{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PQQ4SUMULXOSF4JJM6SXJ47R43","short_pith_number":"pith:PQQ4SUMU","canonical_record":{"source":{"id":"2608.12220","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T16:14:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"89c336730e899ab143c0e8458bedb49fcd56e65c4a8101495a92d82dd6f08d2e","abstract_canon_sha256":"21933ef2daa02a42822ef2afbbcc773b1e29c7dc93e8fb081ea50e7583c3fbb7"},"schema_version":"1.0"},"canonical_sha256":"7c21c951945ddd22f12967a574f3f1e6fb3e0ccf5f069082d97a741fb71d9f0d","source":{"kind":"arxiv","id":"2608.12220","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12220","created_at":"2026-08-13T01:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12220v1","created_at":"2026-08-13T01:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12220","created_at":"2026-08-13T01:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"PQQ4SUMULXOS","created_at":"2026-08-13T01:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"PQQ4SUMULXOSF4JJ","created_at":"2026-08-13T01:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"PQQ4SUMU","created_at":"2026-08-13T01:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PQQ4SUMULXOSF4JJM6SXJ47R43","target":"record","payload":{"canonical_record":{"source":{"id":"2608.12220","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T16:14:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"89c336730e899ab143c0e8458bedb49fcd56e65c4a8101495a92d82dd6f08d2e","abstract_canon_sha256":"21933ef2daa02a42822ef2afbbcc773b1e29c7dc93e8fb081ea50e7583c3fbb7"},"schema_version":"1.0"},"canonical_sha256":"7c21c951945ddd22f12967a574f3f1e6fb3e0ccf5f069082d97a741fb71d9f0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:30:32.615757Z","signature_b64":"j6aaXBm/WQRfCZlz7vMJ9rGij6WEkmYB2KJ4nmc6XOT7NP1aZ44KCc8UokcHteGFDmHDorwgj7/b70iNAzepBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c21c951945ddd22f12967a574f3f1e6fb3e0ccf5f069082d97a741fb71d9f0d","last_reissued_at":"2026-08-13T01:30:32.613475Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:30:32.613475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.12220","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-13T01:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L/CoCev9FSOws0HP5YJzwfNgJc8PZVW35UDqlMn1LPNNgv2mK1JdRX2tEUy5offuMIGMW7Ql4wWsj/vafUW+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T17:53:02.947943Z"},"content_sha256":"81aac0201048bfdfc74789fb842c9390802810d435bf255160c8554308482afd","schema_version":"1.0","event_id":"sha256:81aac0201048bfdfc74789fb842c9390802810d435bf255160c8554308482afd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PQQ4SUMULXOSF4JJM6SXJ47R43","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Huining Yuan, Weichen Zhang, Xiao-Ping Zhang, Xinlei Chen, Zile Zhou","submitted_at":"2026-08-12T16:14:25Z","abstract_excerpt":"Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps. Concurrently, structured reasoning approaches overlook the critical depth perception necessary for comprehensive 3D understanding. To address these challenges, we propose SCOUT (Structured Chain-Of-Thought Utilizing Process-Supervised RL Training). Specifically, we design a structured Chain-of-Thought (CoT) framework that expli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12220","kind":"arxiv","version":1},"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/2608.12220/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":"2026-08-13T01:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J8u61tooaTjPlAYt1CIeB071gRLhUU6YKVZ3X+OnHTHPiK9wbNAm1p7qmwsmYUicdyvL+MmeUsKXMn4oOlChBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T17:53:02.948842Z"},"content_sha256":"c7cadb0c99d497921e4bb648c731e91e69973a6e2352b849460d16db950976c5","schema_version":"1.0","event_id":"sha256:c7cadb0c99d497921e4bb648c731e91e69973a6e2352b849460d16db950976c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQQ4SUMULXOSF4JJM6SXJ47R43/bundle.json","state_url":"https://