{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UCFUNI4RXMO5L4532N33L2VD42","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":"1906bb04a4e7907fa7204397fd31ea1030c87b7f693ee3acb4e502fdead289c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T06:44:25Z","title_canon_sha256":"adc25490095aebde1a5c39f4b0cf77285861fd758a1c03d2e34e9f580069e168"},"schema_version":"1.0","source":{"id":"2412.20750","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20750","created_at":"2026-07-02T01:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20750v3","created_at":"2026-07-02T01:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20750","created_at":"2026-07-02T01:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"UCFUNI4RXMO5","created_at":"2026-07-02T01:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"UCFUNI4RXMO5L453","created_at":"2026-07-02T01:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"UCFUNI4R","created_at":"2026-07-02T01:17:11Z"}],"graph_snapshots":[{"event_id":"sha256:3b9a8c460e4381c246bb2dcd35efd29d6f614ee6cd9514aeaabca64b79fafea6","target":"graph","created_at":"2026-07-02T01:17:11Z","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/2412.20750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale Vision-Language Models (VLMs) have achieved notable progress in aligning visual inputs with text. However, their ability to deeply understand the unique physical properties of non-RGB vision sensor images remains limited. In this paper, we revisit and analyze these limitations and introduce a novel, cost-efficient paradigm that significantly advances sensor image understanding-without requiring extensive training data or any modifications to the existing VLM architectures. Specifically, we propose Sensor-Aware Attributes Fine-Tuning (SAFT) with the Diverse Negative Attributes (DNA)","authors_text":"Sangyun Chung, Se Yeon Kim, Yong Man Ro, Youngchae Chee, Youngjoon Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T06:44:25Z","title":"Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20750","kind":"arxiv","version":3},"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":"sha256:9a54cc41e2d5e174160dad6b4ecdc28afb86c919663916609bac53c001afe86b","target":"record","created_at":"2026-07-02T01:17:11Z","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":"1906bb04a4e7907fa7204397fd31ea1030c87b7f693ee3acb4e502fdead289c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T06:44:25Z","title_canon_sha256":"adc25490095aebde1a5c39f4b0cf77285861fd758a1c03d2e34e9f580069e168"},"schema_version":"1.0","source":{"id":"2412.20750","kind":"arxiv","version":3}},"canonical_sha256":"a08b46a391bb1dd5f3bbd377b5eaa3e6b158733089b586938c3eacce5723cd66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a08b46a391bb1dd5f3bbd377b5eaa3e6b158733089b586938c3eacce5723cd66","first_computed_at":"2026-07-02T01:17:11.687073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:11.687073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E0jrPIAj1kTUkFveBEkC+FnPpX0kFaPRAhWokDV5WPw6Ao8zoRfLjURmrf0mHd7uzdoSKm9FxcdzowuL3oviAw==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:11.687580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20750","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a54cc41e2d5e174160dad6b4ecdc28afb86c919663916609bac53c001afe86b","sha256:3b9a8c460e4381c246bb2dcd35efd29d6f614ee6cd9514aeaabca64b79fafea6"],"state_sha256":"64e8ec7c2cb40cf82243b467002252daa884c2a05f33bd93b28e837cce0be446"}