{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DW7EGYTLD4VQ4QH65JF4KZASYZ","short_pith_number":"pith:DW7EGYTL","canonical_record":{"source":{"id":"2501.07886","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T06:54:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1d94e46884a245491085adc48831f8dc5f60d1a64df29d78714096a38f9c2a4c","abstract_canon_sha256":"3964c83b320606c1513d01b736ac55d06ed0c5e18c7005e73678f623aa7376f5"},"schema_version":"1.0"},"canonical_sha256":"1dbe43626b1f2b0e40feea4bc56412c66dd6618505a49326560d9367e070bfee","source":{"kind":"arxiv","id":"2501.07886","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07886","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07886v1","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07886","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"DW7EGYTLD4VQ","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"pith_short_16","alias_value":"DW7EGYTLD4VQ4QH6","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"pith_short_8","alias_value":"DW7EGYTL","created_at":"2026-07-05T10:00:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DW7EGYTLD4VQ4QH65JF4KZASYZ","target":"record","payload":{"canonical_record":{"source":{"id":"2501.07886","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T06:54:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1d94e46884a245491085adc48831f8dc5f60d1a64df29d78714096a38f9c2a4c","abstract_canon_sha256":"3964c83b320606c1513d01b736ac55d06ed0c5e18c7005e73678f623aa7376f5"},"schema_version":"1.0"},"canonical_sha256":"1dbe43626b1f2b0e40feea4bc56412c66dd6618505a49326560d9367e070bfee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:51.921494Z","signature_b64":"CjV4OQ+PvPQBwGBN3oIM6VnttJvzumHDXvgOewEVWiCgymHE1nZLcoFfHP35wx1l+JES0VFhB5+HOk7Ii/hNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dbe43626b1f2b0e40feea4bc56412c66dd6618505a49326560d9367e070bfee","last_reissued_at":"2026-07-05T10:00:51.920879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:51.920879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.07886","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":"2026-07-05T10:00:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6kjYob2qK0Zm8cNuYHBC4o/CPQ3TM1PkKnuU26WtnE+ENM1BhJZGtCqdQTi41WgilQddfiHVyVJxb6P5HpOkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:55:34.350936Z"},"content_sha256":"46869e155cdbe03831675181446ca757d16962763f418d71031f64495aa6dd1f","schema_version":"1.0","event_id":"sha256:46869e155cdbe03831675181446ca757d16962763f418d71031f64495aa6dd1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DW7EGYTLD4VQ4QH65JF4KZASYZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cassidy Laidlaw, Jacob Steinhardt, Yaowen Ye","submitted_at":"2025-01-14T06:54:17Z","abstract_excerpt":"Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more capable, the tasks they are given become harder to supervise. Will post-training remain effective under unreliable supervision? To test this, we simulate unreliable demonstrations and comparison feedback using small LMs and time-constrained humans. We find that in the presence of unreliable supervision, SFT still retains some effectiveness, but DPO (a common "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07886","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/2501.07886/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":"2026-07-05T10:00:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IeGfVdzpL6NTq+c37lXqfGq2ufgcdqMDNbV/l6eaX+kcvT4obnV/Ow0er3NAOV42BzDBXpXWhQSPO3AS3U7eBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:55:34.351450Z"},"content_sha256":"ee917801872391b34e87ace4e707abb89cafe3823c79ef7e4fafe6645dd97d7d","schema_version":"1.0","event_id":"sha256:ee917801872391b34e87ace4e707abb89cafe3823c79ef7e4fafe6645dd97d7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DW7EGYTLD4VQ4QH65JF4KZASYZ/bundle.json","state_url":"https://pith.science/pith/DW7EGYTLD4VQ4QH65JF4KZASYZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DW7EGYTLD4VQ4QH65JF4KZASYZ/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":"2026-08-13T23:55:34Z","links":{"resolver":"https://pith.science/pith/DW7EGYTLD4VQ4QH65JF4KZASYZ","bundle":"https://pith.science/pith/DW7EGYTLD4VQ4QH65JF4KZASYZ/bundle.json","state":"https://pith.science/pith/DW7EGYTLD4VQ4QH65JF4KZASYZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DW7EGYTLD4VQ4QH65JF4KZASYZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DW7EGYTLD4VQ4QH65JF4KZASYZ","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":"3964c83b320606c1513d01b736ac55d06ed0c5e18c7005e73678f623aa7376f5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T06:54:17Z","title_canon_sha256":"1d94e46884a245491085adc48831f8dc5f60d1a64df29d78714096a38f9c2a4c"},"schema_version":"1.0","source":{"id":"2501.07886","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07886","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07886v1","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07886","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"DW7EGYTLD4VQ","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"pith_short_16","alias_value":"DW7EGYTLD4VQ4QH6","created_at":"2026-07-05T10:00:51Z"},{"alias_kind":"pith_short_8","alias_value":"DW7EGYTL","created_at":"2026-07-05T10:00:51Z"}],"graph_snapshots":[{"event_id":"sha256:ee917801872391b34e87ace4e707abb89cafe3823c79ef7e4fafe6645dd97d7d","target":"graph","created_at":"2026-07-05T10:00:51Z","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/2501.07886/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more capable, the tasks they are given become harder to supervise. Will post-training remain effective under unreliable supervision? To test this, we simulate unreliable demonstrations and comparison feedback using small LMs and time-constrained humans. We find that in the presence of unreliable supervision, SFT still retains some effectiveness, but DPO (a common ","authors_text":"Cassidy Laidlaw, Jacob Steinhardt, Yaowen Ye","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T06:54:17Z","title":"Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07886","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":"sha256:46869e155cdbe03831675181446ca757d16962763f418d71031f64495aa6dd1f","target":"record","created_at":"2026-07-05T10:00:51Z","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":"3964c83b320606c1513d01b736ac55d06ed0c5e18c7005e73678f623aa7376f5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T06:54:17Z","title_canon_sha256":"1d94e46884a245491085adc48831f8dc5f60d1a64df29d78714096a38f9c2a4c"},"schema_version":"1.0","source":{"id":"2501.07886","kind":"arxiv","version":1}},"canonical_sha256":"1dbe43626b1f2b0e40feea4bc56412c66dd6618505a49326560d9367e070bfee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1dbe43626b1f2b0e40feea4bc56412c66dd6618505a49326560d9367e070bfee","first_computed_at":"2026-07-05T10:00:51.920879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:51.920879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CjV4OQ+PvPQBwGBN3oIM6VnttJvzumHDXvgOewEVWiCgymHE1nZLcoFfHP35wx1l+JES0VFhB5+HOk7Ii/hNDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:51.921494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07886","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46869e155cdbe03831675181446ca757d16962763f418d71031f64495aa6dd1f","sha256:ee917801872391b34e87ace4e707abb89cafe3823c79ef7e4fafe6645dd97d7d"],"state_sha256":"a85d418910798e99216bb985f1098ef91733c2eaaf128b54d7f5961acc083a89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t/CNXKp9PBcYEkK0btjYM284iWXCekB8DRkRQ9F51+tMNz0lNhEjRgicMauhLhS9QqSXX2xuXX8/ALqYAfFtDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T23:55:34.361063Z","bundle_sha256":"5607674f0f6007541aecd20c0f253a425c808e42aac188e99f0f19e2ee717de8"}}