{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U4LKF5NWGTDCEQJKBAEFH25ECK","short_pith_number":"pith:U4LKF5NW","canonical_record":{"source":{"id":"2408.09849","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T09:51:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2672097a3ad14f1ebfa0cd0cd93b9f347d575780971809420239dfc99c6e650b","abstract_canon_sha256":"ca6dac792f1963902cefcabaa204b1674fbc2976740087609b28dcd23c2bfbe3"},"schema_version":"1.0"},"canonical_sha256":"a716a2f5b634c622412a080853eba4129ecf046b42f8bcdbf44aebacf01f0ecb","source":{"kind":"arxiv","id":"2408.09849","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09849","created_at":"2026-07-05T09:48:15Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09849v2","created_at":"2026-07-05T09:48:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09849","created_at":"2026-07-05T09:48:15Z"},{"alias_kind":"pith_short_12","alias_value":"U4LKF5NWGTDC","created_at":"2026-07-05T09:48:15Z"},{"alias_kind":"pith_short_16","alias_value":"U4LKF5NWGTDCEQJK","created_at":"2026-07-05T09:48:15Z"},{"alias_kind":"pith_short_8","alias_value":"U4LKF5NW","created_at":"2026-07-05T09:48:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U4LKF5NWGTDCEQJKBAEFH25ECK","target":"record","payload":{"canonical_record":{"source":{"id":"2408.09849","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T09:51:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2672097a3ad14f1ebfa0cd0cd93b9f347d575780971809420239dfc99c6e650b","abstract_canon_sha256":"ca6dac792f1963902cefcabaa204b1674fbc2976740087609b28dcd23c2bfbe3"},"schema_version":"1.0"},"canonical_sha256":"a716a2f5b634c622412a080853eba4129ecf046b42f8bcdbf44aebacf01f0ecb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:15.253526Z","signature_b64":"2vlVnwnNxbi2JG+2IgyeBb8hCW6yKfujJ70eRXRZsL/Y9XlkYIwW0ACFkdZ2nLaPHyz3oft1hUcNxvuXoxFyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a716a2f5b634c622412a080853eba4129ecf046b42f8bcdbf44aebacf01f0ecb","last_reissued_at":"2026-07-05T09:48:15.253048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:15.253048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.09849","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:48:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5S8kvq/es8PPdAkxdQ18fNUD+CNKp/8dpIW0m53TXpnFx/5TQeNTs6UPhBjTYejkLWGzLI8q1eY3pDuZxai6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:39:20.467371Z"},"content_sha256":"046c88f70622b7b0762b2916eba2000a0077ad077d8eba0284269138a7ceaec2","schema_version":"1.0","event_id":"sha256:046c88f70622b7b0762b2916eba2000a0077ad077d8eba0284269138a7ceaec2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U4LKF5NWGTDCEQJKBAEFH25ECK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Importance Weighting Can Help Large Language Models Self-Improve","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chi-Min Chan, Chunyang Jiang, Qifeng Liu, Wei Xue, Yike Guo","submitted_at":"2024-08-19T09:51:02Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable capability in numerous tasks and applications. However, fine-tuning LLMs using high-quality datasets under external supervision remains prohibitively expensive. In response, LLM self-improvement approaches have been vibrantly developed recently. The typical paradigm of LLM self-improvement involves training LLM on self-generated data, part of which may be detrimental and should be filtered out due to the unstable data quality. While current works primarily employs filtering strategies based on answer correctness, in this paper, we demonstrate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09849","kind":"arxiv","version":2},"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/2408.09849/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":"2026-07-05T09:48:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eGkK6W6Y3TUDrgDwSiHbRJLyllTfUOo7rylTk1prvMh/WZG6JnG7EEtMWgix31Zle17vFHwh8Iqc/altqln7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:39:20.468464Z"},"content_sha256":"174af502f4edb09c40297988e83e3864e3e579a223db32fdb2b4e443a71471f4","schema_version":"1.0","event_id":"sha256:174af502f4edb09c40297988e83e3864e3e579a223db32fdb2b4e443a71471f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U4LKF5NWGTDCEQJKBAEFH25ECK/bundle.json","state_url":"https://