{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BCXC2YRN3XWXHY7VJXUBP3X4P7","short_pith_number":"pith:BCXC2YRN","canonical_record":{"source":{"id":"2407.19594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-28T21:58:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4765d60a4750e9915353b629b743d1784e91eeb58c3f6c845b6bc70f79cf3e2","abstract_canon_sha256":"042f2af102c348bf0a91a57b226a10980cb60755d9056f05e05672a6eb8fc572"},"schema_version":"1.0"},"canonical_sha256":"08ae2d622ddded73e3f54de817eefc7fd795b8bfe58e2d37d248f1fd775ea452","source":{"kind":"arxiv","id":"2407.19594","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19594","created_at":"2026-07-05T08:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19594v2","created_at":"2026-07-05T08:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19594","created_at":"2026-07-05T08:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"BCXC2YRN3XWX","created_at":"2026-07-05T08:49:54Z"},{"alias_kind":"pith_short_16","alias_value":"BCXC2YRN3XWXHY7V","created_at":"2026-07-05T08:49:54Z"},{"alias_kind":"pith_short_8","alias_value":"BCXC2YRN","created_at":"2026-07-05T08:49:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BCXC2YRN3XWXHY7VJXUBP3X4P7","target":"record","payload":{"canonical_record":{"source":{"id":"2407.19594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-28T21:58:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4765d60a4750e9915353b629b743d1784e91eeb58c3f6c845b6bc70f79cf3e2","abstract_canon_sha256":"042f2af102c348bf0a91a57b226a10980cb60755d9056f05e05672a6eb8fc572"},"schema_version":"1.0"},"canonical_sha256":"08ae2d622ddded73e3f54de817eefc7fd795b8bfe58e2d37d248f1fd775ea452","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:54.484689Z","signature_b64":"/8nSoUjNKYbizfGAjsf2MqjfY0iJ5Y0De/Q3+yrh8GRr7o3jIfZ8blKbEqfg2wIzCiK7wClyGXSYVtb40mxtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08ae2d622ddded73e3f54de817eefc7fd795b8bfe58e2d37d248f1fd775ea452","last_reissued_at":"2026-07-05T08:49:54.484226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:54.484226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.19594","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":"2026-07-05T08:49:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dv8B1LLMRCxxY/NYkyJTie8MFEXf5y/2A5raamN7N0RyMkii+r8IVenXVQnKJsRYphGkJnRBonHRL3UQWSWyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:15:28.870259Z"},"content_sha256":"93b231fbe2f0e6c3aabbd8ff54de0bf5cbc77ecf12a204c2ae97a43f4b780cb5","schema_version":"1.0","event_id":"sha256:93b231fbe2f0e6c3aabbd8ff54de0bf5cbc77ecf12a204c2ae97a43f4b780cb5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BCXC2YRN3XWXHY7VJXUBP3X4P7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jason Weston, Jiantao Jiao, Jing Xu, Olga Golovneva, Sainbayar Sukhbaatar, Tianhao Wu, Weizhe Yuan, Yuandong Tian","submitted_at":"2024-07-28T21:58:28Z","abstract_excerpt":"Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains. While improving these models traditionally relies on costly human data, recent self-rewarding mechanisms (Yuan et al., 2024) have shown that LLMs can improve by judging their own responses instead of relying on human labelers. However, existing methods have primarily focused on improving model responses rather than judgment capabilities, resulting in rapid saturation during iterative training. To address this issue, we introduce a novel Meta-Rewarding step to the self-improvement process, where the model judge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19594","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/2407.19594/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":"2026-07-05T08:49:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tFiA2yBcjRgexh7DspJV57zNgNZQsQPDDE0TqCV4V0Qnj714AVGXuYefEJ9xZQ64k7dVfqiOgzNy75rDqYSMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:15:28.870848Z"},"content_sha256":"472385354032be3355214a4f95c493b8e628a2296e7b24d62bd4ff3e89b5070b","schema_version":"1.0","event_id":"sha256:472385354032be3355214a4f95c493b8e628a2296e7b24d62bd4ff3e89b5070b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCXC2YRN3XWXHY7VJXUBP3X4P7/bundle.json","state_url":"https://pith.science