{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CTCTZR272KPYZQIDXR4SA7FHXL","short_pith_number":"pith:CTCTZR27","schema_version":"1.0","canonical_sha256":"14c53cc75fd29f8cc103bc79207ca7bae94ac3616064e5622896a1e0df437e16","source":{"kind":"arxiv","id":"2604.19971","version":2},"attestation_state":"computed","paper":{"title":"Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Semantic Prompting lets LLMs interpret spatial layout changes to make targeted narrative revisions instead of full regenerations.","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Chris North, Eric Krokos, Ibrahim Tahmid, Kirsten Whitley, Xuan Wang, Xuxin Tang","submitted_at":"2026-04-21T20:28:42Z","abstract_excerpt":"Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can automate narrative generation from spatial layouts, current collage-based and re-generation methods struggle to support the incremental spatial refinements inherent to the sensemaking process. We identify three critical gaps in existing spatial-textual generation: interaction-revision misalignment, human-LLM intent misalignment, and lack of granular customization. To address these, we introduce Semantic Prompting, a framework for spatial refinement t"},"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":"2604.19971","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-04-21T20:28:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ceb430056b726cd5f07835f79f76e15961b2dda24222df7eb5329256e34181da","abstract_canon_sha256":"ca4c21d3d46c9dae1f13828422266a5811d3fac5ea0706ad45604f6fcc5033f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:38.551571Z","signature_b64":"+rksL8ovoi9kGLj9hCyrjaE3xviSzGQUCxzKv+E5VMlzUbCEPNJ92y53tzYovR6jbgboLGeBEvVLhFPp6P5ZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14c53cc75fd29f8cc103bc79207ca7bae94ac3616064e5622896a1e0df437e16","last_reissued_at":"2026-06-30T01:17:38.550983Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:38.550983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Semantic Prompting lets LLMs interpret spatial layout changes to make targeted narrative revisions instead of full regenerations.","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Chris North, Eric Krokos, Ibrahim Tahmid, Kirsten Whitley, Xuan Wang, Xuxin Tang","submitted_at":"2026-04-21T20:28:42Z","abstract_excerpt":"Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can automate narrative generation from spatial layouts, current collage-based and re-generation methods struggle to support the incremental spatial refinements inherent to the sensemaking process. We identify three critical gaps in existing spatial-textual generation: interaction-revision misalignment, human-LLM intent misalignment, and lack of granular customization. To address these, we introduce Semantic Prompting, a framework for spatial refinement t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The empirical evaluation demonstrated that S-PRISM effectively enhanced the precision of interaction-revision refinement. A user study (N=14) highlighted how participants leveraged S-PRISM for incremental formalization through interactive steering.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLMs can accurately perceive semantic interactions from spatial layouts and reason about refinement intent without persistent human-LLM misalignment, as assumed in the framework design.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Semantic Prompting enables LLMs to perform precise incremental narrative revisions by perceiving semantic interactions in spatial layouts, addressing misalignment gaps in existing methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Semantic Prompting lets LLMs interpret spatial layout changes to make targeted narrative revisions instead of full regenerations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5beb05b4297fd0433e914e23cf974c05800cd1d29907ee591d3e64ba5a1b2e9d"},"source":{"id":"2604.19971","kind":"arxiv","version":2},"verdict":{"id":"baca82a1-7d05-4d81-9805-542231646bf6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T01:16:43.451059Z","strongest_claim":"The empirical evaluation demonstrated that S-PRISM effectively enhanced the precision of interaction-revision refinement. A user study (N=14) highlighted how participants leveraged S-PRISM for incremental formalization through interactive steering.","one_line_summary":"Semantic Prompting enables LLMs to perform precise incremental narrative revisions by perceiving semantic interactions in spatial layouts, addressing misalignment gaps in existing methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLMs can accurately perceive semantic interactions from spatial layouts and reason about refinement intent without persistent human-LLM misalignment, as assumed in the framework design.","pith_extraction_headline":"Semantic Prompting lets LLMs interpret spatial layout changes to make targeted narrative revisions instead of full regenerations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.19971/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T15:39:46.206286Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T02:29:52.385944Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"06055c0717c1156dfb2ae7c31de476b6a32b64051fd4d33d614339fe3a8fd05c"},"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":"2604.19971","created_at":"2026-06-30T01:17:38.551071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.19971v2","created_at":"2026-06-30T01:17:38.551071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.19971","created_at":"2026-06-30T01:17:38.551071+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTCTZR272KPY","created_at":"2026-06-30T01:17:38.551071+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTCTZR272KPYZQID","created_at":"2026-06-30T01:17:38.551071+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTCTZR27","created_at":"2026-06-30T01:17:38.551071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.28517","citing_title":"Drag, Infer, Reproject: Grounding LLMs through Spatial Interaction for Image Clustering","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28517","citing_title":"Drag, Infer, Reproject: Grounding LLMs through Spatial Interaction for Image Clustering","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTCTZR272KPYZQIDXR4SA7FHXL","json":"https://pith.science/pith/CTCTZR272KPYZQIDXR4SA7FHXL.json","graph_json":"https://pith.science/api/pith-number/CTCTZR272KPYZQIDXR4SA7FHXL/graph.json","events_json":"https://pith.science/api/pith-number/CTCTZR272KPYZQIDXR4SA7FHXL/events.json","paper":"https://pith.science/paper/CTCTZR27"},"agent_actions":{"view_html":"https://pith.science/pith/CTCTZR272KPYZQIDXR4SA7FHXL","download_json":"https://pith.science/pith/CTCTZR272KPYZQIDXR4SA7FHXL.json","view_paper":"https://pith.science/paper/CTCTZR27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.19971&json=true","fetch_graph":"https://pith.science/api/pith-number/CTCTZR272KPYZQIDXR4SA7FHXL/graph.json","fetch_events":"https://pith.science/api/pith-number/CTCTZR272KPYZQIDXR4SA7FHXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTCTZR272KPYZQIDXR4SA7FHXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTCTZR272KPYZQIDXR4SA7FHXL/action/storage_attestation","attest_author":"https://pith.science/pith/CTCTZR272KPYZQIDXR4SA7FHXL/action/author_attestation","sign_citation":"https://pith.science/pith/CTCTZR272KPYZQIDXR4SA7FHXL/action/citation_signature","submit_replication":"https://pith.science/pith/CTCTZR272KPYZQIDXR4SA7FHXL/action/replication_record"}},"created_at":"2026-06-30T01:17:38.551071+00:00","updated_at":"2026-06-30T01:17:38.551071+00:00"}