{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VRG3LBHSHVWUZSA7XWP2HD3ZKM","short_pith_number":"pith:VRG3LBHS","schema_version":"1.0","canonical_sha256":"ac4db584f23d6d4cc81fbd9fa38f7953120d188d5a09b7c2120cb28f3a775e44","source":{"kind":"arxiv","id":"2605.26014","version":1},"attestation_state":"computed","paper":{"title":"STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Andong Deng, Chen Chen, Fuxiao Liu, Huaxiu Yao, Mohit Bansal, Qin Zhang, Shoubin Yu, Yiming Liang, Yixiao Chen, Yixuan Wang, Yiyang Zhou","submitted_at":"2026-05-25T16:33:00Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.26014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T16:33:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2ec9c19e4445c54e837c9db6771ea15ec5edcee7a4ab696894bef7afb6e0bf93","abstract_canon_sha256":"4a76824d39167c5417f16f7f2f49eed77cbeda019bbc92d65ca94f287bc428e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:23.355269Z","signature_b64":"UQ226YODoVBuihbEAulLGDbcPifUR9YGSR3vFVTSXL4ir30xYRUA23BBt/bOjg9/dtCbmW5kxCU6vJH8dGnMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac4db584f23d6d4cc81fbd9fa38f7953120d188d5a09b7c2120cb28f3a775e44","last_reissued_at":"2026-05-26T02:05:23.354714Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:23.354714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Andong Deng, Chen Chen, Fuxiao Liu, Huaxiu Yao, Mohit Bansal, Qin Zhang, Shoubin Yu, Yiming Liang, Yixiao Chen, Yixuan Wang, Yiyang Zhou","submitted_at":"2026-05-25T16:33:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26014","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/2605.26014/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.26014","created_at":"2026-05-26T02:05:23.354817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26014v1","created_at":"2026-05-26T02:05:23.354817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26014","created_at":"2026-05-26T02:05:23.354817+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRG3LBHSHVWU","created_at":"2026-05-26T02:05:23.354817+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRG3LBHSHVWUZSA7","created_at":"2026-05-26T02:05:23.354817+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRG3LBHS","created_at":"2026-05-26T02:05:23.354817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRG3LBHSHVWUZSA7XWP2HD3ZKM","json":"https://pith.science/pith/VRG3LBHSHVWUZSA7XWP2HD3ZKM.json","graph_json":"https://pith.science/api/pith-number/VRG3LBHSHVWUZSA7XWP2HD3ZKM/graph.json","events_json":"https://pith.science/api/pith-number/VRG3LBHSHVWUZSA7XWP2HD3ZKM/events.json","paper":"https://pith.science/paper/VRG3LBHS"},"agent_actions":{"view_html":"https://pith.science/pith/VRG3LBHSHVWUZSA7XWP2HD3ZKM","download_json":"https://pith.science/pith/VRG3LBHSHVWUZSA7XWP2HD3ZKM.json","view_paper":"https://pith.science/paper/VRG3LBHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26014&json=true","fetch_graph":"https://pith.science/api/pith-number/VRG3LBHSHVWUZSA7XWP2HD3ZKM/graph.json","fetch_events":"https://pith.science/api/pith-number/VRG3LBHSHVWUZSA7XWP2HD3ZKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRG3LBHSHVWUZSA7XWP2HD3ZKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRG3LBHSHVWUZSA7XWP2HD3ZKM/action/storage_attestation","attest_author":"https://pith.science/pith/VRG3LBHSHVWUZSA7XWP2HD3ZKM/action/author_attestation","sign_citation":"https://pith.science/pith/VRG3LBHSHVWUZSA7XWP2HD3ZKM/action/citation_signature","submit_replication":"https://pith.science/pith/VRG3LBHSHVWUZSA7XWP2HD3ZKM/action/replication_record"}},"created_at":"2026-05-26T02:05:23.354817+00:00","updated_at":"2026-05-26T02:05:23.354817+00:00"}