{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7CROL6OY75RALCM3ZMZCDKBTU7","short_pith_number":"pith:7CROL6OY","schema_version":"1.0","canonical_sha256":"f8a2e5f9d8ff6205899bcb3221a833a7ce65cb561921fd66cd6cdc587e1cce7c","source":{"kind":"arxiv","id":"1901.09496","version":2},"attestation_state":"computed","paper":{"title":"Characterizing the Shape of Activation Space in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Hylton, Paul Schrater, Thomas Gebhart","submitted_at":"2019-01-28T03:10:56Z","abstract_excerpt":"The representations learned by deep neural networks are difficult to interpret in part due to their large parameter space and the complexities introduced by their multi-layer structure. We introduce a method for computing persistent homology over the graphical activation structure of neural networks, which provides access to the task-relevant substructures activated throughout the network for a given input. This topological perspective provides unique insights into the distributed representations encoded by neural networks in terms of the shape of their activation structures. We demonstrate th"},"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":"1901.09496","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T03:10:56Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"f561a56ae03b968b4918246e4c95492e0d0d75b4d2d7faed6ce0625156ff0763","abstract_canon_sha256":"db4bb3b0c83b84014a81b1cb28089ce62a211672824785d1d75b1f92fb6f6df0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:42.579515Z","signature_b64":"0CoyTo+r4GgoggvNLRezbQkWEeXuL+ndVU81l3gDKX8vVL4i9uF81Np9cAS81PyiiTBI+2B0MkvfaYHAGO+iDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8a2e5f9d8ff6205899bcb3221a833a7ce65cb561921fd66cd6cdc587e1cce7c","last_reissued_at":"2026-05-17T23:44:42.578995Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:42.578995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Characterizing the Shape of Activation Space in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Hylton, Paul Schrater, Thomas Gebhart","submitted_at":"2019-01-28T03:10:56Z","abstract_excerpt":"The representations learned by deep neural networks are difficult to interpret in part due to their large parameter space and the complexities introduced by their multi-layer structure. We introduce a method for computing persistent homology over the graphical activation structure of neural networks, which provides access to the task-relevant substructures activated throughout the network for a given input. This topological perspective provides unique insights into the distributed representations encoded by neural networks in terms of the shape of their activation structures. We demonstrate th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09496","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":"1901.09496","created_at":"2026-05-17T23:44:42.579078+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.09496v2","created_at":"2026-05-17T23:44:42.579078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09496","created_at":"2026-05-17T23:44:42.579078+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CROL6OY75RA","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CROL6OY75RALCM3","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CROL6OY","created_at":"2026-05-18T12:33:12.712433+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/7CROL6OY75RALCM3ZMZCDKBTU7","json":"https://pith.science/pith/7CROL6OY75RALCM3ZMZCDKBTU7.json","graph_json":"https://pith.science/api/pith-number/7CROL6OY75RALCM3ZMZCDKBTU7/graph.json","events_json":"https://pith.science/api/pith-number/7CROL6OY75RALCM3ZMZCDKBTU7/events.json","paper":"https://pith.science/paper/7CROL6OY"},"agent_actions":{"view_html":"https://pith.science/pith/7CROL6OY75RALCM3ZMZCDKBTU7","download_json":"https://pith.science/pith/7CROL6OY75RALCM3ZMZCDKBTU7.json","view_paper":"https://pith.science/paper/7CROL6OY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.09496&json=true","fetch_graph":"https://pith.science/api/pith-number/7CROL6OY75RALCM3ZMZCDKBTU7/graph.json","fetch_events":"https://pith.science/api/pith-number/7CROL6OY75RALCM3ZMZCDKBTU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CROL6OY75RALCM3ZMZCDKBTU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CROL6OY75RALCM3ZMZCDKBTU7/action/storage_attestation","attest_author":"https://pith.science/pith/7CROL6OY75RALCM3ZMZCDKBTU7/action/author_attestation","sign_citation":"https://pith.science/pith/7CROL6OY75RALCM3ZMZCDKBTU7/action/citation_signature","submit_replication":"https://pith.science/pith/7CROL6OY75RALCM3ZMZCDKBTU7/action/replication_record"}},"created_at":"2026-05-17T23:44:42.579078+00:00","updated_at":"2026-05-17T23:44:42.579078+00:00"}