{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZWRLTKTFEDLN5I6LOYGE5AHIBK","short_pith_number":"pith:ZWRLTKTF","schema_version":"1.0","canonical_sha256":"cda2b9aa6520d6dea3cb760c4e80e80ab0f603d4aee2b0e7c8010b04882246eb","source":{"kind":"arxiv","id":"2507.21521","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amrutha Machireddy, Athmanarayanan Lakshmi Narayanan, Ranganath Krishnan","submitted_at":"2025-07-29T06:08:28Z","abstract_excerpt":"Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates addressing challenges in uncertainty estimation and efficient sampling given the vast number of parameters involved. In this work, we introduce a novel parameter-efficient learning methodology that incorporates uncertainty calibration loss within the AL framework. We propose a differentiable loss function that promotes uncertainty calibration for effectively "},"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":"2507.21521","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T06:08:28Z","cross_cats_sorted":[],"title_canon_sha256":"1d52ecf8e5a2e8cf21b329b1ff0a169e434a2d5fcaafe0aea3071db77cd09c80","abstract_canon_sha256":"63b1d2c0b26cddd0bff111ddfeece7e8b808f4d4617b44b8572b1dacd315ac42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:01.672686Z","signature_b64":"iCdTjmogOz7c5aZT6KUYMPlwhZ2HfR9GirZDJ44Fp+043DI28d/VZg8m+WyHMJlwnI07X7AmLHiHwM8RTy20Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cda2b9aa6520d6dea3cb760c4e80e80ab0f603d4aee2b0e7c8010b04882246eb","last_reissued_at":"2026-07-05T11:45:01.672264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:01.672264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amrutha Machireddy, Athmanarayanan Lakshmi Narayanan, Ranganath Krishnan","submitted_at":"2025-07-29T06:08:28Z","abstract_excerpt":"Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates addressing challenges in uncertainty estimation and efficient sampling given the vast number of parameters involved. In this work, we introduce a novel parameter-efficient learning methodology that incorporates uncertainty calibration loss within the AL framework. We propose a differentiable loss function that promotes uncertainty calibration for effectively "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21521","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/2507.21521/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":"2507.21521","created_at":"2026-07-05T11:45:01.672320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21521v1","created_at":"2026-07-05T11:45:01.672320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21521","created_at":"2026-07-05T11:45:01.672320+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWRLTKTFEDLN","created_at":"2026-07-05T11:45:01.672320+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWRLTKTFEDLN5I6L","created_at":"2026-07-05T11:45:01.672320+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWRLTKTF","created_at":"2026-07-05T11:45:01.672320+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/ZWRLTKTFEDLN5I6LOYGE5AHIBK","json":"https://pith.science/pith/ZWRLTKTFEDLN5I6LOYGE5AHIBK.json","graph_json":"https://pith.science/api/pith-number/ZWRLTKTFEDLN5I6LOYGE5AHIBK/graph.json","events_json":"https://pith.science/api/pith-number/ZWRLTKTFEDLN5I6LOYGE5AHIBK/events.json","paper":"https://pith.science/paper/ZWRLTKTF"},"agent_actions":{"view_html":"https://pith.science/pith/ZWRLTKTFEDLN5I6LOYGE5AHIBK","download_json":"https://pith.science/pith/ZWRLTKTFEDLN5I6LOYGE5AHIBK.json","view_paper":"https://pith.science/paper/ZWRLTKTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21521&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWRLTKTFEDLN5I6LOYGE5AHIBK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWRLTKTFEDLN5I6LOYGE5AHIBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWRLTKTFEDLN5I6LOYGE5AHIBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWRLTKTFEDLN5I6LOYGE5AHIBK/action/storage_attestation","attest_author":"https://pith.science/pith/ZWRLTKTFEDLN5I6LOYGE5AHIBK/action/author_attestation","sign_citation":"https://pith.science/pith/ZWRLTKTFEDLN5I6LOYGE5AHIBK/action/citation_signature","submit_replication":"https://pith.science/pith/ZWRLTKTFEDLN5I6LOYGE5AHIBK/action/replication_record"}},"created_at":"2026-07-05T11:45:01.672320+00:00","updated_at":"2026-07-05T11:45:01.672320+00:00"}