{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KYYRCFVCHMOODVIY4ZQ5MNNO5E","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":"1ca5126eba4accf6e5897e9f75c031e3f83a287f8a08759893710715c28a8ea7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T21:34:40Z","title_canon_sha256":"2ebc7ad5ee2156c1adc19018b09bb6df7c02b5319abb2c19f9f8264f9693445e"},"schema_version":"1.0","source":{"id":"2403.04908","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04908","created_at":"2026-07-05T09:13:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04908v3","created_at":"2026-07-05T09:13:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04908","created_at":"2026-07-05T09:13:50Z"},{"alias_kind":"pith_short_12","alias_value":"KYYRCFVCHMOO","created_at":"2026-07-05T09:13:50Z"},{"alias_kind":"pith_short_16","alias_value":"KYYRCFVCHMOODVIY","created_at":"2026-07-05T09:13:50Z"},{"alias_kind":"pith_short_8","alias_value":"KYYRCFVC","created_at":"2026-07-05T09:13:50Z"}],"graph_snapshots":[{"event_id":"sha256:767b8cd2140b995011ebff52c0388cc6f983127b900e49e5f7edd6cd9a51f372","target":"graph","created_at":"2026-07-05T09:13:50Z","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/2403.04908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices, yet challenges in handling diverse visual modalities, manual annotation, and computational constraints remain. We introduce EdgeVL, a novel framework that bridges this gap by seamlessly integrating dual-modality knowledge distillation and quantization-aware contrastive learning. This approach enables the adaptation of large VL models, like CLIP, for efficient use with both RGB and non-RGB images on resource-limited devices without the need for manual annotations. EdgeVL not only transf","authors_text":"Charles Fleming, Chris Xiaoxuan Lu, Gaowen Liu, Kaiwen Cai, Zhekai Duan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T21:34:40Z","title":"Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04908","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":"sha256:2b2f5f26f105b6edc73597749946a472f7ca68b4e02a2f5bda94c41367d7c681","target":"record","created_at":"2026-07-05T09:13:50Z","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":"1ca5126eba4accf6e5897e9f75c031e3f83a287f8a08759893710715c28a8ea7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T21:34:40Z","title_canon_sha256":"2ebc7ad5ee2156c1adc19018b09bb6df7c02b5319abb2c19f9f8264f9693445e"},"schema_version":"1.0","source":{"id":"2403.04908","kind":"arxiv","version":3}},"canonical_sha256":"56311116a23b1ce1d518e661d635aee91fe8c608a5b75c21d8feeafefd6cec6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56311116a23b1ce1d518e661d635aee91fe8c608a5b75c21d8feeafefd6cec6b","first_computed_at":"2026-07-05T09:13:50.515852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:50.515852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VBodJ9ea5UlEEeOvfDCgm+7iERhNjZGkO0dMvVdOoZVhL7W+QcHJLms5tk5hkHcs9HOdTK2mRf8fUFkeA10SDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:50.516392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04908","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b2f5f26f105b6edc73597749946a472f7ca68b4e02a2f5bda94c41367d7c681","sha256:767b8cd2140b995011ebff52c0388cc6f983127b900e49e5f7edd6cd9a51f372"],"state_sha256":"714c762a73f7d4e0a2fca9ada3c08ad3cd7153c8843fdebcda777c783aa5ffe6"}