{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3H6URVYD3QA7M2ESU5FJYEEIQX","short_pith_number":"pith:3H6URVYD","schema_version":"1.0","canonical_sha256":"d9fd48d703dc01f66892a74a9c108885c294d1550dd3a34c62e8b4ba0800f576","source":{"kind":"arxiv","id":"1912.06332","version":4},"attestation_state":"computed","paper":{"title":"TopoAct: Visually Exploring the Shape of Activations in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CG","authors_text":"Archit Rathore, Bei Wang, Nithin Chalapathi, Sourabh Palande","submitted_at":"2019-12-13T06:15:08Z","abstract_excerpt":"Deep neural networks such as GoogLeNet, ResNet, and BERT have achieved impressive performance in tasks such as image and text classification. To understand how such performance is achieved, we probe a trained deep neural network by studying neuron activations, i.e., combinations of neuron firings, at various layers of the network in response to a particular input. With a large number of inputs, we aim to obtain a global view of what neurons detect by studying their activations. In particular, we develop visualizations that show the shape of the activation space, the organizational principle be"},"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":"1912.06332","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CG","submitted_at":"2019-12-13T06:15:08Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"abaf9dbf08f2ed8e9c8d057621dc2ddea82d51a3619b826c68a98bdf1438759c","abstract_canon_sha256":"4c3951a7d6921de939270d635ece115b1aa4cd2df5fc481aae74e8086318b5e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:56.084701Z","signature_b64":"nokh6eh5p/dEzqFdvUArOwYeyDp4EEqyEpDtKmRvdpBwSlOo+mS9UKR8piMKLufcxX9e2bOvjUcMBuaF3Uk5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9fd48d703dc01f66892a74a9c108885c294d1550dd3a34c62e8b4ba0800f576","last_reissued_at":"2026-07-05T02:30:56.084215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:56.084215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TopoAct: Visually Exploring the Shape of Activations in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CG","authors_text":"Archit Rathore, Bei Wang, Nithin Chalapathi, Sourabh Palande","submitted_at":"2019-12-13T06:15:08Z","abstract_excerpt":"Deep neural networks such as GoogLeNet, ResNet, and BERT have achieved impressive performance in tasks such as image and text classification. To understand how such performance is achieved, we probe a trained deep neural network by studying neuron activations, i.e., combinations of neuron firings, at various layers of the network in response to a particular input. With a large number of inputs, we aim to obtain a global view of what neurons detect by studying their activations. In particular, we develop visualizations that show the shape of the activation space, the organizational principle be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06332","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.06332/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":"1912.06332","created_at":"2026-07-05T02:30:56.084274+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.06332v4","created_at":"2026-07-05T02:30:56.084274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06332","created_at":"2026-07-05T02:30:56.084274+00:00"},{"alias_kind":"pith_short_12","alias_value":"3H6URVYD3QA7","created_at":"2026-07-05T02:30:56.084274+00:00"},{"alias_kind":"pith_short_16","alias_value":"3H6URVYD3QA7M2ES","created_at":"2026-07-05T02:30:56.084274+00:00"},{"alias_kind":"pith_short_8","alias_value":"3H6URVYD","created_at":"2026-07-05T02:30:56.084274+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/3H6URVYD3QA7M2ESU5FJYEEIQX","json":"https://pith.science/pith/3H6URVYD3QA7M2ESU5FJYEEIQX.json","graph_json":"https://pith.science/api/pith-number/3H6URVYD3QA7M2ESU5FJYEEIQX/graph.json","events_json":"https://pith.science/api/pith-number/3H6URVYD3QA7M2ESU5FJYEEIQX/events.json","paper":"https://pith.science/paper/3H6URVYD"},"agent_actions":{"view_html":"https://pith.science/pith/3H6URVYD3QA7M2ESU5FJYEEIQX","download_json":"https://pith.science/pith/3H6URVYD3QA7M2ESU5FJYEEIQX.json","view_paper":"https://pith.science/paper/3H6URVYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.06332&json=true","fetch_graph":"https://pith.science/api/pith-number/3H6URVYD3QA7M2ESU5FJYEEIQX/graph.json","fetch_events":"https://pith.science/api/pith-number/3H6URVYD3QA7M2ESU5FJYEEIQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3H6URVYD3QA7M2ESU5FJYEEIQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3H6URVYD3QA7M2ESU5FJYEEIQX/action/storage_attestation","attest_author":"https://pith.science/pith/3H6URVYD3QA7M2ESU5FJYEEIQX/action/author_attestation","sign_citation":"https://pith.science/pith/3H6URVYD3QA7M2ESU5FJYEEIQX/action/citation_signature","submit_replication":"https://pith.science/pith/3H6URVYD3QA7M2ESU5FJYEEIQX/action/replication_record"}},"created_at":"2026-07-05T02:30:56.084274+00:00","updated_at":"2026-07-05T02:30:56.084274+00:00"}