{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HSDV7KFD7UASADC3SPHYJW6YHI","short_pith_number":"pith:HSDV7KFD","schema_version":"1.0","canonical_sha256":"3c875fa8a3fd01200c5b93cf84dbd83a1e175fa05493208cddbf30fb45967b43","source":{"kind":"arxiv","id":"2606.21861","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Vision-Language Models for Classroom Engagement Recognition: A Benchmark Study of Prompt Sensitivity and Cross-Dataset Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aman Goyal, Kemmannu Vineet Venkatesh Rao, Kshama Nitin Shah","submitted_at":"2026-06-20T03:53:40Z","abstract_excerpt":"Automated classroom engagement recognition holds substantial promise for scalable learning analytics, yet the suitability of modern Vision-Language Models (VLMs) for this task under zero-shot conditions remains largely unexplored. We present a systematic benchmark that evaluates five widely-used VLMs: CLIP, BLIP-VQA, GPT-4o, LLaVA-1.5-7B, and Qwen2.5VL-7B-Instruct across two complementary educational datasets: DAiSEE, an individual-student video dataset (300 sampled test clips), and the Student Classroom Behaviour dataset (SCB, 1,168 scene-level images). Each model is probed with three prompt "},"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":"2606.21861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-20T03:53:40Z","cross_cats_sorted":[],"title_canon_sha256":"0284275fa3050e4938bd2ff70073a8cbf8e878523cdb8762577afc5716a06715","abstract_canon_sha256":"308f2801e089b2016901582c609ad2c5d916fd2dcc9c73cb8a23dd103a61d04c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:01.259853Z","signature_b64":"vrrZnTUfpt6mXSiyA/Bwfn5Q85uIQDWw4adJzo4S6UjC+P6msu4SOiyC2le9xyPvFMEIMrc/FJYk5c6r6DxDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c875fa8a3fd01200c5b93cf84dbd83a1e175fa05493208cddbf30fb45967b43","last_reissued_at":"2026-06-23T02:13:01.259461Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:01.259461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Vision-Language Models for Classroom Engagement Recognition: A Benchmark Study of Prompt Sensitivity and Cross-Dataset Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aman Goyal, Kemmannu Vineet Venkatesh Rao, Kshama Nitin Shah","submitted_at":"2026-06-20T03:53:40Z","abstract_excerpt":"Automated classroom engagement recognition holds substantial promise for scalable learning analytics, yet the suitability of modern Vision-Language Models (VLMs) for this task under zero-shot conditions remains largely unexplored. We present a systematic benchmark that evaluates five widely-used VLMs: CLIP, BLIP-VQA, GPT-4o, LLaVA-1.5-7B, and Qwen2.5VL-7B-Instruct across two complementary educational datasets: DAiSEE, an individual-student video dataset (300 sampled test clips), and the Student Classroom Behaviour dataset (SCB, 1,168 scene-level images). Each model is probed with three prompt "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21861","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/2606.21861/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":"2606.21861","created_at":"2026-06-23T02:13:01.259516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21861v1","created_at":"2026-06-23T02:13:01.259516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21861","created_at":"2026-06-23T02:13:01.259516+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSDV7KFD7UAS","created_at":"2026-06-23T02:13:01.259516+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSDV7KFD7UASADC3","created_at":"2026-06-23T02:13:01.259516+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSDV7KFD","created_at":"2026-06-23T02:13:01.259516+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSDV7KFD7UASADC3SPHYJW6YHI","json":"https://pith.science/pith/HSDV7KFD7UASADC3SPHYJW6YHI.json","graph_json":"https://pith.science/api/pith-number/HSDV7KFD7UASADC3SPHYJW6YHI/graph.json","events_json":"https://pith.science/api/pith-number/HSDV7KFD7UASADC3SPHYJW6YHI/events.json","paper":"https://pith.science/paper/HSDV7KFD"},"agent_actions":{"view_html":"https://pith.science/pith/HSDV7KFD7UASADC3SPHYJW6YHI","download_json":"https://pith.science/pith/HSDV7KFD7UASADC3SPHYJW6YHI.json","view_paper":"https://pith.science/paper/HSDV7KFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21861&json=true","fetch_graph":"https://pith.science/api/pith-number/HSDV7KFD7UASADC3SPHYJW6YHI/graph.json","fetch_events":"https://pith.science/api/pith-number/HSDV7KFD7UASADC3SPHYJW6YHI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSDV7KFD7UASADC3SPHYJW6YHI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSDV7KFD7UASADC3SPHYJW6YHI/action/storage_attestation","attest_author":"https://pith.science/pith/HSDV7KFD7UASADC3SPHYJW6YHI/action/author_attestation","sign_citation":"https://pith.science/pith/HSDV7KFD7UASADC3SPHYJW6YHI/action/citation_signature","submit_replication":"https://pith.science/pith/HSDV7KFD7UASADC3SPHYJW6YHI/action/replication_record"}},"created_at":"2026-06-23T02:13:01.259516+00:00","updated_at":"2026-06-23T02:13:01.259516+00:00"}