{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AMIYHDKYFLCXH2PONGQSOZ2URA","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":"265418582cb516785a6352b63777941089f631a4e4b0d78e914102161f8cea44","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T16:14:46Z","title_canon_sha256":"bacab7cc18b6693ea5356b7dbc3e3fbb3f2c7770b1adc5f4d3b4e764433d9323"},"schema_version":"1.0","source":{"id":"2503.10665","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10665","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10665v1","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10665","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"pith_short_12","alias_value":"AMIYHDKYFLCX","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"AMIYHDKYFLCXH2PO","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"AMIYHDKY","created_at":"2026-07-05T10:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:c2ce67be224bfd155e2a82c26834cd88fde745474b6a3d5d9edba58b893f96f9","target":"graph","created_at":"2026-07-05T10:31:03Z","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/2503.10665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of small vision-language models (sVLMs) marks a critical advancement in multimodal AI, enabling efficient processing of visual and textual data in resource-constrained environments. This survey offers a comprehensive exploration of sVLM development, presenting a taxonomy of architectures - transformer-based, mamba-based, and hybrid - that highlight innovations in compact design and computational efficiency. Techniques such as knowledge distillation, lightweight attention mechanisms, and modality pre-fusion are discussed as enablers of high performance with reduced resource requir","authors_text":"Gourav Bal, Himani Bansal Agrawal, Kartheek Vadlamani, Moinak Chinmoy Khamaru, Navdeep Nayak, Nitesh Patnaik, Rishi Raj, Saishree Smaranika Panda, Vishal Meena","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T16:14:46Z","title":"Small Vision-Language Models: A Survey on Compact Architectures and Techniques"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10665","kind":"arxiv","version":1},"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":"sha256:799facf4698accf5e2148b7e7f681516244ffba9a2cb134733a4d742c6345381","target":"record","created_at":"2026-07-05T10:31:03Z","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":"265418582cb516785a6352b63777941089f631a4e4b0d78e914102161f8cea44","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T16:14:46Z","title_canon_sha256":"bacab7cc18b6693ea5356b7dbc3e3fbb3f2c7770b1adc5f4d3b4e764433d9323"},"schema_version":"1.0","source":{"id":"2503.10665","kind":"arxiv","version":1}},"canonical_sha256":"0311838d582ac573e9ee69a12767548806232d9a98519ba17634aef7f90ef0b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0311838d582ac573e9ee69a12767548806232d9a98519ba17634aef7f90ef0b6","first_computed_at":"2026-07-05T10:31:03.275411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:03.275411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uy/o0KGE3Tyzvivqe5d1HouHaRpLR5VBZhACH5U49M115ja+FodSoHg1bJk51Jqa8ajkwk0HhV1jNd2dymgAAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:03.276808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10665","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:799facf4698accf5e2148b7e7f681516244ffba9a2cb134733a4d742c6345381","sha256:c2ce67be224bfd155e2a82c26834cd88fde745474b6a3d5d9edba58b893f96f9"],"state_sha256":"a378a0badcf494c9d3e21521be8ce7c0b6eb64097150dd3e4895ab11d8fd5c3c"}