{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OP2HN2ZQ2S24PGV6RHIGFZLAQE","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":"e95997ed9b4c1fd0ff6cce3a7d04b10a7b1769682b1f5402cc74485ddc9d4fbb","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T17:59:45Z","title_canon_sha256":"8f2a7f623f3c68e63463d090f47fb4506eb475b9a71beb6673e5f4e95cd79860"},"schema_version":"1.0","source":{"id":"2406.07544","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07544","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07544v2","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07544","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"pith_short_12","alias_value":"OP2HN2ZQ2S24","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"pith_short_16","alias_value":"OP2HN2ZQ2S24PGV6","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"pith_short_8","alias_value":"OP2HN2ZQ","created_at":"2026-07-05T08:37:07Z"}],"graph_snapshots":[{"event_id":"sha256:ffc02f0e187efd633d016ee3b664f15cc7683588553f6b37f3ba57b08f2ae4e4","target":"graph","created_at":"2026-07-05T08:37:07Z","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/2406.07544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Being able to carry out complicated vision language reasoning tasks in 3D space represents a significant milestone in developing household robots and human-centered embodied AI. In this work, we demonstrate that a critical and distinct challenge in 3D vision language reasoning is situational awareness, which incorporates two key components: (1) The autonomous agent grounds its self-location based on a language prompt. (2) The agent answers open-ended questions from the perspective of its calculated position. To address this challenge, we introduce SIG3D, an end-to-end Situation-Grounded model ","authors_text":"Liang-Yan Gui, Yunze Man, Yu-Xiong Wang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T17:59:45Z","title":"Situational Awareness Matters in 3D Vision Language Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07544","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:dd45dc94831541da2d5b4591107ed849208b144a335145da4661fe0e18aa3b7d","target":"record","created_at":"2026-07-05T08:37:07Z","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":"e95997ed9b4c1fd0ff6cce3a7d04b10a7b1769682b1f5402cc74485ddc9d4fbb","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T17:59:45Z","title_canon_sha256":"8f2a7f623f3c68e63463d090f47fb4506eb475b9a71beb6673e5f4e95cd79860"},"schema_version":"1.0","source":{"id":"2406.07544","kind":"arxiv","version":2}},"canonical_sha256":"73f476eb30d4b5c79abe89d062e5608126963ced14b283ac06448348e5cce99b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73f476eb30d4b5c79abe89d062e5608126963ced14b283ac06448348e5cce99b","first_computed_at":"2026-07-05T08:37:07.203649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:07.203649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LVrXACh8Z+tmOtrrl776CS1JOW0mGopa0Bv4oa9KGOlj9jkuJDpF4UCS7APKeaQZte5TSIGiCOr/ZVjy/69YDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:07.204102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07544","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd45dc94831541da2d5b4591107ed849208b144a335145da4661fe0e18aa3b7d","sha256:ffc02f0e187efd633d016ee3b664f15cc7683588553f6b37f3ba57b08f2ae4e4"],"state_sha256":"0af89d19f9fae4f9d9db218e9c613f208b52a62e496cdb9c558e1258ea19d7b2"}