{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YYLIFSUQRJMM2PUX7F3FOBH56O","short_pith_number":"pith:YYLIFSUQ","canonical_record":{"source":{"id":"2404.04298","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-04T20:27:37Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"640933ad3495403f07dfff78c44a2f435e767927f47662a8d7bec371ac8a90ba","abstract_canon_sha256":"a73e75a933ebecd64d30fa7eac4bc6a3f35c2544c99c68e5828a7c6e324c4655"},"schema_version":"1.0"},"canonical_sha256":"c61682ca908a58cd3e97f9765704fdf3828020d71aef902fda742ded352fa82c","source":{"kind":"arxiv","id":"2404.04298","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04298","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04298v3","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04298","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"YYLIFSUQRJMM","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"YYLIFSUQRJMM2PUX","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"YYLIFSUQ","created_at":"2026-07-05T09:03:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YYLIFSUQRJMM2PUX7F3FOBH56O","target":"record","payload":{"canonical_record":{"source":{"id":"2404.04298","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-04T20:27:37Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"640933ad3495403f07dfff78c44a2f435e767927f47662a8d7bec371ac8a90ba","abstract_canon_sha256":"a73e75a933ebecd64d30fa7eac4bc6a3f35c2544c99c68e5828a7c6e324c4655"},"schema_version":"1.0"},"canonical_sha256":"c61682ca908a58cd3e97f9765704fdf3828020d71aef902fda742ded352fa82c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:50.920712Z","signature_b64":"WhkpH0D0nS/zWpjDzGElui5OHBzELS9skOyTHJhKEWddph115++VaObf3BOYYkWjxE2PuayJH0ceHnZg2d5sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c61682ca908a58cd3e97f9765704fdf3828020d71aef902fda742ded352fa82c","last_reissued_at":"2026-07-05T09:03:50.920172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:50.920172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.04298","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V1ast+fsc0/ZTFLAESnHEORql2F3OvJ9rf1jZIAhw58NJKRmIghkjdGShRTihc75YSwHjgywLqKhnOR1oSR2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:13:02.785977Z"},"content_sha256":"88d2808d714a4e97ff35d33b979f828e175e42f744630303f04aee6d1a541c53","schema_version":"1.0","event_id":"sha256:88d2808d714a4e97ff35d33b979f828e175e42f744630303f04aee6d1a541c53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YYLIFSUQRJMM2PUX7F3FOBH56O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Benjamin Van Durme, Daniel Khashabi, Dongwei Jiang, Jingyu Zhang, Nathaniel Weir, Orion Weller","submitted_at":"2024-04-04T20:27:37Z","abstract_excerpt":"Can LLMs consistently improve their previous outputs for better results? For this to be true, LLMs would need to be better at discriminating among previously-generated alternatives, than generating initial responses. We explore the validity of this hypothesis in practice. We first formulate a unified framework that allows us to compare the generative and discriminative capability of any model on any task. In our resulting experimental analysis of several open-source and industrial LLMs, we observe that models are not reliably better at discriminating among previously-generated alternatives tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04298","kind":"arxiv","version":3},"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/2404.04298/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":"2026-07-05T09:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OsJuC2GdzdLv4VfXd1TO9c1uCDanqs5+JOBHBfEAvXvCKR4l7FECEdtk/tL/4OuKus5anpmkwYTPfi6Gd6lNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:13:02.786516Z"},"content_sha256":"fe1d673e3f2823977788b8b93fd66fcf55f592ab79b3525f3f3fb6295c29da6e","schema_version":"1.0","event_id":"sha256:fe1d673e3f2823977788b8b93fd66fcf55f592ab79b3525f3f3fb6295c29da6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YYLIFSUQRJMM2PUX7F3FOBH56O/bundle.json","state_url":"https://pith.science/pith/YYLIFSUQRJMM2PUX7F3FOBH56O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YYLIFSUQRJMM2PUX7F3FOBH56O/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":"2026-08-08T13:13:02Z","links":{"resolver":"https://pith.science/pith/YYLIFSUQRJMM2PUX7F3FOBH56O","bundle":"https://pith.science/pith/YYLIFSUQRJMM2PUX7F3FOBH56O/bundle.json","state":"https://pith.science/pith/YYLIFSUQRJMM2PUX7F3FOBH56O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YYLIFSUQRJMM2PUX7F3FOBH56O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YYLIFSUQRJMM2PUX7F3FOBH56O","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":"a73e75a933ebecd64d30fa7eac4bc6a3f35c2544c99c68e5828a7c6e324c4655","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-04T20:27:37Z","title_canon_sha256":"640933ad3495403f07dfff78c44a2f435e767927f47662a8d7bec371ac8a90ba"},"schema_version":"1.0","source":{"id":"2404.04298","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04298","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04298v3","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04298","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"YYLIFSUQRJMM","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"YYLIFSUQRJMM2PUX","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"YYLIFSUQ","created_at":"2026-07-05T09:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:fe1d673e3f2823977788b8b93fd66fcf55f592ab79b3525f3f3fb6295c29da6e","target":"graph","created_at":"2026-07-05T09:03:50Z","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/2404.04298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can LLMs consistently improve their previous outputs for better results? For this to be true, LLMs would need to be better at discriminating among previously-generated alternatives, than generating initial responses. We explore the validity of this hypothesis in practice. We first formulate a unified framework that allows us to compare the generative and discriminative capability of any model on any task. In our resulting experimental analysis of several open-source and industrial LLMs, we observe that models are not reliably better at discriminating among previously-generated alternatives tha","authors_text":"Benjamin Van Durme, Daniel Khashabi, Dongwei Jiang, Jingyu Zhang, Nathaniel Weir, Orion Weller","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-04T20:27:37Z","title":"SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04298","kind":"arxiv","version":3},"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":"sha256:88d2808d714a4e97ff35d33b979f828e175e42f744630303f04aee6d1a541c53","target":"record","created_at":"2026-07-05T09:03:50Z","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":"a73e75a933ebecd64d30fa7eac4bc6a3f35c2544c99c68e5828a7c6e324c4655","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-04T20:27:37Z","title_canon_sha256":"640933ad3495403f07dfff78c44a2f435e767927f47662a8d7bec371ac8a90ba"},"schema_version":"1.0","source":{"id":"2404.04298","kind":"arxiv","version":3}},"canonical_sha256":"c61682ca908a58cd3e97f9765704fdf3828020d71aef902fda742ded352fa82c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c61682ca908a58cd3e97f9765704fdf3828020d71aef902fda742ded352fa82c","first_computed_at":"2026-07-05T09:03:50.920172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:50.920172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WhkpH0D0nS/zWpjDzGElui5OHBzELS9skOyTHJhKEWddph115++VaObf3BOYYkWjxE2PuayJH0ceHnZg2d5sAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:50.920712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04298","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88d2808d714a4e97ff35d33b979f828e175e42f744630303f04aee6d1a541c53","sha256:fe1d673e3f2823977788b8b93fd66fcf55f592ab79b3525f3f3fb6295c29da6e"],"state_sha256":"54ddc12f9cee2b3810c581b61e0856ca60e9fa7596c15a9407cd2f636395729e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6m2N4X9a0M0dUTgC4qwJPm0mAvIm9rrN4jAaaR/Svtqybkf7KB1RNFSmeOA4CGLruHaBFPy/59eZWJoC4deuAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:13:02.791085Z","bundle_sha256":"7924f08d4317db10a772e73afe09176ff6241c497188089ebfdb1f82c7b43931"}}