{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CE527YHFYB2WIYZBA6FJJRAPNP","short_pith_number":"pith:CE527YHF","schema_version":"1.0","canonical_sha256":"113bafe0e5c075646321078a94c40f6bca77dd4326b6a5b8e7788b4d9dbb3542","source":{"kind":"arxiv","id":"2608.04307","version":1},"attestation_state":"computed","paper":{"title":"MIDAS: Multi-LLM Iterative Data-Adaptive Summarization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Dhanashree Balaram, Karen Lee, Seojun Shon, Umair Rasheed","submitted_at":"2026-08-05T00:33:39Z","abstract_excerpt":"Text summarization is deceptively difficult. While condensing information seems straightforward, real-world enterprise summarization of support tickets, legal documents, incident reports, and more, demands strict adherence to domain-specific guidelines, output formats, and organizational conventions. Crafting prompts that reliably satisfy these constraints is labor-intensive, requiring significant human expertise and continuous maintenance as requirements evolve. Existing automated prompt optimization methods reduce this burden through Large Language Model (LLM) critique-driven refinement, yet"},"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":"2608.04307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T00:33:39Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"ef9bd9042a9e541bc932d8066cc710d556a3c9a4ae02d4a1dc207783519d8e31","abstract_canon_sha256":"7175bb0fc93b5d4016c5d3cc38a04efdfeb22215e5fc74e30ae01cb18ea3c186"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:32:10.727108Z","signature_b64":"FlHjd5yY1Gj4wTwl0BGAC5srE7MBGSizmkgzvkGfcL8ZKHFkrJ2Ir9zwWNZsipEm/tV1ixyIT2OKE0l/jOBqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"113bafe0e5c075646321078a94c40f6bca77dd4326b6a5b8e7788b4d9dbb3542","last_reissued_at":"2026-08-06T01:32:10.725672Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:32:10.725672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIDAS: Multi-LLM Iterative Data-Adaptive Summarization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Dhanashree Balaram, Karen Lee, Seojun Shon, Umair Rasheed","submitted_at":"2026-08-05T00:33:39Z","abstract_excerpt":"Text summarization is deceptively difficult. While condensing information seems straightforward, real-world enterprise summarization of support tickets, legal documents, incident reports, and more, demands strict adherence to domain-specific guidelines, output formats, and organizational conventions. Crafting prompts that reliably satisfy these constraints is labor-intensive, requiring significant human expertise and continuous maintenance as requirements evolve. Existing automated prompt optimization methods reduce this burden through Large Language Model (LLM) critique-driven refinement, yet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04307","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/2608.04307/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":"2608.04307","created_at":"2026-08-06T01:32:10.727445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04307v1","created_at":"2026-08-06T01:32:10.727445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04307","created_at":"2026-08-06T01:32:10.727445+00:00"},{"alias_kind":"pith_short_12","alias_value":"CE527YHFYB2W","created_at":"2026-08-06T01:32:10.727445+00:00"},{"alias_kind":"pith_short_16","alias_value":"CE527YHFYB2WIYZB","created_at":"2026-08-06T01:32:10.727445+00:00"},{"alias_kind":"pith_short_8","alias_value":"CE527YHF","created_at":"2026-08-06T01:32:10.727445+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/CE527YHFYB2WIYZBA6FJJRAPNP","json":"https://pith.science/pith/CE527YHFYB2WIYZBA6FJJRAPNP.json","graph_json":"https://pith.science/api/pith-number/CE527YHFYB2WIYZBA6FJJRAPNP/graph.json","events_json":"https://pith.science/api/pith-number/CE527YHFYB2WIYZBA6FJJRAPNP/events.json","paper":"https://pith.science/paper/CE527YHF"},"agent_actions":{"view_html":"https://pith.science/pith/CE527YHFYB2WIYZBA6FJJRAPNP","download_json":"https://pith.science/pith/CE527YHFYB2WIYZBA6FJJRAPNP.json","view_paper":"https://pith.science/paper/CE527YHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04307&json=true","fetch_graph":"https://pith.science/api/pith-number/CE527YHFYB2WIYZBA6FJJRAPNP/graph.json","fetch_events":"https://pith.science/api/pith-number/CE527YHFYB2WIYZBA6FJJRAPNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CE527YHFYB2WIYZBA6FJJRAPNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CE527YHFYB2WIYZBA6FJJRAPNP/action/storage_attestation","attest_author":"https://pith.science/pith/CE527YHFYB2WIYZBA6FJJRAPNP/action/author_attestation","sign_citation":"https://pith.science/pith/CE527YHFYB2WIYZBA6FJJRAPNP/action/citation_signature","submit_replication":"https://pith.science/pith/CE527YHFYB2WIYZBA6FJJRAPNP/action/replication_record"}},"created_at":"2026-08-06T01:32:10.727445+00:00","updated_at":"2026-08-06T01:32:10.727445+00:00"}