{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GHQD74VNNIJTIV6X33B2BIROKV","short_pith_number":"pith:GHQD74VN","schema_version":"1.0","canonical_sha256":"31e03ff2ad6a133457d7dec3a0a22e554b6cfcb92fc2817ca733b31ce23b791a","source":{"kind":"arxiv","id":"2607.05290","version":1},"attestation_state":"computed","paper":{"title":"ChatImage: Navigating Long-Form LLM Answers through Interactive Images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Wencan Jiang, Yong Liu","submitted_at":"2026-07-06T16:30:41Z","abstract_excerpt":"Large Language Models (LLMs) can produce detailed answers to complex queries, but these answers are typically presented as dense linear text, which makes fine-grained inspection, navigation, and return visits difficult. We present ChatImage, a system that converts long-form LLM answers into interactive visual images. Given a textual answer, ChatImage first normalizes its content into structured visual modules, plans a visual layout, and renders a coherent image. It then applies a second grounding pass to the rendered image with vision grounding models such as LocateAnything and MiMo-Vision, wi"},"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":"2607.05290","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T16:30:41Z","cross_cats_sorted":[],"title_canon_sha256":"3f1d627812d396d55c4a68b2aed572977bc9ca8b62e0be8acf400994df6c2670","abstract_canon_sha256":"55b247bd4bc197f7d62c69b3fe6960505059c056d3ef4d0d1999557d0e49c613"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:22.362723Z","signature_b64":"/KvS+p/fDkYHh/CN3TdcPE8e8+Nvodh8vtxpRcadP000+sYj+iEDcnxQejuHt9tuDlKewSd+uBPeLWiBdzHeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31e03ff2ad6a133457d7dec3a0a22e554b6cfcb92fc2817ca733b31ce23b791a","last_reissued_at":"2026-07-07T03:19:22.362122Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:22.362122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatImage: Navigating Long-Form LLM Answers through Interactive Images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Wencan Jiang, Yong Liu","submitted_at":"2026-07-06T16:30:41Z","abstract_excerpt":"Large Language Models (LLMs) can produce detailed answers to complex queries, but these answers are typically presented as dense linear text, which makes fine-grained inspection, navigation, and return visits difficult. We present ChatImage, a system that converts long-form LLM answers into interactive visual images. Given a textual answer, ChatImage first normalizes its content into structured visual modules, plans a visual layout, and renders a coherent image. It then applies a second grounding pass to the rendered image with vision grounding models such as LocateAnything and MiMo-Vision, wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05290","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/2607.05290/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":"2607.05290","created_at":"2026-07-07T03:19:22.362229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05290v1","created_at":"2026-07-07T03:19:22.362229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05290","created_at":"2026-07-07T03:19:22.362229+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHQD74VNNIJT","created_at":"2026-07-07T03:19:22.362229+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHQD74VNNIJTIV6X","created_at":"2026-07-07T03:19:22.362229+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHQD74VN","created_at":"2026-07-07T03:19:22.362229+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/GHQD74VNNIJTIV6X33B2BIROKV","json":"https://pith.science/pith/GHQD74VNNIJTIV6X33B2BIROKV.json","graph_json":"https://pith.science/api/pith-number/GHQD74VNNIJTIV6X33B2BIROKV/graph.json","events_json":"https://pith.science/api/pith-number/GHQD74VNNIJTIV6X33B2BIROKV/events.json","paper":"https://pith.science/paper/GHQD74VN"},"agent_actions":{"view_html":"https://pith.science/pith/GHQD74VNNIJTIV6X33B2BIROKV","download_json":"https://pith.science/pith/GHQD74VNNIJTIV6X33B2BIROKV.json","view_paper":"https://pith.science/paper/GHQD74VN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05290&json=true","fetch_graph":"https://pith.science/api/pith-number/GHQD74VNNIJTIV6X33B2BIROKV/graph.json","fetch_events":"https://pith.science/api/pith-number/GHQD74VNNIJTIV6X33B2BIROKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHQD74VNNIJTIV6X33B2BIROKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHQD74VNNIJTIV6X33B2BIROKV/action/storage_attestation","attest_author":"https://pith.science/pith/GHQD74VNNIJTIV6X33B2BIROKV/action/author_attestation","sign_citation":"https://pith.science/pith/GHQD74VNNIJTIV6X33B2BIROKV/action/citation_signature","submit_replication":"https://pith.science/pith/GHQD74VNNIJTIV6X33B2BIROKV/action/replication_record"}},"created_at":"2026-07-07T03:19:22.362229+00:00","updated_at":"2026-07-07T03:19:22.362229+00:00"}