{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QBV2GR33GEUMDKSRGKHQAR4J2V","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":"3a268a3c1d25c2ac31655de2d3ee0a2e9a60ddf157d49d821b6fce9440b09339","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T01:36:22Z","title_canon_sha256":"a82bc5c8b9b16884af889b0d1557127fa1a012b312102520a416ef18cb4d7a1e"},"schema_version":"1.0","source":{"id":"2508.17595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17595","created_at":"2026-07-05T11:58:44Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17595v1","created_at":"2026-07-05T11:58:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17595","created_at":"2026-07-05T11:58:44Z"},{"alias_kind":"pith_short_12","alias_value":"QBV2GR33GEUM","created_at":"2026-07-05T11:58:44Z"},{"alias_kind":"pith_short_16","alias_value":"QBV2GR33GEUMDKSR","created_at":"2026-07-05T11:58:44Z"},{"alias_kind":"pith_short_8","alias_value":"QBV2GR33","created_at":"2026-07-05T11:58:44Z"}],"graph_snapshots":[{"event_id":"sha256:ee9e062bac7bbeabbcd4ab278d68d367bf192929b6453fd00857042b19b18f53","target":"graph","created_at":"2026-07-05T11:58:44Z","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/2508.17595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning about fine-grained spatial relationships in warehouse-scale environments poses a significant challenge for existing vision-language models (VLMs), which often struggle to comprehend 3D layouts, object arrangements, and multimodal cues in real-world industrial settings. In this paper, we present TinyGiantVLM, a lightweight and modular two-stage framework designed for physical spatial reasoning, distinguishing itself from traditional geographic reasoning in complex logistics scenes. Our approach encodes both global and region-level features from RGB and depth modalities using pretraine","authors_text":"Hoang M. Truong, Vinh-Thuan Ly, Xuan-Huong Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T01:36:22Z","title":"TinyGiantVLM: A Lightweight Vision-Language Architecture for Spatial Reasoning under Resource Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17595","kind":"arxiv","version":1},"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":"sha256:423bc97714f214ad27cfbc19eecf46f5d39b84d77221561ac659c26cde54a74e","target":"record","created_at":"2026-07-05T11:58:44Z","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":"3a268a3c1d25c2ac31655de2d3ee0a2e9a60ddf157d49d821b6fce9440b09339","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T01:36:22Z","title_canon_sha256":"a82bc5c8b9b16884af889b0d1557127fa1a012b312102520a416ef18cb4d7a1e"},"schema_version":"1.0","source":{"id":"2508.17595","kind":"arxiv","version":1}},"canonical_sha256":"806ba3477b3128c1aa51328f004789d5526b06a430e98b1d467f6132c1260e16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"806ba3477b3128c1aa51328f004789d5526b06a430e98b1d467f6132c1260e16","first_computed_at":"2026-07-05T11:58:44.309405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:44.309405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yHJuSULq1WBSTFRtTQu+j5GcNYLfGSd9qQAqyrfUht9ovAD13HiHCPNUl0vh1Z6hdpjjz7IM5Erb9wVnM1ciBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:44.309992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:423bc97714f214ad27cfbc19eecf46f5d39b84d77221561ac659c26cde54a74e","sha256:ee9e062bac7bbeabbcd4ab278d68d367bf192929b6453fd00857042b19b18f53"],"state_sha256":"8aabe23cf96d7794180efec63de0e61ff968b248888a9204fd2384aaa7c8e4c6"}