{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KG6XVULEXADTEYWDTJNWRQYWXU","short_pith_number":"pith:KG6XVULE","schema_version":"1.0","canonical_sha256":"51bd7ad164b8073262c39a5b68c316bd213b6d6967a68911e013fa3e23599839","source":{"kind":"arxiv","id":"2506.05379","version":1},"attestation_state":"computed","paper":{"title":"Designing DSIC Mechanisms for Data Sharing in the Era of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.GT","authors_text":"Kourosh Shahnazari, MohammadAmin Fazli, Mohammmadali Keshtparvar, Seyed Moein Ayyoubzadeh","submitted_at":"2025-06-01T22:17:18Z","abstract_excerpt":"Training large language models (LLMs) requires vast amounts of high-quality data from institutions that face legal, privacy, and strategic constraints. Existing data procurement methods often rely on unverifiable trust or ignore heterogeneous provider costs. We introduce a mechanism-design framework for truthful, trust-minimized data sharing that ensures dominant-strategy incentive compatibility (DSIC), individual rationality, and weak budget balance, while rewarding data based on both quality and learning utility. We formalize a model where providers privately know their data cost and quality"},"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":"2506.05379","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2025-06-01T22:17:18Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"a955acf767ce5134d245b72ae1aaa3f5d660cb1fe6bf87e41ffbbef6eb347eb5","abstract_canon_sha256":"1175c59feebc544cfa56112cec2d2be1428d78481e5e1c64564a19956aebe184"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:01.586850Z","signature_b64":"feAm5+941gBTK5fI6xCotVr6bxwk4lHRudkI0/iJ4eFqVOJmhqCrjRO9V3JtkGMidzhBu4DAB13F2JXykPZFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51bd7ad164b8073262c39a5b68c316bd213b6d6967a68911e013fa3e23599839","last_reissued_at":"2026-07-05T11:17:01.586369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:01.586369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Designing DSIC Mechanisms for Data Sharing in the Era of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.GT","authors_text":"Kourosh Shahnazari, MohammadAmin Fazli, Mohammmadali Keshtparvar, Seyed Moein Ayyoubzadeh","submitted_at":"2025-06-01T22:17:18Z","abstract_excerpt":"Training large language models (LLMs) requires vast amounts of high-quality data from institutions that face legal, privacy, and strategic constraints. Existing data procurement methods often rely on unverifiable trust or ignore heterogeneous provider costs. We introduce a mechanism-design framework for truthful, trust-minimized data sharing that ensures dominant-strategy incentive compatibility (DSIC), individual rationality, and weak budget balance, while rewarding data based on both quality and learning utility. We formalize a model where providers privately know their data cost and quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05379","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/2506.05379/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":"2506.05379","created_at":"2026-07-05T11:17:01.586428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05379v1","created_at":"2026-07-05T11:17:01.586428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05379","created_at":"2026-07-05T11:17:01.586428+00:00"},{"alias_kind":"pith_short_12","alias_value":"KG6XVULEXADT","created_at":"2026-07-05T11:17:01.586428+00:00"},{"alias_kind":"pith_short_16","alias_value":"KG6XVULEXADTEYWD","created_at":"2026-07-05T11:17:01.586428+00:00"},{"alias_kind":"pith_short_8","alias_value":"KG6XVULE","created_at":"2026-07-05T11:17:01.586428+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/KG6XVULEXADTEYWDTJNWRQYWXU","json":"https://pith.science/pith/KG6XVULEXADTEYWDTJNWRQYWXU.json","graph_json":"https://pith.science/api/pith-number/KG6XVULEXADTEYWDTJNWRQYWXU/graph.json","events_json":"https://pith.science/api/pith-number/KG6XVULEXADTEYWDTJNWRQYWXU/events.json","paper":"https://pith.science/paper/KG6XVULE"},"agent_actions":{"view_html":"https://pith.science/pith/KG6XVULEXADTEYWDTJNWRQYWXU","download_json":"https://pith.science/pith/KG6XVULEXADTEYWDTJNWRQYWXU.json","view_paper":"https://pith.science/paper/KG6XVULE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05379&json=true","fetch_graph":"https://pith.science/api/pith-number/KG6XVULEXADTEYWDTJNWRQYWXU/graph.json","fetch_events":"https://pith.science/api/pith-number/KG6XVULEXADTEYWDTJNWRQYWXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KG6XVULEXADTEYWDTJNWRQYWXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KG6XVULEXADTEYWDTJNWRQYWXU/action/storage_attestation","attest_author":"https://pith.science/pith/KG6XVULEXADTEYWDTJNWRQYWXU/action/author_attestation","sign_citation":"https://pith.science/pith/KG6XVULEXADTEYWDTJNWRQYWXU/action/citation_signature","submit_replication":"https://pith.science/pith/KG6XVULEXADTEYWDTJNWRQYWXU/action/replication_record"}},"created_at":"2026-07-05T11:17:01.586428+00:00","updated_at":"2026-07-05T11:17:01.586428+00:00"}