{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DW2HM627Q4JTZYXWFWLNGRF2PB","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":"f25fe517a1211e2f321174f820118f4e5eeb284bd84fa99a04a76e5581eb7d9a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T05:58:22Z","title_canon_sha256":"0af4118fe363e5dda5ff6d2565447c939a7b7c4942fc9581c1a12e4f5630852c"},"schema_version":"1.0","source":{"id":"2608.05631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05631","created_at":"2026-08-07T00:50:30Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05631v1","created_at":"2026-08-07T00:50:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05631","created_at":"2026-08-07T00:50:30Z"},{"alias_kind":"pith_short_12","alias_value":"DW2HM627Q4JT","created_at":"2026-08-07T00:50:30Z"},{"alias_kind":"pith_short_16","alias_value":"DW2HM627Q4JTZYXW","created_at":"2026-08-07T00:50:30Z"},{"alias_kind":"pith_short_8","alias_value":"DW2HM627","created_at":"2026-08-07T00:50:30Z"}],"graph_snapshots":[{"event_id":"sha256:0d57176a2edb04a1d5c02593c34287b75f60806b9cc35609851589f8168a5f7a","target":"graph","created_at":"2026-08-07T00:50:30Z","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/2608.05631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models excel at passive perception but struggle with complex visual cognitive tasks requiring multi-step temporal reasoning. This degradation largely stems from the inherent ambiguity of language-based reasoning, which often fails to accurately articulate continuous visual transformations. To address this, we propose ChronoVision, a multimodal framework designed to align visual logic with latent imagery. During supervised fine-tuning, a Reconstructive Visual Head predicts the latent representation of the final transformed state, while an ROI Attention Locating module ","authors_text":"Bingxuan Li, Boyi Li, Houze Yang, Jian Xu, Rushi Wang, Tianjiao Yu, Xu Cao, Yifan Shen, Yuner Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T05:58:22Z","title":"ChronoVision: Temporal Reasoning via Latent State Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05631","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":"sha256:80637f824508148f4097b1f82b2e59ecf2dbcf03d2c9a2886bed7164b47a554a","target":"record","created_at":"2026-08-07T00:50:30Z","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":"f25fe517a1211e2f321174f820118f4e5eeb284bd84fa99a04a76e5581eb7d9a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T05:58:22Z","title_canon_sha256":"0af4118fe363e5dda5ff6d2565447c939a7b7c4942fc9581c1a12e4f5630852c"},"schema_version":"1.0","source":{"id":"2608.05631","kind":"arxiv","version":1}},"canonical_sha256":"1db4767b5f87133ce2f62d96d344ba7847ee39955f4a65bd7f72cdc08358ec1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1db4767b5f87133ce2f62d96d344ba7847ee39955f4a65bd7f72cdc08358ec1d","first_computed_at":"2026-08-07T00:50:30.738748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:50:30.738748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"plnk6WApLrmVYAQXjXx9WSMBaxd3L0K6cVw9oG66pegipm0xXqh3FmLOrV7J0SRgEbLf/MSfV85B6+02TvsnBg==","signature_status":"signed_v1","signed_at":"2026-08-07T00:50:30.740092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80637f824508148f4097b1f82b2e59ecf2dbcf03d2c9a2886bed7164b47a554a","sha256:0d57176a2edb04a1d5c02593c34287b75f60806b9cc35609851589f8168a5f7a"],"state_sha256":"d834122aca0f14bb10f47d1833293f6032513ae84398a965c1e69ed6d61b252c"}