{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VRG3LBHSHVWUZSA7XWP2HD3ZKM","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":"4a76824d39167c5417f16f7f2f49eed77cbeda019bbc92d65ca94f287bc428e3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T16:33:00Z","title_canon_sha256":"2ec9c19e4445c54e837c9db6771ea15ec5edcee7a4ab696894bef7afb6e0bf93"},"schema_version":"1.0","source":{"id":"2605.26014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26014","created_at":"2026-05-26T02:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26014v1","created_at":"2026-05-26T02:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26014","created_at":"2026-05-26T02:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"VRG3LBHSHVWU","created_at":"2026-05-26T02:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"VRG3LBHSHVWUZSA7","created_at":"2026-05-26T02:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"VRG3LBHS","created_at":"2026-05-26T02:05:23Z"}],"graph_snapshots":[{"event_id":"sha256:225c7e8e38e049cd751fdcc8bf141d1151f17dbcc37bc2874dbf70c2efb376df","target":"graph","created_at":"2026-05-26T02:05:23Z","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/2605.26014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames. Existing methods built on large vision-language models (LVLMs) often address this challenge by externalizing reasoning through textual chain-of-thought (CoT), keyframe selection, repeated frame reinsertion, or external tool use. While effective, such pipelines increase inference-time latency and engineering complexity, and they force temporal-visual evidence to be serialized into text or repeatedly re-encoded from frames. Inspired by the intuition that visual reasoning can occur implic","authors_text":"Andong Deng, Chen Chen, Fuxiao Liu, Huaxiu Yao, Mohit Bansal, Qin Zhang, Shoubin Yu, Yiming Liang, Yixiao Chen, Yixuan Wang, Yiyang Zhou","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T16:33:00Z","title":"STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26014","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:d9922f09090bd95a721b8664373df9b538e3aed3852fd5c5ff22f4311e6765a4","target":"record","created_at":"2026-05-26T02:05:23Z","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":"4a76824d39167c5417f16f7f2f49eed77cbeda019bbc92d65ca94f287bc428e3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T16:33:00Z","title_canon_sha256":"2ec9c19e4445c54e837c9db6771ea15ec5edcee7a4ab696894bef7afb6e0bf93"},"schema_version":"1.0","source":{"id":"2605.26014","kind":"arxiv","version":1}},"canonical_sha256":"ac4db584f23d6d4cc81fbd9fa38f7953120d188d5a09b7c2120cb28f3a775e44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac4db584f23d6d4cc81fbd9fa38f7953120d188d5a09b7c2120cb28f3a775e44","first_computed_at":"2026-05-26T02:05:23.354714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:23.354714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UQ226YODoVBuihbEAulLGDbcPifUR9YGSR3vFVTSXL4ir30xYRUA23BBt/bOjg9/dtCbmW5kxCU6vJH8dGnMCw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:23.355269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9922f09090bd95a721b8664373df9b538e3aed3852fd5c5ff22f4311e6765a4","sha256:225c7e8e38e049cd751fdcc8bf141d1151f17dbcc37bc2874dbf70c2efb376df"],"state_sha256":"5c8200ef697a91e7da6ad80cd56de116963d6ee0ab1e1b960d351aefa4d874d8"}