{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TXFFPM5TU4X6TVK34IC5BIMLOT","short_pith_number":"pith:TXFFPM5T","canonical_record":{"source":{"id":"2406.04854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T11:37:45Z","cross_cats_sorted":[],"title_canon_sha256":"46a364a6d843caa56bb86589a3c29aeb62100039271e3ee78e841a56e0e54f28","abstract_canon_sha256":"7e2b3ae9c8489739ed7218a7df76ff13a4683cffac988eff0fc1b1091625c765"},"schema_version":"1.0"},"canonical_sha256":"9dca57b3b3a72fe9d55be205d0a18b74f068d1f92092f71279680d486e2585e4","source":{"kind":"arxiv","id":"2406.04854","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04854","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04854v1","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04854","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"TXFFPM5TU4X6","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"TXFFPM5TU4X6TVK3","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"TXFFPM5T","created_at":"2026-07-05T08:28:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TXFFPM5TU4X6TVK34IC5BIMLOT","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T11:37:45Z","cross_cats_sorted":[],"title_canon_sha256":"46a364a6d843caa56bb86589a3c29aeb62100039271e3ee78e841a56e0e54f28","abstract_canon_sha256":"7e2b3ae9c8489739ed7218a7df76ff13a4683cffac988eff0fc1b1091625c765"},"schema_version":"1.0"},"canonical_sha256":"9dca57b3b3a72fe9d55be205d0a18b74f068d1f92092f71279680d486e2585e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:49.967337Z","signature_b64":"j6EoDr+ZERCmIsoUvYFHHO1QM3m/fT/A9VfHtnb9DacgsZVa4Je738l7Y6lYBfR0dD+pdha+KTrebQBCrPY9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dca57b3b3a72fe9d55be205d0a18b74f068d1f92092f71279680d486e2585e4","last_reissued_at":"2026-07-05T08:28:49.966893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:49.966893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04854","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":"2026-07-05T08:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BZgA6znsYP5j7mcxwX+iSWUun+zkvRU11S4Y164Klp7zIUm4K9bt8K+i2+sew5i1+YREJDDCUEbOCuSb/IczCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:45:54.148236Z"},"content_sha256":"f00bba312cce106e8fde3a5fc611defba46d4ca6b17f13fb37c1578c86245612","schema_version":"1.0","event_id":"sha256:f00bba312cce106e8fde3a5fc611defba46d4ca6b17f13fb37c1578c86245612"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TXFFPM5TU4X6TVK34IC5BIMLOT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty Aware Learning for Language Model Alignment","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dacheng Tao, Dahua Lin, Liang Ding, Qi Zhang, Rui Zheng, Yikun Wang","submitted_at":"2024-06-07T11:37:45Z","abstract_excerpt":"As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges. Existing alignment strategies, which typically leverage diverse and high-quality data sources, often overlook the intrinsic uncertainty of tasks, learning all data samples equally. This may lead to suboptimal data efficiency and model performance. In response, we propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios, by introducing the sample uncertainty (elicited from more capable LLMs). We implement UAL in a simple fashi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04854","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/2406.04854/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":"2026-07-05T08:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VICGBt5yHuTHSJhhzuNStz/EkQkSqXMYW3Unbv2TMPWOL/QxAvIeRJqOBGHhYVRJS8RgUo+vA4NUxqPWpxAGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:45:54.148934Z"},"content_sha256":"17e7d6a450930b45aef83469957e2d2a54f8b2ffa6f31ae8ce76ae679693c592","schema_version":"1.0","event_id":"sha256:17e7d6a450930b45aef83469957e2d2a54f8b2ffa6f31ae8ce76ae679693c592"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXFFPM5TU4X6TVK34IC5BIMLOT/bundle.json","state_url":"https://pith.science/pith/TXFFPM5TU4X6TVK34IC5BIMLOT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXFFPM5TU4X6TVK34IC5BIMLOT/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":"2026-08-08T20:45:54Z","links":{"resolver":"https://pith.science/pith/TXFFPM5TU4X6TVK34IC5BIMLOT","bundle":"https://pith.science/pith/TXFFPM5TU4X6TVK34IC5BIMLOT/bundle.json","state":"https://pith.science/pith/TXFFPM5TU4X6TVK34IC5BIMLOT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXFFPM5TU4X6TVK34IC5BIMLOT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TXFFPM5TU4X6TVK34IC5BIMLOT","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":"7e2b3ae9c8489739ed7218a7df76ff13a4683cffac988eff0fc1b1091625c765","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T11:37:45Z","title_canon_sha256":"46a364a6d843caa56bb86589a3c29aeb62100039271e3ee78e841a56e0e54f28"},"schema_version":"1.0","source":{"id":"2406.04854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04854","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04854v1","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04854","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"TXFFPM5TU4X6","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"TXFFPM5TU4X6TVK3","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"TXFFPM5T","created_at":"2026-07-05T08:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:17e7d6a450930b45aef83469957e2d2a54f8b2ffa6f31ae8ce76ae679693c592","target":"graph","created_at":"2026-07-05T08:28:49Z","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/2406.04854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges. Existing alignment strategies, which typically leverage diverse and high-quality data sources, often overlook the intrinsic uncertainty of tasks, learning all data samples equally. This may lead to suboptimal data efficiency and model performance. In response, we propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios, by introducing the sample uncertainty (elicited from more capable LLMs). We implement UAL in a simple fashi","authors_text":"Dacheng Tao, Dahua Lin, Liang Ding, Qi Zhang, Rui Zheng, Yikun Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T11:37:45Z","title":"Uncertainty Aware Learning for Language Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04854","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:f00bba312cce106e8fde3a5fc611defba46d4ca6b17f13fb37c1578c86245612","target":"record","created_at":"2026-07-05T08:28:49Z","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":"7e2b3ae9c8489739ed7218a7df76ff13a4683cffac988eff0fc1b1091625c765","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T11:37:45Z","title_canon_sha256":"46a364a6d843caa56bb86589a3c29aeb62100039271e3ee78e841a56e0e54f28"},"schema_version":"1.0","source":{"id":"2406.04854","kind":"arxiv","version":1}},"canonical_sha256":"9dca57b3b3a72fe9d55be205d0a18b74f068d1f92092f71279680d486e2585e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dca57b3b3a72fe9d55be205d0a18b74f068d1f92092f71279680d486e2585e4","first_computed_at":"2026-07-05T08:28:49.966893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:49.966893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j6EoDr+ZERCmIsoUvYFHHO1QM3m/fT/A9VfHtnb9DacgsZVa4Je738l7Y6lYBfR0dD+pdha+KTrebQBCrPY9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:49.967337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f00bba312cce106e8fde3a5fc611defba46d4ca6b17f13fb37c1578c86245612","sha256:17e7d6a450930b45aef83469957e2d2a54f8b2ffa6f31ae8ce76ae679693c592"],"state_sha256":"af3108b475cd5c59d6620034bb3947288433ea50ba2fa1443117978b8464f2e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NEoxyJx7W5m8gcWl4cqK/KfthsGJ5pl5LsrPA+TGbtCZ+pqaJ9kOC+VKQFWthMBYOEOlgRjNOeZsJh16mNGrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:45:54.154881Z","bundle_sha256":"4716e0a8e1aa815e01aee98ac9ab856fc403f388376f5b705767c960c15a0854"}}