{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AMIYHDKYFLCXH2PONGQSOZ2URA","short_pith_number":"pith:AMIYHDKY","schema_version":"1.0","canonical_sha256":"0311838d582ac573e9ee69a12767548806232d9a98519ba17634aef7f90ef0b6","source":{"kind":"arxiv","id":"2503.10665","version":1},"attestation_state":"computed","paper":{"title":"Small Vision-Language Models: A Survey on Compact Architectures and Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gourav Bal, Himani Bansal Agrawal, Kartheek Vadlamani, Moinak Chinmoy Khamaru, Navdeep Nayak, Nitesh Patnaik, Rishi Raj, Saishree Smaranika Panda, Vishal Meena","submitted_at":"2025-03-09T16:14:46Z","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"},"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":"2503.10665","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T16:14:46Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"bacab7cc18b6693ea5356b7dbc3e3fbb3f2c7770b1adc5f4d3b4e764433d9323","abstract_canon_sha256":"265418582cb516785a6352b63777941089f631a4e4b0d78e914102161f8cea44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:03.276808Z","signature_b64":"Uy/o0KGE3Tyzvivqe5d1HouHaRpLR5VBZhACH5U49M115ja+FodSoHg1bJk51Jqa8ajkwk0HhV1jNd2dymgAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0311838d582ac573e9ee69a12767548806232d9a98519ba17634aef7f90ef0b6","last_reissued_at":"2026-07-05T10:31:03.275411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:03.275411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Small Vision-Language Models: A Survey on Compact Architectures and Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gourav Bal, Himani Bansal Agrawal, Kartheek Vadlamani, Moinak Chinmoy Khamaru, Navdeep Nayak, Nitesh Patnaik, Rishi Raj, Saishree Smaranika Panda, Vishal Meena","submitted_at":"2025-03-09T16:14:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10665","kind":"arxiv","version":1},"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/2503.10665/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":"2503.10665","created_at":"2026-07-05T10:31:03.275473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10665v1","created_at":"2026-07-05T10:31:03.275473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10665","created_at":"2026-07-05T10:31:03.275473+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMIYHDKYFLCX","created_at":"2026-07-05T10:31:03.275473+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMIYHDKYFLCXH2PO","created_at":"2026-07-05T10:31:03.275473+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMIYHDKY","created_at":"2026-07-05T10:31:03.275473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05210","citing_title":"Integration of Object Detection and Small VLMs for Construction Safety Hazard Identification","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMIYHDKYFLCXH2PONGQSOZ2URA","json":"https://pith.science/pith/AMIYHDKYFLCXH2PONGQSOZ2URA.json","graph_json":"https://pith.science/api/pith-number/AMIYHDKYFLCXH2PONGQSOZ2URA/graph.json","events_json":"https://pith.science/api/pith-number/AMIYHDKYFLCXH2PONGQSOZ2URA/events.json","paper":"https://pith.science/paper/AMIYHDKY"},"agent_actions":{"view_html":"https://pith.science/pith/AMIYHDKYFLCXH2PONGQSOZ2URA","download_json":"https://pith.science/pith/AMIYHDKYFLCXH2PONGQSOZ2URA.json","view_paper":"https://pith.science/paper/AMIYHDKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10665&json=true","fetch_graph":"https://pith.science/api/pith-number/AMIYHDKYFLCXH2PONGQSOZ2URA/graph.json","fetch_events":"https://pith.science/api/pith-number/AMIYHDKYFLCXH2PONGQSOZ2URA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMIYHDKYFLCXH2PONGQSOZ2URA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMIYHDKYFLCXH2PONGQSOZ2URA/action/storage_attestation","attest_author":"https://pith.science/pith/AMIYHDKYFLCXH2PONGQSOZ2URA/action/author_attestation","sign_citation":"https://pith.science/pith/AMIYHDKYFLCXH2PONGQSOZ2URA/action/citation_signature","submit_replication":"https://pith.science/pith/AMIYHDKYFLCXH2PONGQSOZ2URA/action/replication_record"}},"created_at":"2026-07-05T10:31:03.275473+00:00","updated_at":"2026-07-05T10:31:03.275473+00:00"}