{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JEUOOXQUPSSSRDZYMKPI7O3D2F","short_pith_number":"pith:JEUOOXQU","schema_version":"1.0","canonical_sha256":"4928e75e147ca5288f38629e8fbb63d14d3bad9605c03507d2930bcf8d089db8","source":{"kind":"arxiv","id":"2608.09011","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ao Zhou, Cong Wang, Haoru Chen, Qing Gu, Shufan Yang, Zhiwei Jiang, Zifeng Cheng","submitted_at":"2026-08-10T01:53:28Z","abstract_excerpt":"Uncertainty Quantification (UQ) aims to measure the reliability of model predictions, serving as a critical safeguard for deploying Vision-Language Models (VLMs) in safety-critical scenarios. Post-hoc approaches are widely adopted due to their lightweight nature, mapping the outputs of VLMs to uncertainty measures through learnable modules or inductive summarization. However, Post-hoc approaches remain inherently confined to fitting the failure patterns of the source domain, ignoring the dynamic nature of test distributions. To address this challenge, we propose a Dynamic Distribution-Aware Un"},"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":"2608.09011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T01:53:28Z","cross_cats_sorted":[],"title_canon_sha256":"c8fa3cac8829f468b58a342b569c8ed6f848619b91c03947388ae87c5f5f509f","abstract_canon_sha256":"70bacdeb1f7fe8ca1b22f7d36a27b23234dc13e7fe9449ad3ae4276db6706e60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:25:58.291342Z","signature_b64":"nGwVPsW8WGGC6+alqxAhRs3il27j1KZwnJyBsGwBJlFnGnDPwnohunYYFlnAX8GLJlAJeSZVyd+L/QSof94hBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4928e75e147ca5288f38629e8fbb63d14d3bad9605c03507d2930bcf8d089db8","last_reissued_at":"2026-08-11T01:25:58.288771Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:25:58.288771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ao Zhou, Cong Wang, Haoru Chen, Qing Gu, Shufan Yang, Zhiwei Jiang, Zifeng Cheng","submitted_at":"2026-08-10T01:53:28Z","abstract_excerpt":"Uncertainty Quantification (UQ) aims to measure the reliability of model predictions, serving as a critical safeguard for deploying Vision-Language Models (VLMs) in safety-critical scenarios. Post-hoc approaches are widely adopted due to their lightweight nature, mapping the outputs of VLMs to uncertainty measures through learnable modules or inductive summarization. However, Post-hoc approaches remain inherently confined to fitting the failure patterns of the source domain, ignoring the dynamic nature of test distributions. To address this challenge, we propose a Dynamic Distribution-Aware Un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09011","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/2608.09011/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":"2608.09011","created_at":"2026-08-11T01:25:58.289723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09011v1","created_at":"2026-08-11T01:25:58.289723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09011","created_at":"2026-08-11T01:25:58.289723+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEUOOXQUPSSS","created_at":"2026-08-11T01:25:58.289723+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEUOOXQUPSSSRDZY","created_at":"2026-08-11T01:25:58.289723+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEUOOXQU","created_at":"2026-08-11T01:25:58.289723+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/JEUOOXQUPSSSRDZYMKPI7O3D2F","json":"https://pith.science/pith/JEUOOXQUPSSSRDZYMKPI7O3D2F.json","graph_json":"https://pith.science/api/pith-number/JEUOOXQUPSSSRDZYMKPI7O3D2F/graph.json","events_json":"https://pith.science/api/pith-number/JEUOOXQUPSSSRDZYMKPI7O3D2F/events.json","paper":"https://pith.science/paper/JEUOOXQU"},"agent_actions":{"view_html":"https://pith.science/pith/JEUOOXQUPSSSRDZYMKPI7O3D2F","download_json":"https://pith.science/pith/JEUOOXQUPSSSRDZYMKPI7O3D2F.json","view_paper":"https://pith.science/paper/JEUOOXQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09011&json=true","fetch_graph":"https://pith.science/api/pith-number/JEUOOXQUPSSSRDZYMKPI7O3D2F/graph.json","fetch_events":"https://pith.science/api/pith-number/JEUOOXQUPSSSRDZYMKPI7O3D2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEUOOXQUPSSSRDZYMKPI7O3D2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEUOOXQUPSSSRDZYMKPI7O3D2F/action/storage_attestation","attest_author":"https://pith.science/pith/JEUOOXQUPSSSRDZYMKPI7O3D2F/action/author_attestation","sign_citation":"https://pith.science/pith/JEUOOXQUPSSSRDZYMKPI7O3D2F/action/citation_signature","submit_replication":"https://pith.science/pith/JEUOOXQUPSSSRDZYMKPI7O3D2F/action/replication_record"}},"created_at":"2026-08-11T01:25:58.289723+00:00","updated_at":"2026-08-11T01:25:58.289723+00:00"}