{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TGPT5GDLKYUEYBMEP4IH4KXGGZ","short_pith_number":"pith:TGPT5GDL","schema_version":"1.0","canonical_sha256":"999f3e986b56284c05847f107e2ae6365924311d9bbfbc0d35b489de56e96bf7","source":{"kind":"arxiv","id":"2512.12571","version":3},"attestation_state":"computed","paper":{"title":"Measurement Plasticity: Sensor-Level Adaptation for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyeong Im, Hyung-Sin Kim, Wooseok Lee, Yoojin Kwon","submitted_at":"2025-12-14T06:30:32Z","abstract_excerpt":"We propose Multi-View Physical-prompt (MVP) for Test-Time Adaptation (TTA), a forward-only framework that moves TTA from tokens to photons by treating the camera exposure triangle (i.e., ISO, shutter speed, and aperture) as physical prompts. At inference, MVP acquires selected multiple physical views using a source-affinity score, evaluates digitally augmented variants of each retained view and filters the lowest-entropy predictions, and aggregates predictions with hard voting. This selection-then-vote design is simple, calibration-friendly, and requires no gradients or model modifications. On"},"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":"2512.12571","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-14T06:30:32Z","cross_cats_sorted":[],"title_canon_sha256":"6da8ff52f1352f1c2b605309957ee7ceba77126bb4019d50d18af96fa9a45659","abstract_canon_sha256":"8d15838f9fdc06e9b83119c8d0533d8665e8431a8ce0e0480c582d561ff60377"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:17.753296Z","signature_b64":"RcNSaKLiIOH+rKFyAle36AZxNczN8EJ+bbXLwhCtuaKQly2bSNqcmg1ekYk2RKlUNwUdyiMFvlVbL2bWhqkABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"999f3e986b56284c05847f107e2ae6365924311d9bbfbc0d35b489de56e96bf7","last_reissued_at":"2026-06-12T01:09:17.752303Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:17.752303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measurement Plasticity: Sensor-Level Adaptation for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyeong Im, Hyung-Sin Kim, Wooseok Lee, Yoojin Kwon","submitted_at":"2025-12-14T06:30:32Z","abstract_excerpt":"We propose Multi-View Physical-prompt (MVP) for Test-Time Adaptation (TTA), a forward-only framework that moves TTA from tokens to photons by treating the camera exposure triangle (i.e., ISO, shutter speed, and aperture) as physical prompts. At inference, MVP acquires selected multiple physical views using a source-affinity score, evaluates digitally augmented variants of each retained view and filters the lowest-entropy predictions, and aggregates predictions with hard voting. This selection-then-vote design is simple, calibration-friendly, and requires no gradients or model modifications. On"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.12571","kind":"arxiv","version":3},"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/2512.12571/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":"2512.12571","created_at":"2026-06-12T01:09:17.752462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.12571v3","created_at":"2026-06-12T01:09:17.752462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.12571","created_at":"2026-06-12T01:09:17.752462+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGPT5GDLKYUE","created_at":"2026-06-12T01:09:17.752462+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGPT5GDLKYUEYBME","created_at":"2026-06-12T01:09:17.752462+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGPT5GDL","created_at":"2026-06-12T01:09:17.752462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.13959","citing_title":"[Emerging Ideas] Artificial Tripartite Intelligence: A Bio-Inspired, Sensor-First Architecture for Physical AI","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TGPT5GDLKYUEYBMEP4IH4KXGGZ","json":"https://pith.science/pith/TGPT5GDLKYUEYBMEP4IH4KXGGZ.json","graph_json":"https://pith.science/api/pith-number/TGPT5GDLKYUEYBMEP4IH4KXGGZ/graph.json","events_json":"https://pith.science/api/pith-number/TGPT5GDLKYUEYBMEP4IH4KXGGZ/events.json","paper":"https://pith.science/paper/TGPT5GDL"},"agent_actions":{"view_html":"https://pith.science/pith/TGPT5GDLKYUEYBMEP4IH4KXGGZ","download_json":"https://pith.science/pith/TGPT5GDLKYUEYBMEP4IH4KXGGZ.json","view_paper":"https://pith.science/paper/TGPT5GDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.12571&json=true","fetch_graph":"https://pith.science/api/pith-number/TGPT5GDLKYUEYBMEP4IH4KXGGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TGPT5GDLKYUEYBMEP4IH4KXGGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGPT5GDLKYUEYBMEP4IH4KXGGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGPT5GDLKYUEYBMEP4IH4KXGGZ/action/storage_attestation","attest_author":"https://pith.science/pith/TGPT5GDLKYUEYBMEP4IH4KXGGZ/action/author_attestation","sign_citation":"https://pith.science/pith/TGPT5GDLKYUEYBMEP4IH4KXGGZ/action/citation_signature","submit_replication":"https://pith.science/pith/TGPT5GDLKYUEYBMEP4IH4KXGGZ/action/replication_record"}},"created_at":"2026-06-12T01:09:17.752462+00:00","updated_at":"2026-06-12T01:09:17.752462+00:00"}