{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EGM6MDHF5POZV2DA2RUJQPOIAD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bd33fe10061cded6400f53a8132ba3146ce933b778433ec82315e07f9d0dc33c","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-16T18:56:14Z","title_canon_sha256":"befa041a6388ee2c1a5205bed3a00ecf7652846ce915537cc53216188d94ae96"},"schema_version":"1.0","source":{"id":"2504.12427","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12427","created_at":"2026-07-05T10:50:16Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12427v1","created_at":"2026-07-05T10:50:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12427","created_at":"2026-07-05T10:50:16Z"},{"alias_kind":"pith_short_12","alias_value":"EGM6MDHF5POZ","created_at":"2026-07-05T10:50:16Z"},{"alias_kind":"pith_short_16","alias_value":"EGM6MDHF5POZV2DA","created_at":"2026-07-05T10:50:16Z"},{"alias_kind":"pith_short_8","alias_value":"EGM6MDHF","created_at":"2026-07-05T10:50:16Z"}],"graph_snapshots":[{"event_id":"sha256:9d862d5cdd1c70c2c01aab4650b768ffb6b9daaf9aac6b6e2d84c0d323f24064","target":"graph","created_at":"2026-07-05T10:50:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.12427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a state-of-the-art Large Language Model (LLM) is an increasingly expensive endeavor due to growing computational, hardware, energy, and engineering demands. Yet, an often-overlooked (and seldom paid) expense is the human labor behind these models' training data. Every LLM is built on an unfathomable amount of human effort: trillions of carefully written words sourced from books, academic papers, codebases, social media, and more. This position paper aims to assign a monetary value to this labor and argues that the most expensive part of producing an LLM should be the compensation prov","authors_text":"Colin Raffel, Nikhil Kandpal","cross_cats":["cs.AI","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-16T18:56:14Z","title":"Position: The Most Expensive Part of an LLM should be its Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12427","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f0ed60719c0bae5c1d1b4094e0f2c8a911ab444059694b905f3645b2dcfd0a6a","target":"record","created_at":"2026-07-05T10:50:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bd33fe10061cded6400f53a8132ba3146ce933b778433ec82315e07f9d0dc33c","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-16T18:56:14Z","title_canon_sha256":"befa041a6388ee2c1a5205bed3a00ecf7652846ce915537cc53216188d94ae96"},"schema_version":"1.0","source":{"id":"2504.12427","kind":"arxiv","version":1}},"canonical_sha256":"2199e60ce5ebdd9ae860d468983dc800f361fc722be6e6346ce2ecb8e4f9afdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2199e60ce5ebdd9ae860d468983dc800f361fc722be6e6346ce2ecb8e4f9afdf","first_computed_at":"2026-07-05T10:50:16.289055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:16.289055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xE7Xn6Z5p18CJcI8M4d0rXJ7AW+SMImkwP59SZYa/pQkfz6/3DQ+FveNPN6mxmIZJWK1+SOWK+3c87zRLHXEDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:16.289507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12427","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0ed60719c0bae5c1d1b4094e0f2c8a911ab444059694b905f3645b2dcfd0a6a","sha256:9d862d5cdd1c70c2c01aab4650b768ffb6b9daaf9aac6b6e2d84c0d323f24064"],"state_sha256":"5e47055730d9243ef219ea704a2b432382ca54e98f385c459f3462e6293ce527"}