{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JGDYCBP7SNEYZUHBH7GO35W5KA","short_pith_number":"pith:JGDYCBP7","schema_version":"1.0","canonical_sha256":"49878105ff93498cd0e13fccedf6dd502675eeb4b7c6f9e7a2db31da86a747f8","source":{"kind":"arxiv","id":"2511.08307","version":2},"attestation_state":"computed","paper":{"title":"Concentration bounds on response-based vector embeddings of black-box generative models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aranyak Acharyya, Carey E. Priebe, Joshua Agterberg, Youngser Park","submitted_at":"2025-11-11T14:37:05Z","abstract_excerpt":"Generative models, such as large language models or text-to-image diffusion models, can generate relevant responses to user-given queries. Response-based vector embeddings of generative models facilitate statistical analysis and inference on a given collection of black-box generative models. The Data Kernel Perspective Space embedding is one particular method of obtaining response-based vector embeddings for a given set of generative models, already discussed in the literature. In this paper, under appropriate regularity conditions, we establish high probability concentration bounds on the sam"},"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":"2511.08307","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-11-11T14:37:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7c50299f2d53065bc403d4cddb7133c9c9b301014314619fa134fe165b4f36e","abstract_canon_sha256":"754821f38c73937e1290373dc32561d3575760b5e023497f0aa366b8475f2dc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:28.895924Z","signature_b64":"WAGk3Wbkk0UWAQ8/KXOPAOvijf17fsKaWMR8kOZ2QxK5GK6WY8Oxhg10zyrXsW2CbzDkMXcKCvPpPic+g7IMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49878105ff93498cd0e13fccedf6dd502675eeb4b7c6f9e7a2db31da86a747f8","last_reissued_at":"2026-06-30T01:17:28.894926Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:28.894926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concentration bounds on response-based vector embeddings of black-box generative models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aranyak Acharyya, Carey E. Priebe, Joshua Agterberg, Youngser Park","submitted_at":"2025-11-11T14:37:05Z","abstract_excerpt":"Generative models, such as large language models or text-to-image diffusion models, can generate relevant responses to user-given queries. Response-based vector embeddings of generative models facilitate statistical analysis and inference on a given collection of black-box generative models. The Data Kernel Perspective Space embedding is one particular method of obtaining response-based vector embeddings for a given set of generative models, already discussed in the literature. In this paper, under appropriate regularity conditions, we establish high probability concentration bounds on the sam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.08307","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/2511.08307/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":"2511.08307","created_at":"2026-06-30T01:17:28.895050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.08307v2","created_at":"2026-06-30T01:17:28.895050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.08307","created_at":"2026-06-30T01:17:28.895050+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGDYCBP7SNEY","created_at":"2026-06-30T01:17:28.895050+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGDYCBP7SNEYZUHB","created_at":"2026-06-30T01:17:28.895050+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGDYCBP7","created_at":"2026-06-30T01:17:28.895050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.07096","citing_title":"Query-efficient model evaluation using cached responses","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07011","citing_title":"Recovering manifold structure in LLM responses through a joint Euclidean mirror","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGDYCBP7SNEYZUHBH7GO35W5KA","json":"https://pith.science/pith/JGDYCBP7SNEYZUHBH7GO35W5KA.json","graph_json":"https://pith.science/api/pith-number/JGDYCBP7SNEYZUHBH7GO35W5KA/graph.json","events_json":"https://pith.science/api/pith-number/JGDYCBP7SNEYZUHBH7GO35W5KA/events.json","paper":"https://pith.science/paper/JGDYCBP7"},"agent_actions":{"view_html":"https://pith.science/pith/JGDYCBP7SNEYZUHBH7GO35W5KA","download_json":"https://pith.science/pith/JGDYCBP7SNEYZUHBH7GO35W5KA.json","view_paper":"https://pith.science/paper/JGDYCBP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.08307&json=true","fetch_graph":"https://pith.science/api/pith-number/JGDYCBP7SNEYZUHBH7GO35W5KA/graph.json","fetch_events":"https://pith.science/api/pith-number/JGDYCBP7SNEYZUHBH7GO35W5KA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGDYCBP7SNEYZUHBH7GO35W5KA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGDYCBP7SNEYZUHBH7GO35W5KA/action/storage_attestation","attest_author":"https://pith.science/pith/JGDYCBP7SNEYZUHBH7GO35W5KA/action/author_attestation","sign_citation":"https://pith.science/pith/JGDYCBP7SNEYZUHBH7GO35W5KA/action/citation_signature","submit_replication":"https://pith.science/pith/JGDYCBP7SNEYZUHBH7GO35W5KA/action/replication_record"}},"created_at":"2026-06-30T01:17:28.895050+00:00","updated_at":"2026-06-30T01:17:28.895050+00:00"}