{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5RWJKKVYMVCJJIH5G4H575EVF7","short_pith_number":"pith:5RWJKKVY","schema_version":"1.0","canonical_sha256":"ec6c952ab8654494a0fd370fdff4952fe720d40db49a558bd13fdd63440ee180","source":{"kind":"arxiv","id":"2105.04404","version":1},"attestation_state":"computed","paper":{"title":"Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Fr\\'ed\\'eric Chazal, Marc Glisse, Mathieu Carriere, Th\\'eo Lacombe (DATASHAPE), Yuhei Umeda, Yuichi Ike","submitted_at":"2021-05-07T14:16:03Z","abstract_excerpt":"Although neural networks are capable of reaching astonishing performances on a wide variety of contexts, properly training networks on complicated tasks requires expertise and can be expensive from a computational perspective. In industrial applications, data coming from an open-world setting might widely differ from the benchmark datasets on which a network was trained. Being able to monitor the presence of such variations without retraining the network is of crucial importance. In this article, we develop a method to monitor trained neural networks based on the topological properties of thei"},"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":"2105.04404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-05-07T14:16:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b370efbe5adf5aadf85c222fe71c1b2c81e555735fe1aa7a4bcb36e9651b3eca","abstract_canon_sha256":"78f234d8cfd1a70bb0b2f8275c7c6c037b1b81eb8e86cd88525be9a539668a7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:56.881611Z","signature_b64":"4G5eBERn/vg88V9npJmkhlalyMOx714hx/02M9GLFGdzS56EEyCuFvngPEwH4UCgGiAyoiFXjUs5pCHUjMIDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec6c952ab8654494a0fd370fdff4952fe720d40db49a558bd13fdd63440ee180","last_reissued_at":"2026-07-05T02:38:56.881157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:56.881157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Fr\\'ed\\'eric Chazal, Marc Glisse, Mathieu Carriere, Th\\'eo Lacombe (DATASHAPE), Yuhei Umeda, Yuichi Ike","submitted_at":"2021-05-07T14:16:03Z","abstract_excerpt":"Although neural networks are capable of reaching astonishing performances on a wide variety of contexts, properly training networks on complicated tasks requires expertise and can be expensive from a computational perspective. In industrial applications, data coming from an open-world setting might widely differ from the benchmark datasets on which a network was trained. Being able to monitor the presence of such variations without retraining the network is of crucial importance. In this article, we develop a method to monitor trained neural networks based on the topological properties of thei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04404","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/2105.04404/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":"2105.04404","created_at":"2026-07-05T02:38:56.881217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.04404v1","created_at":"2026-07-05T02:38:56.881217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04404","created_at":"2026-07-05T02:38:56.881217+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RWJKKVYMVCJ","created_at":"2026-07-05T02:38:56.881217+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RWJKKVYMVCJJIH5","created_at":"2026-07-05T02:38:56.881217+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RWJKKVY","created_at":"2026-07-05T02:38:56.881217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10996","citing_title":"Towards Scalable Persistence-Based Topological Optimization","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RWJKKVYMVCJJIH5G4H575EVF7","json":"https://pith.science/pith/5RWJKKVYMVCJJIH5G4H575EVF7.json","graph_json":"https://pith.science/api/pith-number/5RWJKKVYMVCJJIH5G4H575EVF7/graph.json","events_json":"https://pith.science/api/pith-number/5RWJKKVYMVCJJIH5G4H575EVF7/events.json","paper":"https://pith.science/paper/5RWJKKVY"},"agent_actions":{"view_html":"https://pith.science/pith/5RWJKKVYMVCJJIH5G4H575EVF7","download_json":"https://pith.science/pith/5RWJKKVYMVCJJIH5G4H575EVF7.json","view_paper":"https://pith.science/paper/5RWJKKVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.04404&json=true","fetch_graph":"https://pith.science/api/pith-number/5RWJKKVYMVCJJIH5G4H575EVF7/graph.json","fetch_events":"https://pith.science/api/pith-number/5RWJKKVYMVCJJIH5G4H575EVF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RWJKKVYMVCJJIH5G4H575EVF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RWJKKVYMVCJJIH5G4H575EVF7/action/storage_attestation","attest_author":"https://pith.science/pith/5RWJKKVYMVCJJIH5G4H575EVF7/action/author_attestation","sign_citation":"https://pith.science/pith/5RWJKKVYMVCJJIH5G4H575EVF7/action/citation_signature","submit_replication":"https://pith.science/pith/5RWJKKVYMVCJJIH5G4H575EVF7/action/replication_record"}},"created_at":"2026-07-05T02:38:56.881217+00:00","updated_at":"2026-07-05T02:38:56.881217+00:00"}