{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SANGPQ5PEDCSWEWGADC2AF3BYN","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":"568c076395116300e36fa6190679c75b1eee3750ec732196721a49e09d1948cd","cross_cats_sorted":["cs.CL","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:49:28Z","title_canon_sha256":"d90b8b364206334a26b19c04fdd45ba10df231173f553962d946805767757031"},"schema_version":"1.0","source":{"id":"2410.02730","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02730","created_at":"2026-07-05T12:02:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02730v3","created_at":"2026-07-05T12:02:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02730","created_at":"2026-07-05T12:02:36Z"},{"alias_kind":"pith_short_12","alias_value":"SANGPQ5PEDCS","created_at":"2026-07-05T12:02:36Z"},{"alias_kind":"pith_short_16","alias_value":"SANGPQ5PEDCSWEWG","created_at":"2026-07-05T12:02:36Z"},{"alias_kind":"pith_short_8","alias_value":"SANGPQ5P","created_at":"2026-07-05T12:02:36Z"}],"graph_snapshots":[{"event_id":"sha256:222d112cc0ee8008055b5404bb73075ee8c27a91c117701d9aed6ea5edf67e55","target":"graph","created_at":"2026-07-05T12:02:36Z","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/2410.02730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) have achieved significant progress in tasks like visual question answering and document understanding. However, their potential to comprehend embodied environments and navigate within them remains underexplored. In this work, we first study the challenge of open-vocabulary object navigation by introducing DivScene, a large-scale dataset with 4,614 houses across 81 scene types and 5,707 kinds of target objects. Our dataset provides a much greater diversity of target objects and scene types than existing datasets, enabling a comprehensive task evaluation. We ","authors_text":"Dong Yu, Hongming Zhang, Kaixin Ma, Tianqing Fang, Xiaoman Pan, Yangqiu Song, Ye Tian, Yue Yang, Zhaowei Wang","cross_cats":["cs.CL","cs.RO"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:49:28Z","title":"DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02730","kind":"arxiv","version":3},"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:bf93845df13c799335df6eb7292206ef9f8bda69edce06f7b8cd7f03bd1dfef4","target":"record","created_at":"2026-07-05T12:02:36Z","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":"568c076395116300e36fa6190679c75b1eee3750ec732196721a49e09d1948cd","cross_cats_sorted":["cs.CL","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:49:28Z","title_canon_sha256":"d90b8b364206334a26b19c04fdd45ba10df231173f553962d946805767757031"},"schema_version":"1.0","source":{"id":"2410.02730","kind":"arxiv","version":3}},"canonical_sha256":"901a67c3af20c52b12c600c5a01761c35e75db7e02062e639ba1cfc0d8e0f62a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"901a67c3af20c52b12c600c5a01761c35e75db7e02062e639ba1cfc0d8e0f62a","first_computed_at":"2026-07-05T12:02:36.389538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:36.389538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S9qAaSyedfyQ/SBdJFJcrEY/gSaQhENrDq03skb6iFSP8Al45ddimKg65jfnTY6doKz71YMXr00ohkegiQViCg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:36.390182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02730","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf93845df13c799335df6eb7292206ef9f8bda69edce06f7b8cd7f03bd1dfef4","sha256:222d112cc0ee8008055b5404bb73075ee8c27a91c117701d9aed6ea5edf67e55"],"state_sha256":"6aedd32ace214e6f1fba3d2f71f24316ef25ca226814ca967f35516037c199f6"}