{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:D2P4AIIVPV4OKPKHYIPFVLFYUT","short_pith_number":"pith:D2P4AIIV","schema_version":"1.0","canonical_sha256":"1e9fc021157d78e53d47c21e5aacb8a4f03a88219c230edff9c4a500efe7290e","source":{"kind":"arxiv","id":"2206.09798","version":2},"attestation_state":"computed","paper":{"title":"Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Mohamadsadegh Khosravani, Sandra Zilles","submitted_at":"2022-06-20T14:28:19Z","abstract_excerpt":"The success of deep active learning hinges on the choice of an effective acquisition function, which ranks not yet labeled data points according to their expected informativeness. Many acquisition functions are (partly) based on the uncertainty that the current model has about the class label of a point, yet there is no generally agreed upon strategy for computing such uncertainty. This paper proposes a new and very simple approach to computing uncertainty in deep active learning with a Convolutional Neural Network (CNN). The main idea is to use the feature representation extracted by the CNN "},"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":"2206.09798","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-20T14:28:19Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"87efe780fcfc8826229dd4be5a24263d4eddc38a1a5dce51b019b74dfc54d931","abstract_canon_sha256":"f3b91f5213d314b80b055ff4660d30fb6400830eeecb697975ba469bc84c82c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:42.750368Z","signature_b64":"td7WKEuQ8Gz+utXFbUUg8M4jpkw80v9grevUAjCmFvbNGQQvmEmqjCiauIz/jYMvBRqifpfyX6GHEX9IoCaKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e9fc021157d78e53d47c21e5aacb8a4f03a88219c230edff9c4a500efe7290e","last_reissued_at":"2026-07-05T07:09:42.749796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:42.749796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Mohamadsadegh Khosravani, Sandra Zilles","submitted_at":"2022-06-20T14:28:19Z","abstract_excerpt":"The success of deep active learning hinges on the choice of an effective acquisition function, which ranks not yet labeled data points according to their expected informativeness. Many acquisition functions are (partly) based on the uncertainty that the current model has about the class label of a point, yet there is no generally agreed upon strategy for computing such uncertainty. This paper proposes a new and very simple approach to computing uncertainty in deep active learning with a Convolutional Neural Network (CNN). The main idea is to use the feature representation extracted by the CNN "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09798","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.09798/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":"2206.09798","created_at":"2026-07-05T07:09:42.749856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09798v2","created_at":"2026-07-05T07:09:42.749856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09798","created_at":"2026-07-05T07:09:42.749856+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2P4AIIVPV4O","created_at":"2026-07-05T07:09:42.749856+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2P4AIIVPV4OKPKH","created_at":"2026-07-05T07:09:42.749856+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2P4AIIV","created_at":"2026-07-05T07:09:42.749856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22813","citing_title":"X-Factor: Quality Is a Dataset-Intrinsic Property","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2P4AIIVPV4OKPKHYIPFVLFYUT","json":"https://pith.science/pith/D2P4AIIVPV4OKPKHYIPFVLFYUT.json","graph_json":"https://pith.science/api/pith-number/D2P4AIIVPV4OKPKHYIPFVLFYUT/graph.json","events_json":"https://pith.science/api/pith-number/D2P4AIIVPV4OKPKHYIPFVLFYUT/events.json","paper":"https://pith.science/paper/D2P4AIIV"},"agent_actions":{"view_html":"https://pith.science/pith/D2P4AIIVPV4OKPKHYIPFVLFYUT","download_json":"https://pith.science/pith/D2P4AIIVPV4OKPKHYIPFVLFYUT.json","view_paper":"https://pith.science/paper/D2P4AIIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09798&json=true","fetch_graph":"https://pith.science/api/pith-number/D2P4AIIVPV4OKPKHYIPFVLFYUT/graph.json","fetch_events":"https://pith.science/api/pith-number/D2P4AIIVPV4OKPKHYIPFVLFYUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2P4AIIVPV4OKPKHYIPFVLFYUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2P4AIIVPV4OKPKHYIPFVLFYUT/action/storage_attestation","attest_author":"https://pith.science/pith/D2P4AIIVPV4OKPKHYIPFVLFYUT/action/author_attestation","sign_citation":"https://pith.science/pith/D2P4AIIVPV4OKPKHYIPFVLFYUT/action/citation_signature","submit_replication":"https://pith.science/pith/D2P4AIIVPV4OKPKHYIPFVLFYUT/action/replication_record"}},"created_at":"2026-07-05T07:09:42.749856+00:00","updated_at":"2026-07-05T07:09:42.749856+00:00"}