF4XUWFD6VVQJLSEKV72MWR","json":"https://pith.science/pith/M7KIF4XUWFD6VVQJLSEKV72MWR.json","graph_json":"https://pith.science/api/pith-number/M7KIF4XUWFD6VVQJLSEKV72MWR/graph.json","events_json":"https://pith.science/api/pith-number/M7KIF4XUWFD6VVQJLSEKV72MWR/events.json","paper":"https://pith.science/paper/M7KIF4XU"},"agent_actions":{"view_html":"https://pith.science/pith/M7KIF4XUWFD6VVQJLSEKV72MWR","download_json":"https://pith.science/pith/M7KIF4XUWFD6VVQJLSEKV72MWR.json","view_paper":"https://pith.science/paper/M7KIF4XU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.02831&json=true","fetch_graph":"https://pith.science/api/pith-number/M7KIF4XUWFD6VVQJLSEKV72MWR/graph.json","fetch_events":"https://pith.science/api/pith-number/M7KIF4XUWFD6VVQJLSEKV72MWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7KIF4XUWFD6VVQJLSEKV72MWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7KIF4XUWFD6VVQJLSEKV72MWR/action/storage_attestation","attest_author":"https://pith.science/pith/M7KIF4XUWFD6VVQJLSEKV72MWR/action/author_attestation","sign_citation":"https://pith.science/pith/M7KIF4XUWFD6VVQJLSEKV72MWR/action/citation_signature","submit_replication":"https://pith.science/pith/M7KIF4XUWFD6VVQJLSEKV72MWR/action/replication_record"}},"created_at":"2026-07-05T00:23:06.585288+00:00","updated_at":"2026-07-05T00:23:06.585288+00:00"}