{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:L7T35TI32LE7LZ2B3A64FCJAOO","short_pith_number":"pith:L7T35TI3","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"},"canonical_sha256":"5fe7becd1bd2c9f5e741d83dc2892073b5239ac978b950079e8ae5caebc4c22e","source":{"kind":"arxiv","id":"2506.04063","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04063","created_at":"2026-07-05T11:15:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04063v1","created_at":"2026-07-05T11:15:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04063","created_at":"2026-07-05T11:15:56Z"},{"alias_kind":"pith_short_12","alias_value":"L7T35TI32LE7","created_at":"2026-07-05T11:15:56Z"},{"alias_kind":"pith_short_16","alias_value":"L7T35TI32LE7LZ2B","created_at":"2026-07-05T11:15:56Z"},{"alias_kind":"pith_short_8","alias_value":"L7T35TI3","created_at":"2026-07-05T11:15:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:L7T35TI32LE7LZ2B3A64FCJAOO","target":"record","payload":{"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"},"canonical_sha256":"5fe7becd1bd2c9f5e741d83dc2892073b5239ac978b950079e8ae5caebc4c22e","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"},"source_kind":"arxiv","source_id":"2506.04063","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cIaFoGKGapj3+93IWMcSloz73rM/j+2wUHxccrFKQ5diBPHAR4HD4t141tiPhvo6swIKmtT4LniZmFJgZMbBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:33:00.791864Z"},"content_sha256":"08619c32f48bff382c95ccebbd688510c173e1d01e0905062622446ff8e3c6e8","schema_version":"1.0","event_id":"sha256:08619c32f48bff382c95ccebbd688510c173e1d01e0905062622446ff8e3c6e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:L7T35TI32LE7LZ2B3A64FCJAOO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p9osQcT2BhB6H+95wFbY2FnzJU8lE7biUdd9DnWn/PGkduEMCsT6o6DHzNN+NGx7uK1VnAAh5Kul0V5RWT93Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:33:00.792256Z"},"content_sha256":"c220d7f3da9cb98af61018d919a02740db3831b6206a9d533980a1ff50a2e4e4","schema_version":"1.0","event_id":"sha256:c220d7f3da9cb98af61018d919a02740db3831b6206a9d533980a1ff50a2e4e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO/bundle.json","state_url":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L7T35TI32LE7LZ2B3A64FCJAOO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-12T18:33:00Z","links":{"resolver":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO","bundle":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO/bundle.json","state":"https://pith.science/pith/L7T35TI32LE7LZ2B3A64FCJAOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L7T35TI32LE7LZ2B3A64FCJAOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L7T35TI32LE7LZ2B3A64FCJAOO","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":"4650e7a0bdbc397ce3d9e9bb1f00e36f06d2cf2fd9813c94bafb74db53adb88c","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-06-04T15:26:38Z","title_canon_sha256":"1a96e36c8176419bc71ea10dbe47d84d85ea04d529b3a87e285136afbf92b5bb"},"schema_version":"1.0","source":{"id":"2506.04063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04063","created_at":"2026-07-05T11:15:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04063v1","created_at":"2026-07-05T11:15:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04063","created_at":"2026-07-05T11:15:56Z"},{"alias_kind":"pith_short_12","alias_value":"L7T35TI32LE7","created_at":"2026-07-05T11:15:56Z"},{"alias_kind":"pith_short_16","alias_value":"L7T35TI32LE7LZ2B","created_at":"2026-07-05T11:15:56Z"},{"alias_kind":"pith_short_8","alias_value":"L7T35TI3","created_at":"2026-07-05T11:15:56Z"}],"graph_snapshots":[{"event_id":"sha256:c220d7f3da9cb98af61018d919a02740db3831b6206a9d533980a1ff50a2e4e4","target":"graph","created_at":"2026-07-05T11:15:56Z","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/2506.04063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alex Sotiropoulos, Bhaskar Krishnamachari, Jared Coleman, Linus Lei, Sulyab Thottungal Valapu","cross_cats":["cs.DC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-06-04T15:26:38Z","title":"Crowd-SFT: Crowdsourcing for LLM Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04063","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":"sha256:08619c32f48bff382c95ccebbd688510c173e1d01e0905062622446ff8e3c6e8","target":"record","created_at":"2026-07-05T11:15:56Z","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":"4650e7a0bdbc397ce3d9e9bb1f00e36f06d2cf2fd9813c94bafb74db53adb88c","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-06-04T15:26:38Z","title_canon_sha256":"1a96e36c8176419bc71ea10dbe47d84d85ea04d529b3a87e285136afbf92b5bb"},"schema_version":"1.0","source":{"id":"2506.04063","kind":"arxiv","version":1}},"canonical_sha256":"5fe7becd1bd2c9f5e741d83dc2892073b5239ac978b950079e8ae5caebc4c22e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fe7becd1bd2c9f5e741d83dc2892073b5239ac978b950079e8ae5caebc4c22e","first_computed_at":"2026-07-05T11:15:56.419678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:56.419678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B8RDB9b8m4zm6apuWlIkWPZY770fmSnihdLOR4JtbCl3/XE1VyWWgGekUkY0+dSyocAl/A8R5KNBExMLYB3ZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:56.420137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08619c32f48bff382c95ccebbd688510c173e1d01e0905062622446ff8e3c6e8","sha256:c220d7f3da9cb98af61018d919a02740db3831b6206a9d533980a1ff50a2e4e4"],"state_sha256":"1a791750fdd6b4f306542900474c5cf5fe42c7eba4888412a939a4c9dce88336"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jugjtw9Q/uq6EKYZLnMAOSstvGu7L+cHTm2kNuJrr8cnolsczDS8lutSPK7PYoetq6G3wQ+Ufy7X5FSy7siAAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T18:33:00.794310Z","bundle_sha256":"56771700efc1c86d269d2a126343d5bd3c0ed6bd6c596f437f303af43ac4d351"}}