{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NL7A2FBFWDBPQXVIKCZO5PPA6A","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":"66c8f29c453612087b04dfa7b6906be7e6d42de97265570b91805b45169f5f97","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T21:12:24Z","title_canon_sha256":"11abb33544857b50fe53056827a90109c3c88e2c1c8b19b193b754e8d5744ae9"},"schema_version":"1.0","source":{"id":"2504.09724","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09724","created_at":"2026-07-05T11:30:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09724v3","created_at":"2026-07-05T11:30:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09724","created_at":"2026-07-05T11:30:22Z"},{"alias_kind":"pith_short_12","alias_value":"NL7A2FBFWDBP","created_at":"2026-07-05T11:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"NL7A2FBFWDBPQXVI","created_at":"2026-07-05T11:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"NL7A2FBF","created_at":"2026-07-05T11:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:5708b39ea9aaa0429b94a335d23cc3fadd6cf9fbe0a8f78785bfa8ddfbe7af8d","target":"graph","created_at":"2026-07-05T11:30:22Z","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/2504.09724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high computational demands pose challenges for real-time applications. This has led to a growing focus on developing efficient vision language models. In this survey, we review key techniques for optimizing VLMs on edge and resource-constrained devices. We also explore compact VLM architectures, frameworks and provide detailed insights into the performance-memory trade-offs","authors_text":"Anuradha Ravi, Emon Dey, Gaurav Shinde, Milind Rampure, Nirmalya Roy, Shadman Sakib","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T21:12:24Z","title":"A Survey on Efficient Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09724","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:fe034f31ad6608d605d6af25c273c072ac17cf70ad73fb785140ef77c1f4e024","target":"record","created_at":"2026-07-05T11:30:22Z","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":"66c8f29c453612087b04dfa7b6906be7e6d42de97265570b91805b45169f5f97","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T21:12:24Z","title_canon_sha256":"11abb33544857b50fe53056827a90109c3c88e2c1c8b19b193b754e8d5744ae9"},"schema_version":"1.0","source":{"id":"2504.09724","kind":"arxiv","version":3}},"canonical_sha256":"6afe0d1425b0c2f85ea850b2eebde0f034994c1c8d3ab2c18757b4889e2c7a2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6afe0d1425b0c2f85ea850b2eebde0f034994c1c8d3ab2c18757b4889e2c7a2f","first_computed_at":"2026-07-05T11:30:22.331128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:22.331128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cqSt7vIRKF/RhCxaBhtvZQVYS8jUMZ2y4jvhfcSsYHg7npjsiyhdFziqvwSDUJMKO8V/Kim0HYLmATxlrLiOCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:22.331642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09724","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe034f31ad6608d605d6af25c273c072ac17cf70ad73fb785140ef77c1f4e024","sha256:5708b39ea9aaa0429b94a335d23cc3fadd6cf9fbe0a8f78785bfa8ddfbe7af8d"],"state_sha256":"4107616598baf25b8a300c0bd06e1c5aa3f80e7f1498eb59ecb4e06034e7d272"}