{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ","short_pith_number":"pith:ZLLB2PNE","canonical_record":{"source":{"id":"2511.07403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-10T18:52:47Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"c2b6382f6cad79de25fc995fe985e8bbf76aea05fea0e3ec68ccc6fc33d13c05","abstract_canon_sha256":"625c64106af67e10e66bc09d73f4dca33e8e4cf5b725d7d796ff17fde9902b4b"},"schema_version":"1.0"},"canonical_sha256":"cad61d3da4c85c4d653e6f9a7b37b546447d59e3a4b229d7346162af6de123d1","source":{"kind":"arxiv","id":"2511.07403","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ","target":"record","payload":{"canonical_record":{"source":{"id":"2511.07403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-10T18:52:47Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"c2b6382f6cad79de25fc995fe985e8bbf76aea05fea0e3ec68ccc6fc33d13c05","abstract_canon_sha256":"625c64106af67e10e66bc09d73f4dca33e8e4cf5b725d7d796ff17fde9902b4b"},"schema_version":"1.0"},"canonical_sha256":"cad61d3da4c85c4d653e6f9a7b37b546447d59e3a4b229d7346162af6de123d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:15:50.676219Z","signature_b64":"uSLoxRREtEz4H24xhlOdJs+EUdfsTWb1L1OQg3KuMNTLzQv6qZPFOiZmK6qW9suY19VUi5h5yNDd/RDoSRNSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad61d3da4c85c4d653e6f9a7b37b546447d59e3a4b229d7346162af6de123d1","last_reissued_at":"2026-07-07T00:15:50.674997Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:15:50.674997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.07403","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T00:15:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dA/wa1T3flJ9Uk9/AlMyzTQuR4Cto8986CEjivjw7VU9dR8g4Yv3uR+QpxuIzN9xDTD/rdCBWC9EoBbv2I5GCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:50:59.074641Z"},"content_sha256":"e07766677fc466fd0bffe0e1cf435def3c1c8b3cae198010afb19d3cf9714930","schema_version":"1.0","event_id":"sha256:e07766677fc466fd0bffe0e1cf435def3c1c8b3cae198010afb19d3cf9714930"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Haoqin Tu, Hardy Chen, Hunar Batra, Ronald Clark, Yuanze Lin","submitted_at":"2025-11-10T18:52:47Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07403","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2511.07403/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T00:15:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"azjMY149XWgCvFMrXJ9o+WI2+e00WxV/GBDBnUN37jMePHGkCxdRMcZaUAdtzpS4jmMJknusZQ7tKEfCDvvyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:50:59.075573Z"},"content_sha256":"5840efa83431d85eb63a93596d5563ee8f46707cfcabff8b8dde73e14814ea65","schema_version":"1.0","event_id":"sha256:5840efa83431d85eb63a93596d5563ee8f46707cfcabff8b8dde73e14814ea65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ/bundle.json","state_url":"https://pith.science/pith/ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T06:50:59Z","links":{"resolver":"https://pith.science/pith/ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ","bundle":"https://pith.science/pith/ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ/bundle.json","state":"https://pith.science/pith/ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLLB2PNEZBOE2ZJ6N6NHWN5VIZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"axuWVmBakxIw5Y2dxktwp2p71pbmH/U3OW3ufQlaOyQiLLthVvtKdjoA1OVZc4tiFMI2PBhPW6kbaUPKmhM5Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:50:59.081595Z","bundle_sha256":"7046aff74eb1047173cbc56a228e6c32fbc43ba830174727a59613a477755d39"}}