{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L7T35TI32LE7LZ2B3A64FCJAOO","short_pith_number":"pith:L7T35TI3","schema_version":"1.0","canonical_sha256":"5fe7becd1bd2c9f5e741d83dc2892073b5239ac978b950079e8ae5caebc4c22e","source":{"kind":"arxiv","id":"2506.04063","version":1},"attestation_state":"computed","paper":{"title":"Crowd-SFT: Crowdsourcing for LLM Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.HC","authors_text":"Alex Sotiropoulos, Bhaskar Krishnamachari, Jared Coleman, Linus Lei, Sulyab Thottungal Valapu","submitted_at":"2025-06-04T15:26:38Z","abstract_excerpt":"Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with a separate reward model, SFT uses human-curated datasets for supervised learning. Both approaches traditionally depend on small, vetted groups of annotators, making them costly, prone to bias, and limited in scalability. We propose an open, crowd-sourced fine-tuning framework that addresses these limitations by enabling broader feedback collection for SFT wi"},"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":"2506.04063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-06-04T15:26:38Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"1a96e36c8176419bc71ea10dbe47d84d85ea04d529b3a87e285136afbf92b5bb","abstract_canon_sha256":"4650e7a0bdbc397ce3d9e9bb1f00e36f06d2cf2fd9813c94bafb74db53adb88c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:56.420137Z","signature_b64":"B8RDB9b8m4zm6apuWlIkWPZY770fmSnihdLOR4JtbCl3/XE1VyWWgGekUkY0+dSyocAl/A8R5KNBExMLYB3ZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe7becd1bd2c9f5e741d83dc2892073b5239ac978b950079e8ae5caebc4c22e","last_reissued_at":"2026-07-05T11:15:56.419678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:56.419678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crowd-SFT: Crowdsourcing for LLM Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.HC","authors_text":"Alex Sotiropoulos, Bhaskar Krishnamachari, Jared Coleman, Linus Lei, Sulyab Thottungal Valapu","submitted_at":"2025-06-04T15:26:38Z","abstract_excerpt":"Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with a separate reward model, SFT uses human-curated datasets for supervised learning. Both approaches traditionally depend on small, vetted groups of annotators, making them costly, prone to bias, and limited in scalability. We propose an open, crowd-sourced fine-tuning framework that addresses these limitations by enabling broader feedback collection for SFT wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04063","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/2506.04063/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":"2506.04063","created_at":"2026-07-05T11:15:56.419734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04063v1","created_at":"2026-07-05T11:15:56.419734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04063","created_at":"2026-07-05T11:15:56.419734+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7T35TI32LE7","created_at":"2026-07-05T11:15:56.419734+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7T35TI32LE7LZ2B","created_at":"2026-07-05T11:15:56.419734+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7T35TI3","created_at":"2026-07-05T11:15:56.419734+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/L7T35TI32LE7LZ2B3A64FCJAOO","json":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO.json","graph_json":"https://pith.science/api/pith-number/L7T35TI32LE7LZ2B3A64FCJAOO/graph.json","events_json":"https://pith.science/api/pith-number/L7T35TI32LE7LZ2B3A64FCJAOO/events.json","paper":"https://pith.science/paper/L7T35TI3"},"agent_actions":{"view_html":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO","download_json":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO.json","view_paper":"https://pith.science/paper/L7T35TI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04063&json=true","fetch_graph":"https://pith.science/api/pith-number/L7T35TI32LE7LZ2B3A64FCJAOO/graph.json","fetch_events":"https://pith.science/api/pith-number/L7T35TI32LE7LZ2B3A64FCJAOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO/action/storage_attestation","attest_author":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO/action/author_attestation","sign_citation":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO/action/citation_signature","submit_replication":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO/action/replication_record"}},"created_at":"2026-07-05T11:15:56.419734+00:00","updated_at":"2026-07-05T11:15:56.419734+00:00"}