/pith/BCXC2YRN3XWXHY7VJXUBP3X4P7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCXC2YRN3XWXHY7VJXUBP3X4P7/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":"2026-08-05T23:15:28Z","links":{"resolver":"https://pith.science/pith/BCXC2YRN3XWXHY7VJXUBP3X4P7","bundle":"https://pith.science/pith/BCXC2YRN3XWXHY7VJXUBP3X4P7/bundle.json","state":"https://pith.science/pith/BCXC2YRN3XWXHY7VJXUBP3X4P7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCXC2YRN3XWXHY7VJXUBP3X4P7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BCXC2YRN3XWXHY7VJXUBP3X4P7","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":"042f2af102c348bf0a91a57b226a10980cb60755d9056f05e05672a6eb8fc572","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-28T21:58:28Z","title_canon_sha256":"c4765d60a4750e9915353b629b743d1784e91eeb58c3f6c845b6bc70f79cf3e2"},"schema_version":"1.0","source":{"id":"2407.19594","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19594","created_at":"2026-07-05T08:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19594v2","created_at":"2026-07-05T08:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19594","created_at":"2026-07-05T08:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"BCXC2YRN3XWX","created_at":"2026-07-05T08:49:54Z"},{"alias_kind":"pith_short_16","alias_value":"BCXC2YRN3XWXHY7V","created_at":"2026-07-05T08:49:54Z"},{"alias_kind":"pith_short_8","alias_value":"BCXC2YRN","created_at":"2026-07-05T08:49:54Z"}],"graph_snapshots":[{"event_id":"sha256:472385354032be3355214a4f95c493b8e628a2296e7b24d62bd4ff3e89b5070b","target":"graph","created_at":"2026-07-05T08:49:54Z","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/2407.19594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains. While improving these models traditionally relies on costly human data, recent self-rewarding mechanisms (Yuan et al., 2024) have shown that LLMs can improve by judging their own responses instead of relying on human labelers. However, existing methods have primarily focused on improving model responses rather than judgment capabilities, resulting in rapid saturation during iterative training. To address this issue, we introduce a novel Meta-Rewarding step to the self-improvement process, where the model judge","authors_text":"Jason Weston, Jiantao Jiao, Jing Xu, Olga Golovneva, Sainbayar Sukhbaatar, Tianhao Wu, Weizhe Yuan, Yuandong Tian","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-28T21:58:28Z","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19594","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":"sha256:93b231fbe2f0e6c3aabbd8ff54de0bf5cbc77ecf12a204c2ae97a43f4b780cb5","target":"record","created_at":"2026-07-05T08:49:54Z","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":"042f2af102c348bf0a91a57b226a10980cb60755d9056f05e05672a6eb8fc572","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-28T21:58:28Z","title_canon_sha256":"c4765d60a4750e9915353b629b743d1784e91eeb58c3f6c845b6bc70f79cf3e2"},"schema_version":"1.0","source":{"id":"2407.19594","kind":"arxiv","version":2}},"canonical_sha256":"08ae2d622ddded73e3f54de817eefc7fd795b8bfe58e2d37d248f1fd775ea452","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08ae2d622ddded73e3f54de817eefc7fd795b8bfe58e2d37d248f1fd775ea452","first_computed_at":"2026-07-05T08:49:54.484226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:49:54.484226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/8nSoUjNKYbizfGAjsf2MqjfY0iJ5Y0De/Q3+yrh8GRr7o3jIfZ8blKbEqfg2wIzCiK7wClyGXSYVtb40mxtAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:49:54.484689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.19594","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93b231fbe2f0e6c3aabbd8ff54de0bf5cbc77ecf12a204c2ae97a43f4b780cb5","sha256:472385354032be3355214a4f95c493b8e628a2296e7b24d62bd4ff3e89b5070b"],"state_sha256":"4490e406852428f96edac12c4356430a7202839ed75980a905390564ca001171"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gh507vojdTwZRh7rBT7NdeyVYngEpXSPAUS6fUOPASiPdIpoc9UHsmvhJjjWgekslLhZVo/x7oXYXdkEnLbPBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:15:28.876708Z","bundle_sha256":"5ff41e3db7b95b8129e77331286099576c6d703d0c70791f2b2650e395ef81f1"}}