{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AOVOK4IVC5LCO2PSLAJBNUX6X4","short_pith_number":"pith:AOVOK4IV","schema_version":"1.0","canonical_sha256":"03aae5711517562769f2581216d2febf22b8a65bbb5ae27b5a057cd3cfd479ad","source":{"kind":"arxiv","id":"2311.15596","version":2},"attestation_state":"computed","paper":{"title":"EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Huaping Liu, Jingwen Wu, Kechen Fang, Peng Li, Sijie Cheng, Yang Liu, Zhicheng Guo","submitted_at":"2023-11-27T07:44:25Z","abstract_excerpt":"Vision-language models (VLMs) have recently shown promising results in traditional downstream tasks. Evaluation studies have emerged to assess their abilities, with the majority focusing on the third-person perspective, and only a few addressing specific tasks from the first-person perspective. However, the capability of VLMs to \"think\" from a first-person perspective, a crucial attribute for advancing autonomous agents and robotics, remains largely unexplored. To bridge this research gap, we introduce EgoThink, a novel visual question-answering benchmark that encompasses six core capabilities"},"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":"2311.15596","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T07:44:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"829e6b88748571ab496e2009ea49125f0867efb998a3a514ebbc955b34819dce","abstract_canon_sha256":"d0410faa2fc0108abd624bb7eacbfcfcbf1e415e57c7fb75c5f299ff944df3fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:34.925262Z","signature_b64":"5sr6Ltjss2jxjGdGMK62ck1L8Bp3hRqa6AaN2R/mROXhzKSu1H6iozcJohEWSCOmkbQB0VZqxb7E1j2KPZu8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03aae5711517562769f2581216d2febf22b8a65bbb5ae27b5a057cd3cfd479ad","last_reissued_at":"2026-07-05T08:01:34.924720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:34.924720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Huaping Liu, Jingwen Wu, Kechen Fang, Peng Li, Sijie Cheng, Yang Liu, Zhicheng Guo","submitted_at":"2023-11-27T07:44:25Z","abstract_excerpt":"Vision-language models (VLMs) have recently shown promising results in traditional downstream tasks. Evaluation studies have emerged to assess their abilities, with the majority focusing on the third-person perspective, and only a few addressing specific tasks from the first-person perspective. However, the capability of VLMs to \"think\" from a first-person perspective, a crucial attribute for advancing autonomous agents and robotics, remains largely unexplored. To bridge this research gap, we introduce EgoThink, a novel visual question-answering benchmark that encompasses six core capabilities"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15596","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/2311.15596/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":"2311.15596","created_at":"2026-07-05T08:01:34.924782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15596v2","created_at":"2026-07-05T08:01:34.924782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15596","created_at":"2026-07-05T08:01:34.924782+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOVOK4IVC5LC","created_at":"2026-07-05T08:01:34.924782+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOVOK4IVC5LCO2PS","created_at":"2026-07-05T08:01:34.924782+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOVOK4IV","created_at":"2026-07-05T08:01:34.924782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.20330","citing_title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOVOK4IVC5LCO2PSLAJBNUX6X4","json":"https://pith.science/pith/AOVOK4IVC5LCO2PSLAJBNUX6X4.json","graph_json":"https://pith.science/api/pith-number/AOVOK4IVC5LCO2PSLAJBNUX6X4/graph.json","events_json":"https://pith.science/api/pith-number/AOVOK4IVC5LCO2PSLAJBNUX6X4/events.json","paper":"https://pith.science/paper/AOVOK4IV"},"agent_actions":{"view_html":"https://pith.science/pith/AOVOK4IVC5LCO2PSLAJBNUX6X4","download_json":"https://pith.science/pith/AOVOK4IVC5LCO2PSLAJBNUX6X4.json","view_paper":"https://pith.science/paper/AOVOK4IV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15596&json=true","fetch_graph":"https://pith.science/api/pith-number/AOVOK4IVC5LCO2PSLAJBNUX6X4/graph.json","fetch_events":"https://pith.science/api/pith-number/AOVOK4IVC5LCO2PSLAJBNUX6X4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOVOK4IVC5LCO2PSLAJBNUX6X4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOVOK4IVC5LCO2PSLAJBNUX6X4/action/storage_attestation","attest_author":"https://pith.science/pith/AOVOK4IVC5LCO2PSLAJBNUX6X4/action/author_attestation","sign_citation":"https://pith.science/pith/AOVOK4IVC5LCO2PSLAJBNUX6X4/action/citation_signature","submit_replication":"https://pith.science/pith/AOVOK4IVC5LCO2PSLAJBNUX6X4/action/replication_record"}},"created_at":"2026-07-05T08:01:34.924782+00:00","updated_at":"2026-07-05T08:01:34.924782+00:00"}