{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:7LSSN6453BVBZ25G3EJMF43NP4","short_pith_number":"pith:7LSSN645","schema_version":"1.0","canonical_sha256":"fae526fb9dd86a1ceba6d912c2f36d7f1dc1b871c241c5284c6e865b19edf4d5","source":{"kind":"arxiv","id":"1609.01885","version":7},"attestation_state":"computed","paper":{"title":"DAiSEE: Towards User Engagement Recognition in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhay Gupta, Arjun D'Cunha, Kamal Awasthi, Vineeth Balasubramanian","submitted_at":"2016-09-07T08:50:11Z","abstract_excerpt":"We introduce DAiSEE, the first multi-label video classification dataset comprising of 9068 video snippets captured from 112 users for recognizing the user affective states of boredom, confusion, engagement, and frustration in the wild. The dataset has four levels of labels namely - very low, low, high, and very high for each of the affective states, which are crowd annotated and correlated with a gold standard annotation created using a team of expert psychologists. We have also established benchmark results on this dataset using state-of-the-art video classification methods that are available"},"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":"1609.01885","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-07T08:50:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cebb5770c4a805dcb93f4b7c329b2c4fd7119123e3374b57ba91478d4fd9f887","abstract_canon_sha256":"48d21fca7c55fa7db0293c6e98edb65909c7a8959a2599995b23b6d9e9412faa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:08.532500Z","signature_b64":"cglzcGxgOTiacsv7Sj5jE1474//IH5yMYNSFVJhe61oTLrPv4k4mKvImVE1WJCti2vWCnGHx/1Ynnwp/uKWBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fae526fb9dd86a1ceba6d912c2f36d7f1dc1b871c241c5284c6e865b19edf4d5","last_reissued_at":"2026-07-05T04:38:08.532022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:08.532022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DAiSEE: Towards User Engagement Recognition in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhay Gupta, Arjun D'Cunha, Kamal Awasthi, Vineeth Balasubramanian","submitted_at":"2016-09-07T08:50:11Z","abstract_excerpt":"We introduce DAiSEE, the first multi-label video classification dataset comprising of 9068 video snippets captured from 112 users for recognizing the user affective states of boredom, confusion, engagement, and frustration in the wild. The dataset has four levels of labels namely - very low, low, high, and very high for each of the affective states, which are crowd annotated and correlated with a gold standard annotation created using a team of expert psychologists. We have also established benchmark results on this dataset using state-of-the-art video classification methods that are available"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.01885","kind":"arxiv","version":7},"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/1609.01885/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":"1609.01885","created_at":"2026-07-05T04:38:08.532080+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.01885v7","created_at":"2026-07-05T04:38:08.532080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.01885","created_at":"2026-07-05T04:38:08.532080+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LSSN6453BVB","created_at":"2026-07-05T04:38:08.532080+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LSSN6453BVBZ25G","created_at":"2026-07-05T04:38:08.532080+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LSSN645","created_at":"2026-07-05T04:38:08.532080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21861","citing_title":"Zero-Shot Vision-Language Models for Classroom Engagement Recognition: A Benchmark Study of Prompt Sensitivity and Cross-Dataset Generalization","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23204","citing_title":"Unmasking LAION-5B: Age, Gender, Race, and Emotion Biases in Large-Scale Image Datasets","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2502.20209","citing_title":"DIPSER: A Dataset for In-Person Student Engagement Recognition in the Wild","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19798","citing_title":"Towards Trust Calibration in Socially Interactive Agents: Investigating Gendered Multimodal Behaviors Generation with LLMs","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03615","citing_title":"PriorNet: Prior-Guided Engagement Estimation from Face Video","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04713","citing_title":"Not Every Subject Should Stay: Machine Unlearning for Noisy Engagement Recognition","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10078","citing_title":"Attention-Guided Dual-Stream Learning for Group Engagement Recognition: Fusing Transformer-Encoded Motion Dynamics with Scene Context via Adaptive Gating","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7LSSN6453BVBZ25G3EJMF43NP4","json":"https://pith.science/pith/7LSSN6453BVBZ25G3EJMF43NP4.json","graph_json":"https://pith.science/api/pith-number/7LSSN6453BVBZ25G3EJMF43NP4/graph.json","events_json":"https://pith.science/api/pith-number/7LSSN6453BVBZ25G3EJMF43NP4/events.json","paper":"https://pith.science/paper/7LSSN645"},"agent_actions":{"view_html":"https://pith.science/pith/7LSSN6453BVBZ25G3EJMF43NP4","download_json":"https://pith.science/pith/7LSSN6453BVBZ25G3EJMF43NP4.json","view_paper":"https://pith.science/paper/7LSSN645","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.01885&json=true","fetch_graph":"https://pith.science/api/pith-number/7LSSN6453BVBZ25G3EJMF43NP4/graph.json","fetch_events":"https://pith.science/api/pith-number/7LSSN6453BVBZ25G3EJMF43NP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LSSN6453BVBZ25G3EJMF43NP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LSSN6453BVBZ25G3EJMF43NP4/action/storage_attestation","attest_author":"https://pith.science/pith/7LSSN6453BVBZ25G3EJMF43NP4/action/author_attestation","sign_citation":"https://pith.science/pith/7LSSN6453BVBZ25G3EJMF43NP4/action/citation_signature","submit_replication":"https://pith.science/pith/7LSSN6453BVBZ25G3EJMF43NP4/action/replication_record"}},"created_at":"2026-07-05T04:38:08.532080+00:00","updated_at":"2026-07-05T04:38:08.532080+00:00"}