{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2KPPFJ6FWGK27XF5HSNJHT5NKC","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":"24798c9c81575561982875f81bb5d5f6a77bf9073f3a1b90fb8b59e26fa7ca30","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T13:55:55Z","title_canon_sha256":"1386968f2873048a2ff042ea01fbb2ea466bfbd9acfaa918dc1a403ee9efd397"},"schema_version":"1.0","source":{"id":"2607.08497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08497","created_at":"2026-07-10T01:19:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08497v1","created_at":"2026-07-10T01:19:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08497","created_at":"2026-07-10T01:19:52Z"},{"alias_kind":"pith_short_12","alias_value":"2KPPFJ6FWGK2","created_at":"2026-07-10T01:19:52Z"},{"alias_kind":"pith_short_16","alias_value":"2KPPFJ6FWGK27XF5","created_at":"2026-07-10T01:19:52Z"},{"alias_kind":"pith_short_8","alias_value":"2KPPFJ6F","created_at":"2026-07-10T01:19:52Z"}],"graph_snapshots":[{"event_id":"sha256:9fc83cb70842871083501dd31b74cbe13cc2e95644da61eee1a01cf80bdaaaa5","target":"graph","created_at":"2026-07-10T01:19:52Z","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/2607.08497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing. However, they repeatedly feed all historical visual and textual inputs into a shared context window, limiting long-horizon multimodal dialogue due to visual token explosion and unreliable cross-turn referencing. We propose a Cognitive-structured Multimodal Agent that externalizes visual information into an Episodic Visual Memory and selectively reactivates relevant episodes during reasoning. The agent consists of a Perceptual Abstraction Engine for structu","authors_text":"Canmiao Fu, Chen Li, Feng Wang, Ge Li, Jing Lyu, Zhipeng Huang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T13:55:55Z","title":"Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08497","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:dfa90d942f941688623ea763fd9488fad117b71e405aad1897f5bfdc7582da69","target":"record","created_at":"2026-07-10T01:19:52Z","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":"24798c9c81575561982875f81bb5d5f6a77bf9073f3a1b90fb8b59e26fa7ca30","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T13:55:55Z","title_canon_sha256":"1386968f2873048a2ff042ea01fbb2ea466bfbd9acfaa918dc1a403ee9efd397"},"schema_version":"1.0","source":{"id":"2607.08497","kind":"arxiv","version":1}},"canonical_sha256":"d29ef2a7c5b195afdcbd3c9a93cfad50ba1507f9d569ace44cf5bbfcbe36fa23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d29ef2a7c5b195afdcbd3c9a93cfad50ba1507f9d569ace44cf5bbfcbe36fa23","first_computed_at":"2026-07-10T01:19:52.152701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:52.152701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tTo44m4JJ3cg2JGS0DAQ6w5V168ZpvxwLSehHT8o7ZOHSYN1+5iGUZ9GXV/WMLktmRXiZo9UsMbfddlSR9G+AQ==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:52.153089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfa90d942f941688623ea763fd9488fad117b71e405aad1897f5bfdc7582da69","sha256:9fc83cb70842871083501dd31b74cbe13cc2e95644da61eee1a01cf80bdaaaa5"],"state_sha256":"2d3293e20d284fb376c0405424d1237c2ab6da107daca7815fa02839dd119bc9"}