{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ","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":"625c64106af67e10e66bc09d73f4dca33e8e4cf5b725d7d796ff17fde9902b4b","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-10T18:52:47Z","title_canon_sha256":"c2b6382f6cad79de25fc995fe985e8bbf76aea05fea0e3ec68ccc6fc33d13c05"},"schema_version":"1.0","source":{"id":"2511.07403","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.07403","created_at":"2026-07-07T00:15:50Z"},{"alias_kind":"arxiv_version","alias_value":"2511.07403v2","created_at":"2026-07-07T00:15:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07403","created_at":"2026-07-07T00:15:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZLLB2PNEZBOE","created_at":"2026-07-07T00:15:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZLLB2PNEZBOE2ZJ6","created_at":"2026-07-07T00:15:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZLLB2PNE","created_at":"2026-07-07T00:15:50Z"}],"graph_snapshots":[{"event_id":"sha256:5840efa83431d85eb63a93596d5563ee8f46707cfcabff8b8dde73e14814ea65","target":"graph","created_at":"2026-07-07T00:15:50Z","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/2511.07403/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning. Existing spatial MLLMs rely on large-scale datasets, explicit 3D inputs, architecture-specific modifications, or sparse Reinforcement Learning (RL) methods that provide insufficient guidance for spatially-grounded reasoning. We introduce SpatialThinker. To our knowledge, it is the first MLLM unifying Scene Graph Generation (SGG) and visual reasoning in a single pass via online RL. The model simulates human-like spatial perception by constructing ","authors_text":"Cihang Xie, Haoqin Tu, Hardy Chen, Hunar Batra, Ronald Clark, Yuanze Lin","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-10T18:52:47Z","title":"SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07403","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:e07766677fc466fd0bffe0e1cf435def3c1c8b3cae198010afb19d3cf9714930","target":"record","created_at":"2026-07-07T00:15:50Z","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":"625c64106af67e10e66bc09d73f4dca33e8e4cf5b725d7d796ff17fde9902b4b","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-10T18:52:47Z","title_canon_sha256":"c2b6382f6cad79de25fc995fe985e8bbf76aea05fea0e3ec68ccc6fc33d13c05"},"schema_version":"1.0","source":{"id":"2511.07403","kind":"arxiv","version":2}},"canonical_sha256":"cad61d3da4c85c4d653e6f9a7b37b546447d59e3a4b229d7346162af6de123d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cad61d3da4c85c4d653e6f9a7b37b546447d59e3a4b229d7346162af6de123d1","first_computed_at":"2026-07-07T00:15:50.674997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T00:15:50.674997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uSLoxRREtEz4H24xhlOdJs+EUdfsTWb1L1OQg3KuMNTLzQv6qZPFOiZmK6qW9suY19VUi5h5yNDd/RDoSRNSAg==","signature_status":"signed_v1","signed_at":"2026-07-07T00:15:50.676219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.07403","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e07766677fc466fd0bffe0e1cf435def3c1c8b3cae198010afb19d3cf9714930","sha256:5840efa83431d85eb63a93596d5563ee8f46707cfcabff8b8dde73e14814ea65"],"state_sha256":"b1b62e2071793a1f8937200fbf191ece5e5619788f18111f8eb9ec9fd2f846af"}