{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D2BKANZODDSHU7GOSY26HYJHXZ","short_pith_number":"pith:D2BKANZO","schema_version":"1.0","canonical_sha256":"1e82a0372e18e47a7cce9635e3e127be49fa32e269fa2516d5b91a2f72f05b62","source":{"kind":"arxiv","id":"2506.13657","version":2},"attestation_state":"computed","paper":{"title":"Lecture Video Visual Objects (LVVO) Dataset: A Benchmark for Visual Object Detection in Educational Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dipayan Biswas, Jaspal Subhlok, Shishir Shah","submitted_at":"2025-06-16T16:18:21Z","abstract_excerpt":"We introduce the Lecture Video Visual Objects (LVVO) dataset, a new benchmark for visual object detection in educational video content. The dataset consists of 4,000 frames extracted from 245 lecture videos spanning biology, computer science, and geosciences. A subset of 1,000 frames, referred to as LVVO_1k, has been manually annotated with bounding boxes for four visual categories: Table, Chart-Graph, Photographic-image, and Visual-illustration. Each frame was labeled independently by two annotators, resulting in an inter-annotator F1 score of 83.41%, indicating strong agreement. To ensure hi"},"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":"2506.13657","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-16T16:18:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12c357af17c8396948c6ab85c84fd54207d36ec5f43054964fb3fadaecbf5d09","abstract_canon_sha256":"38462b13dec4833e5bca1ae6ed3764d7363f3a4a2cda4925328f466142a871cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:42.885768Z","signature_b64":"Ef3mhR6+YRHE4e1955cwOOCjrfyi1lK/iN6+lf1afCVKYl5MUro/2CGwtAmIcYN+9C4GDh/yp1cCKezZfPfNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e82a0372e18e47a7cce9635e3e127be49fa32e269fa2516d5b91a2f72f05b62","last_reissued_at":"2026-07-05T11:22:42.885326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:42.885326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lecture Video Visual Objects (LVVO) Dataset: A Benchmark for Visual Object Detection in Educational Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dipayan Biswas, Jaspal Subhlok, Shishir Shah","submitted_at":"2025-06-16T16:18:21Z","abstract_excerpt":"We introduce the Lecture Video Visual Objects (LVVO) dataset, a new benchmark for visual object detection in educational video content. The dataset consists of 4,000 frames extracted from 245 lecture videos spanning biology, computer science, and geosciences. A subset of 1,000 frames, referred to as LVVO_1k, has been manually annotated with bounding boxes for four visual categories: Table, Chart-Graph, Photographic-image, and Visual-illustration. Each frame was labeled independently by two annotators, resulting in an inter-annotator F1 score of 83.41%, indicating strong agreement. To ensure hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13657","kind":"arxiv","version":2},"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/2506.13657/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":"2506.13657","created_at":"2026-07-05T11:22:42.885389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13657v2","created_at":"2026-07-05T11:22:42.885389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13657","created_at":"2026-07-05T11:22:42.885389+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2BKANZODDSH","created_at":"2026-07-05T11:22:42.885389+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2BKANZODDSHU7GO","created_at":"2026-07-05T11:22:42.885389+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2BKANZO","created_at":"2026-07-05T11:22:42.885389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21903","citing_title":"Visual Content Detection in Educational Videos with Transfer Learning and Dataset Enrichment","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2BKANZODDSHU7GOSY26HYJHXZ","json":"https://pith.science/pith/D2BKANZODDSHU7GOSY26HYJHXZ.json","graph_json":"https://pith.science/api/pith-number/D2BKANZODDSHU7GOSY26HYJHXZ/graph.json","events_json":"https://pith.science/api/pith-number/D2BKANZODDSHU7GOSY26HYJHXZ/events.json","paper":"https://pith.science/paper/D2BKANZO"},"agent_actions":{"view_html":"https://pith.science/pith/D2BKANZODDSHU7GOSY26HYJHXZ","download_json":"https://pith.science/pith/D2BKANZODDSHU7GOSY26HYJHXZ.json","view_paper":"https://pith.science/paper/D2BKANZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13657&json=true","fetch_graph":"https://pith.science/api/pith-number/D2BKANZODDSHU7GOSY26HYJHXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/D2BKANZODDSHU7GOSY26HYJHXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2BKANZODDSHU7GOSY26HYJHXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2BKANZODDSHU7GOSY26HYJHXZ/action/storage_attestation","attest_author":"https://pith.science/pith/D2BKANZODDSHU7GOSY26HYJHXZ/action/author_attestation","sign_citation":"https://pith.science/pith/D2BKANZODDSHU7GOSY26HYJHXZ/action/citation_signature","submit_replication":"https://pith.science/pith/D2BKANZODDSHU7GOSY26HYJHXZ/action/replication_record"}},"created_at":"2026-07-05T11:22:42.885389+00:00","updated_at":"2026-07-05T11:22:42.885389+00:00"}