{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AOVOK4IVC5LCO2PSLAJBNUX6X4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d0410faa2fc0108abd624bb7eacbfcfcbf1e415e57c7fb75c5f299ff944df3fe","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T07:44:25Z","title_canon_sha256":"829e6b88748571ab496e2009ea49125f0867efb998a3a514ebbc955b34819dce"},"schema_version":"1.0","source":{"id":"2311.15596","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15596","created_at":"2026-07-05T08:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15596v2","created_at":"2026-07-05T08:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15596","created_at":"2026-07-05T08:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"AOVOK4IVC5LC","created_at":"2026-07-05T08:01:34Z"},{"alias_kind":"pith_short_16","alias_value":"AOVOK4IVC5LCO2PS","created_at":"2026-07-05T08:01:34Z"},{"alias_kind":"pith_short_8","alias_value":"AOVOK4IV","created_at":"2026-07-05T08:01:34Z"}],"graph_snapshots":[{"event_id":"sha256:54dfcb4dec488a32e401d33a6e2ee528b5eebdaab296090069f10b70ad2e06bc","target":"graph","created_at":"2026-07-05T08:01:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.15596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huaping Liu, Jingwen Wu, Kechen Fang, Peng Li, Sijie Cheng, Yang Liu, Zhicheng Guo","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T07:44:25Z","title":"EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15596","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4c9f04214bab5784fb485896e11a806d555a6bb822a1506d0a15451403d0fb3a","target":"record","created_at":"2026-07-05T08:01:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d0410faa2fc0108abd624bb7eacbfcfcbf1e415e57c7fb75c5f299ff944df3fe","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T07:44:25Z","title_canon_sha256":"829e6b88748571ab496e2009ea49125f0867efb998a3a514ebbc955b34819dce"},"schema_version":"1.0","source":{"id":"2311.15596","kind":"arxiv","version":2}},"canonical_sha256":"03aae5711517562769f2581216d2febf22b8a65bbb5ae27b5a057cd3cfd479ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03aae5711517562769f2581216d2febf22b8a65bbb5ae27b5a057cd3cfd479ad","first_computed_at":"2026-07-05T08:01:34.924720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:34.924720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5sr6Ltjss2jxjGdGMK62ck1L8Bp3hRqa6AaN2R/mROXhzKSu1H6iozcJohEWSCOmkbQB0VZqxb7E1j2KPZu8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:34.925262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.15596","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c9f04214bab5784fb485896e11a806d555a6bb822a1506d0a15451403d0fb3a","sha256:54dfcb4dec488a32e401d33a6e2ee528b5eebdaab296090069f10b70ad2e06bc"],"state_sha256":"de3a44d69200cad4b88eef330a0644ca94def00d2af3ce38ca4779caf20b9de2"}