{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5JFGZXDZEH6HFLHSJ4BS4XCYGF","short_pith_number":"pith:5JFGZXDZ","schema_version":"1.0","canonical_sha256":"ea4a6cdc7921fc72acf24f032e5c58314aeb95a0c1112293814db3b7416e23b7","source":{"kind":"arxiv","id":"2603.26798","version":2},"attestation_state":"computed","paper":{"title":"Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Annika M\\\"utze, Diedrich Wolter, Edgar Heinert, Georgii Mikriukov, Gesina Schwalbe, Jae Hee Lee, Marvin Keller, Matthias Rottmann, Mert Keser, Moritz Bayerkuhnlein, Sparsh Tiwari","submitted_at":"2026-03-26T00:38:38Z","abstract_excerpt":"Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected. We present a post-hoc framework to explain, verify, and align the semantic hierarchies induced by a VLM over a given set of child classes. First, we extract a binary hierarchy by agglomerative clustering of class centroids and name internal nodes by dictionary-based matching to a concept bank. Second, we quantify plausibility by comparing the extracted tree against human ontologies using e"},"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":"2603.26798","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-26T00:38:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"634ff50ee8b064b5ee795d4a9a6a68178a7654dab72bae1ca4aae58cb5438fa9","abstract_canon_sha256":"e18086f9951e80f6e423c7ee4aeaed24570ee36f833c5239884114a7557fd993"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:24:42.138006Z","signature_b64":"h/oVkrD7WTVjkccqK3rcVqQ9e83/SLe2Ri5JGIUTld+QyPS6Vz8IvcDi6akVEZjqghrcubLBAOxyEQApevueBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea4a6cdc7921fc72acf24f032e5c58314aeb95a0c1112293814db3b7416e23b7","last_reissued_at":"2026-08-11T01:24:42.135323Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:24:42.135323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Annika M\\\"utze, Diedrich Wolter, Edgar Heinert, Georgii Mikriukov, Gesina Schwalbe, Jae Hee Lee, Marvin Keller, Matthias Rottmann, Mert Keser, Moritz Bayerkuhnlein, Sparsh Tiwari","submitted_at":"2026-03-26T00:38:38Z","abstract_excerpt":"Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected. We present a post-hoc framework to explain, verify, and align the semantic hierarchies induced by a VLM over a given set of child classes. First, we extract a binary hierarchy by agglomerative clustering of class centroids and name internal nodes by dictionary-based matching to a concept bank. Second, we quantify plausibility by comparing the extracted tree against human ontologies using e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.26798","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/2603.26798/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":"2603.26798","created_at":"2026-08-11T01:24:42.136189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.26798v2","created_at":"2026-08-11T01:24:42.136189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.26798","created_at":"2026-08-11T01:24:42.136189+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JFGZXDZEH6H","created_at":"2026-08-11T01:24:42.136189+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JFGZXDZEH6HFLHS","created_at":"2026-08-11T01:24:42.136189+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JFGZXDZ","created_at":"2026-08-11T01:24:42.136189+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/5JFGZXDZEH6HFLHSJ4BS4XCYGF","json":"https://pith.science/pith/5JFGZXDZEH6HFLHSJ4BS4XCYGF.json","graph_json":"https://pith.science/api/pith-number/5JFGZXDZEH6HFLHSJ4BS4XCYGF/graph.json","events_json":"https://pith.science/api/pith-number/5JFGZXDZEH6HFLHSJ4BS4XCYGF/events.json","paper":"https://pith.science/paper/5JFGZXDZ"},"agent_actions":{"view_html":"https://pith.science/pith/5JFGZXDZEH6HFLHSJ4BS4XCYGF","download_json":"https://pith.science/pith/5JFGZXDZEH6HFLHSJ4BS4XCYGF.json","view_paper":"https://pith.science/paper/5JFGZXDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.26798&json=true","fetch_graph":"https://pith.science/api/pith-number/5JFGZXDZEH6HFLHSJ4BS4XCYGF/graph.json","fetch_events":"https://pith.science/api/pith-number/5JFGZXDZEH6HFLHSJ4BS4XCYGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JFGZXDZEH6HFLHSJ4BS4XCYGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JFGZXDZEH6HFLHSJ4BS4XCYGF/action/storage_attestation","attest_author":"https://pith.science/pith/5JFGZXDZEH6HFLHSJ4BS4XCYGF/action/author_attestation","sign_citation":"https://pith.science/pith/5JFGZXDZEH6HFLHSJ4BS4XCYGF/action/citation_signature","submit_replication":"https://pith.science/pith/5JFGZXDZEH6HFLHSJ4BS4XCYGF/action/replication_record"}},"created_at":"2026-08-11T01:24:42.136189+00:00","updated_at":"2026-08-11T01:24:42.136189+00:00"}