pith.science/pith/PQQ4SUMULXOSF4JJM6SXJ47R43/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQQ4SUMULXOSF4JJM6SXJ47R43/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":"2026-08-22T17:53:02Z","links":{"resolver":"https://pith.science/pith/PQQ4SUMULXOSF4JJM6SXJ47R43","bundle":"https://pith.science/pith/PQQ4SUMULXOSF4JJM6SXJ47R43/bundle.json","state":"https://pith.science/pith/PQQ4SUMULXOSF4JJM6SXJ47R43/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQQ4SUMULXOSF4JJM6SXJ47R43/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PQQ4SUMULXOSF4JJM6SXJ47R43","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":"21933ef2daa02a42822ef2afbbcc773b1e29c7dc93e8fb081ea50e7583c3fbb7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T16:14:25Z","title_canon_sha256":"89c336730e899ab143c0e8458bedb49fcd56e65c4a8101495a92d82dd6f08d2e"},"schema_version":"1.0","source":{"id":"2608.12220","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12220","created_at":"2026-08-13T01:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12220v1","created_at":"2026-08-13T01:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12220","created_at":"2026-08-13T01:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"PQQ4SUMULXOS","created_at":"2026-08-13T01:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"PQQ4SUMULXOSF4JJ","created_at":"2026-08-13T01:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"PQQ4SUMU","created_at":"2026-08-13T01:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:c7cadb0c99d497921e4bb648c731e91e69973a6e2352b849460d16db950976c5","target":"graph","created_at":"2026-08-13T01:30:32Z","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/2608.12220/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps. Concurrently, structured reasoning approaches overlook the critical depth perception necessary for comprehensive 3D understanding. To address these challenges, we propose SCOUT (Structured Chain-Of-Thought Utilizing Process-Supervised RL Training). Specifically, we design a structured Chain-of-Thought (CoT) framework that expli","authors_text":"Huining Yuan, Weichen Zhang, Xiao-Ping Zhang, Xinlei Chen, Zile Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T16:14:25Z","title":"SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12220","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":"sha256:81aac0201048bfdfc74789fb842c9390802810d435bf255160c8554308482afd","target":"record","created_at":"2026-08-13T01:30:32Z","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":"21933ef2daa02a42822ef2afbbcc773b1e29c7dc93e8fb081ea50e7583c3fbb7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T16:14:25Z","title_canon_sha256":"89c336730e899ab143c0e8458bedb49fcd56e65c4a8101495a92d82dd6f08d2e"},"schema_version":"1.0","source":{"id":"2608.12220","kind":"arxiv","version":1}},"canonical_sha256":"7c21c951945ddd22f12967a574f3f1e6fb3e0ccf5f069082d97a741fb71d9f0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c21c951945ddd22f12967a574f3f1e6fb3e0ccf5f069082d97a741fb71d9f0d","first_computed_at":"2026-08-13T01:30:32.613475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:30:32.613475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j6aaXBm/WQRfCZlz7vMJ9rGij6WEkmYB2KJ4nmc6XOT7NP1aZ44KCc8UokcHteGFDmHDorwgj7/b70iNAzepBw==","signature_status":"signed_v1","signed_at":"2026-08-13T01:30:32.615757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12220","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81aac0201048bfdfc74789fb842c9390802810d435bf255160c8554308482afd","sha256:c7cadb0c99d497921e4bb648c731e91e69973a6e2352b849460d16db950976c5"],"state_sha256":"6a9187e38d6d01ffe7e419eccc1a2eb3ccdb8cbe048c3ad2fe5c48f86eb2de9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j98q+69dYf22JKQU9EgsCGkcGJy+3gcNX5SxKonAtKc5Dicc4yTtDpWGbrpLk2Bzs2xh6o6MtfoTS16XukszBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T17:53:02.953423Z","bundle_sha256":"f7810ec57081b751e52254357273212a8c58c31eb3f40454581164a821bf096d"}}