{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QA37IJOR6V3EIBHTJQXK3YJFIU","short_pith_number":"pith:QA37IJOR","schema_version":"1.0","canonical_sha256":"8037f425d1f5764404f34c2eade125452b860b2720e2fde1a55d694540f2a0a3","source":{"kind":"arxiv","id":"2508.13948","version":1},"attestation_state":"computed","paper":{"title":"Prompt Orchestration Markup Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.PL"],"primary_cat":"cs.HC","authors_text":"Jiahang Xu, Nan Chen, Yuge Zhang, Yuqing Yang","submitted_at":"2025-08-19T15:37:29Z","abstract_excerpt":"Large Language Models (LLMs) require sophisticated prompting, yet current practices face challenges in structure, data integration, format sensitivity, and tooling. Existing methods lack comprehensive solutions for organizing complex prompts involving diverse data types (documents, tables, images) or managing presentation variations systematically. To address these gaps, we introduce POML (Prompt Orchestration Markup Language). POML employs component-based markup for logical structure (roles, tasks, examples), specialized tags for seamless data integration, and a CSS-like styling system to dec"},"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":"2508.13948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-08-19T15:37:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.PL"],"title_canon_sha256":"0e5b3bf119e975a617cbf8f06a043a1a461057f529119e6e3ecd7d869df9c669","abstract_canon_sha256":"39f12ebb39595ea15bd5112028169dc9229bd582cb16c41c6d8ff47fdc9ae3ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:09.941908Z","signature_b64":"r5nK3KR2eG0mPps0lhib7OnQ0ephyRlw8EA8KDbPm04UJPtWm8rkawB1ZIkIViZJ7YrDLimfWCHhH+ALYEDVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8037f425d1f5764404f34c2eade125452b860b2720e2fde1a55d694540f2a0a3","last_reissued_at":"2026-07-05T11:56:09.941444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:09.941444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Orchestration Markup Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.PL"],"primary_cat":"cs.HC","authors_text":"Jiahang Xu, Nan Chen, Yuge Zhang, Yuqing Yang","submitted_at":"2025-08-19T15:37:29Z","abstract_excerpt":"Large Language Models (LLMs) require sophisticated prompting, yet current practices face challenges in structure, data integration, format sensitivity, and tooling. Existing methods lack comprehensive solutions for organizing complex prompts involving diverse data types (documents, tables, images) or managing presentation variations systematically. To address these gaps, we introduce POML (Prompt Orchestration Markup Language). POML employs component-based markup for logical structure (roles, tasks, examples), specialized tags for seamless data integration, and a CSS-like styling system to dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13948","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/2508.13948/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":"2508.13948","created_at":"2026-07-05T11:56:09.941508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13948v1","created_at":"2026-07-05T11:56:09.941508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13948","created_at":"2026-07-05T11:56:09.941508+00:00"},{"alias_kind":"pith_short_12","alias_value":"QA37IJOR6V3E","created_at":"2026-07-05T11:56:09.941508+00:00"},{"alias_kind":"pith_short_16","alias_value":"QA37IJOR6V3EIBHT","created_at":"2026-07-05T11:56:09.941508+00:00"},{"alias_kind":"pith_short_8","alias_value":"QA37IJOR","created_at":"2026-07-05T11:56:09.941508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09283","citing_title":"A Prompt-Aware Structuring Framework for Reliable Reuse of AI-Generated Content in the Agentic Web","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01920","citing_title":"A Language for Describing Agentic LLM Contexts","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QA37IJOR6V3EIBHTJQXK3YJFIU","json":"https://pith.science/pith/QA37IJOR6V3EIBHTJQXK3YJFIU.json","graph_json":"https://pith.science/api/pith-number/QA37IJOR6V3EIBHTJQXK3YJFIU/graph.json","events_json":"https://pith.science/api/pith-number/QA37IJOR6V3EIBHTJQXK3YJFIU/events.json","paper":"https://pith.science/paper/QA37IJOR"},"agent_actions":{"view_html":"https://pith.science/pith/QA37IJOR6V3EIBHTJQXK3YJFIU","download_json":"https://pith.science/pith/QA37IJOR6V3EIBHTJQXK3YJFIU.json","view_paper":"https://pith.science/paper/QA37IJOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13948&json=true","fetch_graph":"https://pith.science/api/pith-number/QA37IJOR6V3EIBHTJQXK3YJFIU/graph.json","fetch_events":"https://pith.science/api/pith-number/QA37IJOR6V3EIBHTJQXK3YJFIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QA37IJOR6V3EIBHTJQXK3YJFIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QA37IJOR6V3EIBHTJQXK3YJFIU/action/storage_attestation","attest_author":"https://pith.science/pith/QA37IJOR6V3EIBHTJQXK3YJFIU/action/author_attestation","sign_citation":"https://pith.science/pith/QA37IJOR6V3EIBHTJQXK3YJFIU/action/citation_signature","submit_replication":"https://pith.science/pith/QA37IJOR6V3EIBHTJQXK3YJFIU/action/replication_record"}},"created_at":"2026-07-05T11:56:09.941508+00:00","updated_at":"2026-07-05T11:56:09.941508+00:00"}