pith.science/pith/U4LKF5NWGTDCEQJKBAEFH25ECK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U4LKF5NWGTDCEQJKBAEFH25ECK/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":"2026-08-09T03:39:20Z","links":{"resolver":"https://pith.science/pith/U4LKF5NWGTDCEQJKBAEFH25ECK","bundle":"https://pith.science/pith/U4LKF5NWGTDCEQJKBAEFH25ECK/bundle.json","state":"https://pith.science/pith/U4LKF5NWGTDCEQJKBAEFH25ECK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U4LKF5NWGTDCEQJKBAEFH25ECK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U4LKF5NWGTDCEQJKBAEFH25ECK","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":"ca6dac792f1963902cefcabaa204b1674fbc2976740087609b28dcd23c2bfbe3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T09:51:02Z","title_canon_sha256":"2672097a3ad14f1ebfa0cd0cd93b9f347d575780971809420239dfc99c6e650b"},"schema_version":"1.0","source":{"id":"2408.09849","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09849","created_at":"2026-07-05T09:48:15Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09849v2","created_at":"2026-07-05T09:48:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09849","created_at":"2026-07-05T09:48:15Z"},{"alias_kind":"pith_short_12","alias_value":"U4LKF5NWGTDC","created_at":"2026-07-05T09:48:15Z"},{"alias_kind":"pith_short_16","alias_value":"U4LKF5NWGTDCEQJK","created_at":"2026-07-05T09:48:15Z"},{"alias_kind":"pith_short_8","alias_value":"U4LKF5NW","created_at":"2026-07-05T09:48:15Z"}],"graph_snapshots":[{"event_id":"sha256:174af502f4edb09c40297988e83e3864e3e579a223db32fdb2b4e443a71471f4","target":"graph","created_at":"2026-07-05T09:48:15Z","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/2408.09849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown remarkable capability in numerous tasks and applications. However, fine-tuning LLMs using high-quality datasets under external supervision remains prohibitively expensive. In response, LLM self-improvement approaches have been vibrantly developed recently. The typical paradigm of LLM self-improvement involves training LLM on self-generated data, part of which may be detrimental and should be filtered out due to the unstable data quality. While current works primarily employs filtering strategies based on answer correctness, in this paper, we demonstrate ","authors_text":"Chi-Min Chan, Chunyang Jiang, Qifeng Liu, Wei Xue, Yike Guo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T09:51:02Z","title":"Importance Weighting Can Help Large Language Models Self-Improve"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09849","kind":"arxiv","version":2},"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":"sha256:046c88f70622b7b0762b2916eba2000a0077ad077d8eba0284269138a7ceaec2","target":"record","created_at":"2026-07-05T09:48:15Z","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":"ca6dac792f1963902cefcabaa204b1674fbc2976740087609b28dcd23c2bfbe3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T09:51:02Z","title_canon_sha256":"2672097a3ad14f1ebfa0cd0cd93b9f347d575780971809420239dfc99c6e650b"},"schema_version":"1.0","source":{"id":"2408.09849","kind":"arxiv","version":2}},"canonical_sha256":"a716a2f5b634c622412a080853eba4129ecf046b42f8bcdbf44aebacf01f0ecb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a716a2f5b634c622412a080853eba4129ecf046b42f8bcdbf44aebacf01f0ecb","first_computed_at":"2026-07-05T09:48:15.253048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:15.253048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2vlVnwnNxbi2JG+2IgyeBb8hCW6yKfujJ70eRXRZsL/Y9XlkYIwW0ACFkdZ2nLaPHyz3oft1hUcNxvuXoxFyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:15.253526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09849","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:046c88f70622b7b0762b2916eba2000a0077ad077d8eba0284269138a7ceaec2","sha256:174af502f4edb09c40297988e83e3864e3e579a223db32fdb2b4e443a71471f4"],"state_sha256":"2ccd2d1711a4641af6401372e482fafc451ec704bfbf080eb65b31c86f57fbb5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ot9YlPQPhOj41FQLje8pkttx/RJCRqX39w21/Yb80t2MbYqP9txizWzoQltzVRDGcnFtJQZoG9gLhsjfunCbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:39:20.475123Z","bundle_sha256":"1df89f27ae96c3658c7aba8e72f650cfe663b98f88261dbf4410d47310bf85a6"}}