{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5MIK3NQE6JBMHSWRBJIIK5IGBU","short_pith_number":"pith:5MIK3NQE","schema_version":"1.0","canonical_sha256":"eb10adb604f242c3cad10a508575060d0daac4de8181fbb0d5a2daead38144e4","source":{"kind":"arxiv","id":"2405.01121","version":3},"attestation_state":"computed","paper":{"title":"Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Filippo Galgani, Ido Dagan, Lotem Golany, Maya Mamo, Nadav Bar, Nimrod Parasol, Omer Vandsburger","submitted_at":"2024-05-02T09:35:06Z","abstract_excerpt":"Automating data generation with Large Language Models (LLMs) has become increasingly popular. In this work, we investigate the feasibility and effectiveness of LLM-based data generation in the challenging setting of source-grounded information-seeking dialogs, with response attribution, over long documents. Our source texts consist of long and noisy meeting transcripts, adding to the task complexity. Since automating attribution remains difficult, we propose a semi-automatic approach: dialog queries and responses are generated with LLMs, followed by human verification and identification of att"},"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":"2405.01121","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T09:35:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cbd0b4c42a1654697f2f74834fac02222b2c4475a33ac90e378ee64b5b3fbba0","abstract_canon_sha256":"5e5455375c8cae700d949c1290291978be055c6f4b7e0d336336437fa2b8b8ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:42.884493Z","signature_b64":"Xo3oN/yZfdL95WJmixa/nnvgUkUu9HIgElTNbtcaMmfyica5miRyw+w+nVB+6+qN/EQDKRKypxMCroTsBesRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb10adb604f242c3cad10a508575060d0daac4de8181fbb0d5a2daead38144e4","last_reissued_at":"2026-07-05T09:20:42.883999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:42.883999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Filippo Galgani, Ido Dagan, Lotem Golany, Maya Mamo, Nadav Bar, Nimrod Parasol, Omer Vandsburger","submitted_at":"2024-05-02T09:35:06Z","abstract_excerpt":"Automating data generation with Large Language Models (LLMs) has become increasingly popular. In this work, we investigate the feasibility and effectiveness of LLM-based data generation in the challenging setting of source-grounded information-seeking dialogs, with response attribution, over long documents. Our source texts consist of long and noisy meeting transcripts, adding to the task complexity. Since automating attribution remains difficult, we propose a semi-automatic approach: dialog queries and responses are generated with LLMs, followed by human verification and identification of att"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01121","kind":"arxiv","version":3},"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/2405.01121/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":"2405.01121","created_at":"2026-07-05T09:20:42.884057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.01121v3","created_at":"2026-07-05T09:20:42.884057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01121","created_at":"2026-07-05T09:20:42.884057+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MIK3NQE6JBM","created_at":"2026-07-05T09:20:42.884057+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MIK3NQE6JBMHSWR","created_at":"2026-07-05T09:20:42.884057+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MIK3NQE","created_at":"2026-07-05T09:20:42.884057+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/5MIK3NQE6JBMHSWRBJIIK5IGBU","json":"https://pith.science/pith/5MIK3NQE6JBMHSWRBJIIK5IGBU.json","graph_json":"https://pith.science/api/pith-number/5MIK3NQE6JBMHSWRBJIIK5IGBU/graph.json","events_json":"https://pith.science/api/pith-number/5MIK3NQE6JBMHSWRBJIIK5IGBU/events.json","paper":"https://pith.science/paper/5MIK3NQE"},"agent_actions":{"view_html":"https://pith.science/pith/5MIK3NQE6JBMHSWRBJIIK5IGBU","download_json":"https://pith.science/pith/5MIK3NQE6JBMHSWRBJIIK5IGBU.json","view_paper":"https://pith.science/paper/5MIK3NQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.01121&json=true","fetch_graph":"https://pith.science/api/pith-number/5MIK3NQE6JBMHSWRBJIIK5IGBU/graph.json","fetch_events":"https://pith.science/api/pith-number/5MIK3NQE6JBMHSWRBJIIK5IGBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MIK3NQE6JBMHSWRBJIIK5IGBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MIK3NQE6JBMHSWRBJIIK5IGBU/action/storage_attestation","attest_author":"https://pith.science/pith/5MIK3NQE6JBMHSWRBJIIK5IGBU/action/author_attestation","sign_citation":"https://pith.science/pith/5MIK3NQE6JBMHSWRBJIIK5IGBU/action/citation_signature","submit_replication":"https://pith.science/pith/5MIK3NQE6JBMHSWRBJIIK5IGBU/action/replication_record"}},"created_at":"2026-07-05T09:20:42.884057+00:00","updated_at":"2026-07-05T09:20:42.884057+00:00"}