{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DAWM2H3HIO4KFCLIFJ2EK2G2VQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c0644d8e610a95128ce7c89da57d039b1e4d973995f08beac063f927efa88636","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T13:31:54Z","title_canon_sha256":"bdc999284fce3d801f2d95646ae68e08fa5d086359c1242c2e4ebb8150ce0419"},"schema_version":"1.0","source":{"id":"2505.17883","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17883","created_at":"2026-07-05T11:08:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17883v1","created_at":"2026-07-05T11:08:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17883","created_at":"2026-07-05T11:08:33Z"},{"alias_kind":"pith_short_12","alias_value":"DAWM2H3HIO4K","created_at":"2026-07-05T11:08:33Z"},{"alias_kind":"pith_short_16","alias_value":"DAWM2H3HIO4KFCLI","created_at":"2026-07-05T11:08:33Z"},{"alias_kind":"pith_short_8","alias_value":"DAWM2H3H","created_at":"2026-07-05T11:08:33Z"}],"graph_snapshots":[{"event_id":"sha256:b8bc34aea400097c37eb0753bd84a37bdb2c9524f92e782451b250f70f14eea1","target":"graph","created_at":"2026-07-05T11:08:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.17883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Concepts such as objects, patterns, and shapes are how humans understand the world. Building on this intuition, concept-based explainability methods aim to study representations learned by deep neural networks in relation to human-understandable concepts. Here, Concept Activation Vectors (CAVs) are an important tool and can identify whether a model learned a concept or not. However, the computational cost and time requirements of existing CAV computation pose a significant challenge, particularly in large-scale, high-dimensional architectures. To address this limitation, we introduce FastCAV, ","authors_text":"Joachim Denzler, Julia Niebling, Laines Schmalwasser, Niklas Penzel","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T13:31:54Z","title":"FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17883","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5893ee7ab8f19732281f57b4388d3dbf072df61821a0f2c558fcda4750f01f22","target":"record","created_at":"2026-07-05T11:08:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c0644d8e610a95128ce7c89da57d039b1e4d973995f08beac063f927efa88636","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T13:31:54Z","title_canon_sha256":"bdc999284fce3d801f2d95646ae68e08fa5d086359c1242c2e4ebb8150ce0419"},"schema_version":"1.0","source":{"id":"2505.17883","kind":"arxiv","version":1}},"canonical_sha256":"182ccd1f6743b8a289682a744568daac06388158c40b76809daaa7f12947681d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"182ccd1f6743b8a289682a744568daac06388158c40b76809daaa7f12947681d","first_computed_at":"2026-07-05T11:08:33.285765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:33.285765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y+c5wBlEPFdD8p2Jc2qWcZFb38w4aAxbnlOh4dLnnMLiKipwtCmU99ym5ViLmvvR3jarsulI1iT7bvlD/j+IDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:33.286322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17883","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5893ee7ab8f19732281f57b4388d3dbf072df61821a0f2c558fcda4750f01f22","sha256:b8bc34aea400097c37eb0753bd84a37bdb2c9524f92e782451b250f70f14eea1"],"state_sha256":"403b42b9dec797fb8d2e796f146aec1b7b1a613319edda376d70f4f8eaf04d3d"}