{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HLQVQ6CPFXAJDK3E4VBUPKRVIP","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":"debf54fb9214e3d4166bcffd176ade6884cc8f0355ae695f4ba3c8adbf478895","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-01T15:28:13Z","title_canon_sha256":"5ed9a9fe5370727cc641da44d7aa6ad3382d53375190f16aa191747cdee6b394"},"schema_version":"1.0","source":{"id":"2604.03318","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.03318","created_at":"2026-05-26T02:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2604.03318v2","created_at":"2026-05-26T02:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03318","created_at":"2026-05-26T02:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"HLQVQ6CPFXAJ","created_at":"2026-05-26T02:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"HLQVQ6CPFXAJDK3E","created_at":"2026-05-26T02:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"HLQVQ6CP","created_at":"2026-05-26T02:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:544f2839706c6469b3f392ecc5fb6268b0a0e340eb5017d24b06b31fcddff7c9","target":"graph","created_at":"2026-05-26T02:05:08Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"we propose EgoMind, a Chain-of-Thought framework that enables geometry-free spatial reasoning through Role-Play Caption, which jointly constructs a coherent linguistic scene graph across frames, and Progressive Spatial Analysis, which progressively reasons toward task-specific questions. With only 5K auto-generated SFT samples and 20K RL samples, EgoMind achieves competitive results on VSI-Bench, SPAR-Bench, SITE-Bench, and SPBench"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That purely linguistic role-play captions can reliably construct cross-frame spatial relationships sufficient for competitive benchmark performance without any geometric supervision or 3D priors."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"EgoMind activates spatial cognition in MLLMs via linguistic Role-Play Caption and Progressive Spatial Analysis, reaching competitive results on VSI-Bench, SPAR-Bench, SITE-Bench and SPBench with only 5K SFT and 20K RL samples."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"EgoMind activates spatial reasoning in MLLMs through purely linguistic chain-of-thought without 3D geometry or priors."}],"snapshot_sha256":"65d0b684fb8acfa1c1c74839b35dcdde1a71c81c137fdf68b7b61f8115ca96de"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"826fb40e55ddd2ea0c1dec6a22996605e998f578b06df7502a444da527fc6e81"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.03318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) are increasingly being applied to spatial cognition tasks, where they are expected to understand and interact with complex environments. Most existing works improve spatial reasoning by introducing 3D priors or geometric supervision, which enhances performance but incurs substantial data preparation and alignment costs. In contrast, purely 2D approaches often struggle with multi-frame spatial reasoning due to their limited ability to capture cross-frame spatial relationships. To address these limitations, we propose EgoMind, a Chain-of-Thought framework","authors_text":"Di Huang, Huiqun Wang, Zhenghao Chen","cross_cats":[],"headline":"EgoMind activates spatial reasoning in MLLMs through purely linguistic chain-of-thought without 3D geometry or priors.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-01T15:28:13Z","title":"EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.03318","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T22:38:11.218940Z","id":"51e9e421-ae38-491e-b7ea-c622e707fe04","model_set":{"reader":"grok-4.3"},"one_line_summary":"EgoMind activates spatial cognition in MLLMs via linguistic Role-Play Caption and Progressive Spatial Analysis, reaching competitive results on VSI-Bench, SPAR-Bench, SITE-Bench and SPBench with only 5K SFT and 20K RL samples.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"EgoMind activates spatial reasoning in MLLMs through purely linguistic chain-of-thought without 3D geometry or priors.","strongest_claim":"we propose EgoMind, a Chain-of-Thought framework that enables geometry-free spatial reasoning through Role-Play Caption, which jointly constructs a coherent linguistic scene graph across frames, and Progressive Spatial Analysis, which progressively reasons toward task-specific questions. With only 5K auto-generated SFT samples and 20K RL samples, EgoMind achieves competitive results on VSI-Bench, SPAR-Bench, SITE-Bench, and SPBench","weakest_assumption":"That purely linguistic role-play captions can reliably construct cross-frame spatial relationships sufficient for competitive benchmark performance without any geometric supervision or 3D priors."}},"verdict_id":"51e9e421-ae38-491e-b7ea-c622e707fe04"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0d2f301d021103d9af36606e46f06533ba42be904bf62adcfc18db9fb7d93830","target":"record","created_at":"2026-05-26T02:05:08Z","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":"debf54fb9214e3d4166bcffd176ade6884cc8f0355ae695f4ba3c8adbf478895","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-01T15:28:13Z","title_canon_sha256":"5ed9a9fe5370727cc641da44d7aa6ad3382d53375190f16aa191747cdee6b394"},"schema_version":"1.0","source":{"id":"2604.03318","kind":"arxiv","version":2}},"canonical_sha256":"3ae158784f2dc091ab64e54347aa3543fd8f9301accc5699f68c598194ac3b5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ae158784f2dc091ab64e54347aa3543fd8f9301accc5699f68c598194ac3b5b","first_computed_at":"2026-05-26T02:05:08.816284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:08.816284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CL+FDYFDM19VQ6VaoINzPeYHcZwlFpDSzht5IfYkpYb7KsH1fVK0fTGlrQ+9w+tDZE2jJ9ZgIyqv5Cgnsvv9AA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:08.817034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.03318","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d2f301d021103d9af36606e46f06533ba42be904bf62adcfc18db9fb7d93830","sha256:544f2839706c6469b3f392ecc5fb6268b0a0e340eb5017d24b06b31fcddff7c9"],"state_sha256":"dca3d30ec34bc8ee6f67ab50cb3a911458904e9b10f7404df0ae1c1269d89545"}