{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PWZ2TBK3PQ773BSTD4KEJDACTD","short_pith_number":"pith:PWZ2TBK3","schema_version":"1.0","canonical_sha256":"7db3a9855b7c3ffd86531f14448c0298eceae9550f7477532172eaeff71db2b3","source":{"kind":"arxiv","id":"2502.00198","version":4},"attestation_state":"computed","paper":{"title":"Fairshare Data Pricing via Data Valuation for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.GT","authors_text":"Beibei Li, Cathy Jiao, Chenyan Xiong, Luyang Zhang","submitted_at":"2025-01-31T22:27:34Z","abstract_excerpt":"Training data is the backbone of large language models (LLMs), yet today's data markets often operate under exploitative pricing -- sourcing data from marginalized groups with little pay or recognition. This paper introduces a theoretical framework for LLM data markets, modeling the strategic interactions between buyers (LLM builders) and sellers (human annotators). We begin with theoretical and empirical analysis showing how exploitative pricing drives high-quality sellers out of the market, degrading data quality and long-term model performance. Then we introduce fairshare, a pricing mechani"},"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":"2502.00198","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2025-01-31T22:27:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"50a215ea6bd66da5654cbf1fd2e1d1bcebb3567f8da332aec692674c1a5ef693","abstract_canon_sha256":"6d2f3b6e84d9bc087b6cf25c4b375cc45fd9afbb19c0db45439358f61678c304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:57:29.349160Z","signature_b64":"3MX4vb+lyFDXGEzDZjxkdVLVWcjOesjiC241VJwfyAkutyjWTERSE8yam8za2EcOKk5Jb25zFvL/YyGnKH6vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7db3a9855b7c3ffd86531f14448c0298eceae9550f7477532172eaeff71db2b3","last_reissued_at":"2026-08-04T01:57:29.347592Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:57:29.347592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairshare Data Pricing via Data Valuation for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.GT","authors_text":"Beibei Li, Cathy Jiao, Chenyan Xiong, Luyang Zhang","submitted_at":"2025-01-31T22:27:34Z","abstract_excerpt":"Training data is the backbone of large language models (LLMs), yet today's data markets often operate under exploitative pricing -- sourcing data from marginalized groups with little pay or recognition. This paper introduces a theoretical framework for LLM data markets, modeling the strategic interactions between buyers (LLM builders) and sellers (human annotators). We begin with theoretical and empirical analysis showing how exploitative pricing drives high-quality sellers out of the market, degrading data quality and long-term model performance. Then we introduce fairshare, a pricing mechani"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00198","kind":"arxiv","version":4},"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/2502.00198/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":"2502.00198","created_at":"2026-08-04T01:57:29.348836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00198v4","created_at":"2026-08-04T01:57:29.348836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00198","created_at":"2026-08-04T01:57:29.348836+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWZ2TBK3PQ77","created_at":"2026-08-04T01:57:29.348836+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWZ2TBK3PQ773BST","created_at":"2026-08-04T01:57:29.348836+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWZ2TBK3","created_at":"2026-08-04T01:57:29.348836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.15520","citing_title":"On the Fragility of Data Attribution When Learning Is Distributed","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2602.10995","citing_title":"A Human-Centric Framework for Data Attribution in Large Language Models","ref_index":197,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17227","citing_title":"Cloud-native and Distributed Systems for Efficient and Scalable Large Language Models -- A Research Agenda","ref_index":131,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PWZ2TBK3PQ773BSTD4KEJDACTD","json":"https://pith.science/pith/PWZ2TBK3PQ773BSTD4KEJDACTD.json","graph_json":"https://pith.science/api/pith-number/PWZ2TBK3PQ773BSTD4KEJDACTD/graph.json","events_json":"https://pith.science/api/pith-number/PWZ2TBK3PQ773BSTD4KEJDACTD/events.json","paper":"https://pith.science/paper/PWZ2TBK3"},"agent_actions":{"view_html":"https://pith.science/pith/PWZ2TBK3PQ773BSTD4KEJDACTD","download_json":"https://pith.science/pith/PWZ2TBK3PQ773BSTD4KEJDACTD.json","view_paper":"https://pith.science/paper/PWZ2TBK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00198&json=true","fetch_graph":"https://pith.science/api/pith-number/PWZ2TBK3PQ773BSTD4KEJDACTD/graph.json","fetch_events":"https://pith.science/api/pith-number/PWZ2TBK3PQ773BSTD4KEJDACTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWZ2TBK3PQ773BSTD4KEJDACTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWZ2TBK3PQ773BSTD4KEJDACTD/action/storage_attestation","attest_author":"https://pith.science/pith/PWZ2TBK3PQ773BSTD4KEJDACTD/action/author_attestation","sign_citation":"https://pith.science/pith/PWZ2TBK3PQ773BSTD4KEJDACTD/action/citation_signature","submit_replication":"https://pith.science/pith/PWZ2TBK3PQ773BSTD4KEJDACTD/action/replication_record"}},"created_at":"2026-08-04T01:57:29.348836+00:00","updated_at":"2026-08-04T01:57:29.348836+00:00"}