{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2KPPFJ6FWGK27XF5HSNJHT5NKC","short_pith_number":"pith:2KPPFJ6F","schema_version":"1.0","canonical_sha256":"d29ef2a7c5b195afdcbd3c9a93cfad50ba1507f9d569ace44cf5bbfcbe36fa23","source":{"kind":"arxiv","id":"2607.08497","version":1},"attestation_state":"computed","paper":{"title":"Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Canmiao Fu, Chen Li, Feng Wang, Ge Li, Jing Lyu, Zhipeng Huang","submitted_at":"2026-07-09T13:55:55Z","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"},"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":"2607.08497","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T13:55:55Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"1386968f2873048a2ff042ea01fbb2ea466bfbd9acfaa918dc1a403ee9efd397","abstract_canon_sha256":"24798c9c81575561982875f81bb5d5f6a77bf9073f3a1b90fb8b59e26fa7ca30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:52.153089Z","signature_b64":"tTo44m4JJ3cg2JGS0DAQ6w5V168ZpvxwLSehHT8o7ZOHSYN1+5iGUZ9GXV/WMLktmRXiZo9UsMbfddlSR9G+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d29ef2a7c5b195afdcbd3c9a93cfad50ba1507f9d569ace44cf5bbfcbe36fa23","last_reissued_at":"2026-07-10T01:19:52.152701Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:52.152701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Canmiao Fu, Chen Li, Feng Wang, Ge Li, Jing Lyu, Zhipeng Huang","submitted_at":"2026-07-09T13:55:55Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08497","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/2607.08497/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":"2607.08497","created_at":"2026-07-10T01:19:52.152758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08497v1","created_at":"2026-07-10T01:19:52.152758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08497","created_at":"2026-07-10T01:19:52.152758+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KPPFJ6FWGK2","created_at":"2026-07-10T01:19:52.152758+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KPPFJ6FWGK27XF5","created_at":"2026-07-10T01:19:52.152758+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KPPFJ6F","created_at":"2026-07-10T01:19:52.152758+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/2KPPFJ6FWGK27XF5HSNJHT5NKC","json":"https://pith.science/pith/2KPPFJ6FWGK27XF5HSNJHT5NKC.json","graph_json":"https://pith.science/api/pith-number/2KPPFJ6FWGK27XF5HSNJHT5NKC/graph.json","events_json":"https://pith.science/api/pith-number/2KPPFJ6FWGK27XF5HSNJHT5NKC/events.json","paper":"https://pith.science/paper/2KPPFJ6F"},"agent_actions":{"view_html":"https://pith.science/pith/2KPPFJ6FWGK27XF5HSNJHT5NKC","download_json":"https://pith.science/pith/2KPPFJ6FWGK27XF5HSNJHT5NKC.json","view_paper":"https://pith.science/paper/2KPPFJ6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08497&json=true","fetch_graph":"https://pith.science/api/pith-number/2KPPFJ6FWGK27XF5HSNJHT5NKC/graph.json","fetch_events":"https://pith.science/api/pith-number/2KPPFJ6FWGK27XF5HSNJHT5NKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KPPFJ6FWGK27XF5HSNJHT5NKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KPPFJ6FWGK27XF5HSNJHT5NKC/action/storage_attestation","attest_author":"https://pith.science/pith/2KPPFJ6FWGK27XF5HSNJHT5NKC/action/author_attestation","sign_citation":"https://pith.science/pith/2KPPFJ6FWGK27XF5HSNJHT5NKC/action/citation_signature","submit_replication":"https://pith.science/pith/2KPPFJ6FWGK27XF5HSNJHT5NKC/action/replication_record"}},"created_at":"2026-07-10T01:19:52.152758+00:00","updated_at":"2026-07-10T01:19:52.152758+00:00"}