{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HWOR3U2ATQSSWABPZUT2T67RHR","short_pith_number":"pith:HWOR3U2A","schema_version":"1.0","canonical_sha256":"3d9d1dd3409c252b002fcd27a9fbf13c57587b873954381f18f30a87f5cf8cf9","source":{"kind":"arxiv","id":"2408.09065","version":1},"attestation_state":"computed","paper":{"title":"Linking Robustness and Generalization: A k* Distribution Analysis of Concept Clustering in Latent Space for Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Danilo Vasconcellos Vargas, Pin-Yu Chen, Shashank Kotyan","submitted_at":"2024-08-17T01:43:51Z","abstract_excerpt":"Most evaluations of vision models use indirect methods to assess latent space quality. These methods often involve adding extra layers to project the latent space into a new one. This projection makes it difficult to analyze and compare the original latent space. This article uses the k* Distribution, a local neighborhood analysis method, to examine the learned latent space at the level of individual concepts, which can be extended to examine the entire latent space. We introduce skewness-based true and approximate metrics for interpreting individual concepts to assess the overall quality of v"},"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":"2408.09065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-17T01:43:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2c3161ca7189e9a95422b16954d9e18a13a97e77094da9f91717d2675d943c9d","abstract_canon_sha256":"0acd067a854eadd3633ab5b8666423e7aec572113895670935b0a33014431678"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:27.486996Z","signature_b64":"QCM0fWJhwPcaQzNQ3wzDtWEGjm2JN+xvV+5AeBgWVmjyNs54SnUe+yzHQ+62hM/Uq1fadKqyyWiMjUrQqKOUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d9d1dd3409c252b002fcd27a9fbf13c57587b873954381f18f30a87f5cf8cf9","last_reissued_at":"2026-07-05T08:56:27.486627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:27.486627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linking Robustness and Generalization: A k* Distribution Analysis of Concept Clustering in Latent Space for Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Danilo Vasconcellos Vargas, Pin-Yu Chen, Shashank Kotyan","submitted_at":"2024-08-17T01:43:51Z","abstract_excerpt":"Most evaluations of vision models use indirect methods to assess latent space quality. These methods often involve adding extra layers to project the latent space into a new one. This projection makes it difficult to analyze and compare the original latent space. This article uses the k* Distribution, a local neighborhood analysis method, to examine the learned latent space at the level of individual concepts, which can be extended to examine the entire latent space. We introduce skewness-based true and approximate metrics for interpreting individual concepts to assess the overall quality of v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09065","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/2408.09065/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":"2408.09065","created_at":"2026-07-05T08:56:27.486683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09065v1","created_at":"2026-07-05T08:56:27.486683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09065","created_at":"2026-07-05T08:56:27.486683+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWOR3U2ATQSS","created_at":"2026-07-05T08:56:27.486683+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWOR3U2ATQSSWABP","created_at":"2026-07-05T08:56:27.486683+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWOR3U2A","created_at":"2026-07-05T08:56:27.486683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08515","citing_title":"Enhancing Interpretability Through Loss-Defined Classification Objective in Structured Latent Spaces","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWOR3U2ATQSSWABPZUT2T67RHR","json":"https://pith.science/pith/HWOR3U2ATQSSWABPZUT2T67RHR.json","graph_json":"https://pith.science/api/pith-number/HWOR3U2ATQSSWABPZUT2T67RHR/graph.json","events_json":"https://pith.science/api/pith-number/HWOR3U2ATQSSWABPZUT2T67RHR/events.json","paper":"https://pith.science/paper/HWOR3U2A"},"agent_actions":{"view_html":"https://pith.science/pith/HWOR3U2ATQSSWABPZUT2T67RHR","download_json":"https://pith.science/pith/HWOR3U2ATQSSWABPZUT2T67RHR.json","view_paper":"https://pith.science/paper/HWOR3U2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09065&json=true","fetch_graph":"https://pith.science/api/pith-number/HWOR3U2ATQSSWABPZUT2T67RHR/graph.json","fetch_events":"https://pith.science/api/pith-number/HWOR3U2ATQSSWABPZUT2T67RHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWOR3U2ATQSSWABPZUT2T67RHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWOR3U2ATQSSWABPZUT2T67RHR/action/storage_attestation","attest_author":"https://pith.science/pith/HWOR3U2ATQSSWABPZUT2T67RHR/action/author_attestation","sign_citation":"https://pith.science/pith/HWOR3U2ATQSSWABPZUT2T67RHR/action/citation_signature","submit_replication":"https://pith.science/pith/HWOR3U2ATQSSWABPZUT2T67RHR/action/replication_record"}},"created_at":"2026-07-05T08:56:27.486683+00:00","updated_at":"2026-07-05T08:56:27.486683+00:00"}