{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:C6WJO2VVBXRG2C6KPGBG5DQT7L","short_pith_number":"pith:C6WJO2VV","schema_version":"1.0","canonical_sha256":"17ac976ab50de26d0bca79826e8e13faf770a3c26a9bf87a429106ccf389470c","source":{"kind":"arxiv","id":"1804.09626","version":2},"attestation_state":"computed","paper":{"title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Ali Farhadi, Cordelia Schmid, Gunnar A. Sigurdsson, Karteek Alahari","submitted_at":"2018-04-25T15:30:27Z","abstract_excerpt":"In Actor and Observer we introduced a dataset linking the first and third-person video understanding domains, the Charades-Ego Dataset. In this paper we describe the egocentric aspect of the dataset and present annotations for Charades-Ego with 68,536 activity instances in 68.8 hours of first and third-person video, making it one of the largest and most diverse egocentric datasets available. Charades-Ego furthermore shares activity classes, scripts, and methodology with the Charades dataset, that consist of additional 82.3 hours of third-person video with 66,500 activity instances. Charades-Eg"},"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":"1804.09626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-25T15:30:27Z","cross_cats_sorted":[],"title_canon_sha256":"58a9fc9bbdc77c262040dc1b7d551c0d2416075764ad90561a5d5496e1521a8b","abstract_canon_sha256":"8a2151ced0ecd283d8be42086cc18bcc050780c4c3161b33170799051a5245dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:16.151147Z","signature_b64":"dxmdHkhHZnQ9HszFpInrcIWmDJnTBqd8khMB/M/8VfBEZ3DnVMglCHQTiIs9e8qiel3IiCXr7vTax0OkX2U0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17ac976ab50de26d0bca79826e8e13faf770a3c26a9bf87a429106ccf389470c","last_reissued_at":"2026-05-18T00:17:16.150410Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:16.150410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Ali Farhadi, Cordelia Schmid, Gunnar A. Sigurdsson, Karteek Alahari","submitted_at":"2018-04-25T15:30:27Z","abstract_excerpt":"In Actor and Observer we introduced a dataset linking the first and third-person video understanding domains, the Charades-Ego Dataset. In this paper we describe the egocentric aspect of the dataset and present annotations for Charades-Ego with 68,536 activity instances in 68.8 hours of first and third-person video, making it one of the largest and most diverse egocentric datasets available. Charades-Ego furthermore shares activity classes, scripts, and methodology with the Charades dataset, that consist of additional 82.3 hours of third-person video with 66,500 activity instances. Charades-Eg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09626","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":""},"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":"1804.09626","created_at":"2026-05-18T00:17:16.150544+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.09626v2","created_at":"2026-05-18T00:17:16.150544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09626","created_at":"2026-05-18T00:17:16.150544+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6WJO2VVBXRG","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6WJO2VVBXRG2C6K","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6WJO2VV","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2501.05067","citing_title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17262","citing_title":"EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2310.01852","citing_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","ref_index":118,"is_internal_anchor":true},{"citing_arxiv_id":"2204.00598","citing_title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26565","citing_title":"DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23803","citing_title":"Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6WJO2VVBXRG2C6KPGBG5DQT7L","json":"https://pith.science/pith/C6WJO2VVBXRG2C6KPGBG5DQT7L.json","graph_json":"https://pith.science/api/pith-number/C6WJO2VVBXRG2C6KPGBG5DQT7L/graph.json","events_json":"https://pith.science/api/pith-number/C6WJO2VVBXRG2C6KPGBG5DQT7L/events.json","paper":"https://pith.science/paper/C6WJO2VV"},"agent_actions":{"view_html":"https://pith.science/pith/C6WJO2VVBXRG2C6KPGBG5DQT7L","download_json":"https://pith.science/pith/C6WJO2VVBXRG2C6KPGBG5DQT7L.json","view_paper":"https://pith.science/paper/C6WJO2VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.09626&json=true","fetch_graph":"https://pith.science/api/pith-number/C6WJO2VVBXRG2C6KPGBG5DQT7L/graph.json","fetch_events":"https://pith.science/api/pith-number/C6WJO2VVBXRG2C6KPGBG5DQT7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6WJO2VVBXRG2C6KPGBG5DQT7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6WJO2VVBXRG2C6KPGBG5DQT7L/action/storage_attestation","attest_author":"https://pith.science/pith/C6WJO2VVBXRG2C6KPGBG5DQT7L/action/author_attestation","sign_citation":"https://pith.science/pith/C6WJO2VVBXRG2C6KPGBG5DQT7L/action/citation_signature","submit_replication":"https://pith.science/pith/C6WJO2VVBXRG2C6KPGBG5DQT7L/action/replication_record"}},"created_at":"2026-05-18T00:17:16.150544+00:00","updated_at":"2026-05-18T00:17:16.150544+00:00"}