{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G5ARZNV23WKWMVLGI6H6A4P4C7","short_pith_number":"pith:G5ARZNV2","canonical_record":{"source":{"id":"2505.05163","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T11:57:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0b602d10b53b25562abea3754a1042e464f7f92d9bbb7dd0b25c5d0ecf5a349a","abstract_canon_sha256":"e4923970648249cb09a7b11248d5c53203dcb645cd1678b900d1e6d0e0514a32"},"schema_version":"1.0"},"canonical_sha256":"37411cb6badd95665566478fe071fc17c1d4250fdd5cede7a0ace26c8005fcec","source":{"kind":"arxiv","id":"2505.05163","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05163","created_at":"2026-07-05T11:31:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05163v2","created_at":"2026-07-05T11:31:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05163","created_at":"2026-07-05T11:31:45Z"},{"alias_kind":"pith_short_12","alias_value":"G5ARZNV23WKW","created_at":"2026-07-05T11:31:45Z"},{"alias_kind":"pith_short_16","alias_value":"G5ARZNV23WKWMVLG","created_at":"2026-07-05T11:31:45Z"},{"alias_kind":"pith_short_8","alias_value":"G5ARZNV2","created_at":"2026-07-05T11:31:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G5ARZNV23WKWMVLGI6H6A4P4C7","target":"record","payload":{"canonical_record":{"source":{"id":"2505.05163","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T11:57:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0b602d10b53b25562abea3754a1042e464f7f92d9bbb7dd0b25c5d0ecf5a349a","abstract_canon_sha256":"e4923970648249cb09a7b11248d5c53203dcb645cd1678b900d1e6d0e0514a32"},"schema_version":"1.0"},"canonical_sha256":"37411cb6badd95665566478fe071fc17c1d4250fdd5cede7a0ace26c8005fcec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:45.194658Z","signature_b64":"qI4XhSIuabK/oDctq6Phm1wlLgoW0PGnXhm7yY3YpDOjwk7xSHDbAEkd7bYY5Ar9zCilX/Mq+ZPx1BbEs6dNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37411cb6badd95665566478fe071fc17c1d4250fdd5cede7a0ace26c8005fcec","last_reissued_at":"2026-07-05T11:31:45.194179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:45.194179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.05163","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f610MmcexSkzjhxcLUFpAKl7/HQ3hZmdLglLvqkdoEhsb1lkg9UKTnqt/H0E/RPkFtQSDpi0FoF6E1ae1sVNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:41:59.952058Z"},"content_sha256":"27ac014d3ea68836938b2a03f6da1999a637c133376545e175343901aee29ff1","schema_version":"1.0","event_id":"sha256:27ac014d3ea68836938b2a03f6da1999a637c133376545e175343901aee29ff1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G5ARZNV23WKWMVLGI6H6A4P4C7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aishwarya Venkataramanan, Joachim Denzler, Paul Bodesheim","submitted_at":"2025-05-08T11:57:35Z","abstract_excerpt":"Vision-Language Models (VLMs) learn joint representations by mapping images and text into a shared latent space. However, recent research highlights that deterministic embeddings from standard VLMs often struggle to capture the uncertainties arising from the ambiguities in visual and textual descriptions and the multiple possible correspondences between images and texts. Existing approaches tackle this by learning probabilistic embeddings during VLM training, which demands large datasets and does not leverage the powerful representations already learned by large-scale VLMs like CLIP. In this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05163","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/2505.05163/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZUth2TzDnMm0psPmRP6fBa8qAuHZVtvN8dDY4Kl4lVvOk+L6DysgEA/XKe5D1Mf56/rOcOxuwT7s2B7mR4QyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:41:59.952451Z"},"content_sha256":"a539195be70ee093fddc2fc29889041f91ff4b792dda7f1ae880cb894a6bf73f","schema_version":"1.0","event_id":"sha256:a539195be70ee093fddc2fc29889041f91ff4b792dda7f1ae880cb894a6bf73f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5ARZNV23WKWMVLGI6H6A4P4C7/bundle.json","state_url":"https://pith.science/pith/G5ARZNV23WKWMVLGI6H6A4P4C7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5ARZNV23WKWMVLGI6H6A4P4C7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T11:41:59Z","links":{"resolver":"https://pith.science/pith/G5ARZNV23WKWMVLGI6H6A4P4C7","bundle":"https://pith.science/pith/G5ARZNV23WKWMVLGI6H6A4P4C7/bundle.json","state":"https://pith.science/pith/G5ARZNV23WKWMVLGI6H6A4P4C7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5ARZNV23WKWMVLGI6H6A4P4C7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G5ARZNV23WKWMVLGI6H6A4P4C7","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":"e4923970648249cb09a7b11248d5c53203dcb645cd1678b900d1e6d0e0514a32","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T11:57:35Z","title_canon_sha256":"0b602d10b53b25562abea3754a1042e464f7f92d9bbb7dd0b25c5d0ecf5a349a"},"schema_version":"1.0","source":{"id":"2505.05163","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05163","created_at":"2026-07-05T11:31:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05163v2","created_at":"2026-07-05T11:31:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05163","created_at":"2026-07-05T11:31:45Z"},{"alias_kind":"pith_short_12","alias_value":"G5ARZNV23WKW","created_at":"2026-07-05T11:31:45Z"},{"alias_kind":"pith_short_16","alias_value":"G5ARZNV23WKWMVLG","created_at":"2026-07-05T11:31:45Z"},{"alias_kind":"pith_short_8","alias_value":"G5ARZNV2","created_at":"2026-07-05T11:31:45Z"}],"graph_snapshots":[{"event_id":"sha256:a539195be70ee093fddc2fc29889041f91ff4b792dda7f1ae880cb894a6bf73f","target":"graph","created_at":"2026-07-05T11:31:45Z","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/2505.05163/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) learn joint representations by mapping images and text into a shared latent space. However, recent research highlights that deterministic embeddings from standard VLMs often struggle to capture the uncertainties arising from the ambiguities in visual and textual descriptions and the multiple possible correspondences between images and texts. Existing approaches tackle this by learning probabilistic embeddings during VLM training, which demands large datasets and does not leverage the powerful representations already learned by large-scale VLMs like CLIP. In this p","authors_text":"Aishwarya Venkataramanan, Joachim Denzler, Paul Bodesheim","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T11:57:35Z","title":"Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05163","kind":"arxiv","version":2},"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":"sha256:27ac014d3ea68836938b2a03f6da1999a637c133376545e175343901aee29ff1","target":"record","created_at":"2026-07-05T11:31:45Z","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":"e4923970648249cb09a7b11248d5c53203dcb645cd1678b900d1e6d0e0514a32","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T11:57:35Z","title_canon_sha256":"0b602d10b53b25562abea3754a1042e464f7f92d9bbb7dd0b25c5d0ecf5a349a"},"schema_version":"1.0","source":{"id":"2505.05163","kind":"arxiv","version":2}},"canonical_sha256":"37411cb6badd95665566478fe071fc17c1d4250fdd5cede7a0ace26c8005fcec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37411cb6badd95665566478fe071fc17c1d4250fdd5cede7a0ace26c8005fcec","first_computed_at":"2026-07-05T11:31:45.194179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:45.194179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qI4XhSIuabK/oDctq6Phm1wlLgoW0PGnXhm7yY3YpDOjwk7xSHDbAEkd7bYY5Ar9zCilX/Mq+ZPx1BbEs6dNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:45.194658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05163","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27ac014d3ea68836938b2a03f6da1999a637c133376545e175343901aee29ff1","sha256:a539195be70ee093fddc2fc29889041f91ff4b792dda7f1ae880cb894a6bf73f"],"state_sha256":"71dda3aca6f331c8ef8d2f53d3eb80de64c4dfe2085039e02c0637f10ae2370f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lzVz8ymu6YaTRMJu8r6dd8mpU26D83bpPXzDpoLt6t9efn04hzW7dIP5tCFNA+u7VNBcQ71WBt/wMckkbZi2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:41:59.954352Z","bundle_sha256":"432470cfcd28cd792dbbd60772fa05ac8369eafcb390b08389c6e0b3522972f7"}}