{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:52SKZCPUKRXFTPRSTMRE6OCRTA","short_pith_number":"pith:52SKZCPU","canonical_record":{"source":{"id":"2406.11275","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:25:09Z","cross_cats_sorted":[],"title_canon_sha256":"f39007266b033b1ae000776f67a3a51029fe1f46f705588cc7b922e715da639f","abstract_canon_sha256":"6b33e1049971e2efacbe2c41f0dbe95c8d21e3a4d5abf2e7d53d18c4215bd3a7"},"schema_version":"1.0"},"canonical_sha256":"eea4ac89f4546e59be329b224f38519804a2e9bbe515d5a9e06f32a8713076db","source":{"kind":"arxiv","id":"2406.11275","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11275","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11275v2","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11275","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"52SKZCPUKRXF","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"52SKZCPUKRXFTPRS","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"52SKZCPU","created_at":"2026-07-05T09:34:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:52SKZCPUKRXFTPRSTMRE6OCRTA","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11275","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:25:09Z","cross_cats_sorted":[],"title_canon_sha256":"f39007266b033b1ae000776f67a3a51029fe1f46f705588cc7b922e715da639f","abstract_canon_sha256":"6b33e1049971e2efacbe2c41f0dbe95c8d21e3a4d5abf2e7d53d18c4215bd3a7"},"schema_version":"1.0"},"canonical_sha256":"eea4ac89f4546e59be329b224f38519804a2e9bbe515d5a9e06f32a8713076db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:14.964387Z","signature_b64":"qMBTZ6Ai5JO5z7qwCcv77maO/3VkAa7bAkkjp1Ek+I+n8xzb3b3PxvVskoHVhG7+Hy177Mi1h1KNK6G2+uMEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eea4ac89f4546e59be329b224f38519804a2e9bbe515d5a9e06f32a8713076db","last_reissued_at":"2026-07-05T09:34:14.963930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:14.963930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11275","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":"2026-07-05T09:34:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KmCwqkjIJVEWdu6KFgtFPWWNnSh+4m3ue5j29gll8WdDvlWv/Gh6ZvsJ1hsig/ebaxmAljJVmgZ2i/Zf6YsNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T10:38:32.170802Z"},"content_sha256":"df1b6048e56395fdeb7283da2eca4d8bd5b966c128871b264bc112bb2224ab60","schema_version":"1.0","event_id":"sha256:df1b6048e56395fdeb7283da2eca4d8bd5b966c128871b264bc112bb2224ab60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:52SKZCPUKRXFTPRSTMRE6OCRTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-training Large Language Models through Knowledge Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Erik Cambria, Przemyslaw Kazienko, Ranjan Satapathy, Teddy Ferdinan, Wei Jie Yeo","submitted_at":"2024-06-17T07:25:09Z","abstract_excerpt":"Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its own labels and selectively trains on unknown data samples identified through a reference-free consistency method. Empirical evaluations demonstrate significant improvements in reducing hallucination in generation across multiple subjects. Furthermore, the selective training framework mitigates catastrophic forgetting in out-of-distribution benchmarks, address"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11275","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/2406.11275/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":"2026-07-05T09:34:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YcLyT6+ApB1w6hDk5c0KsNCUsR9Xommuj7I4mf0TBcW/z3g+bKbOzHj+/jbAiQHJuyV63dn5DGaaQzetSRvFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T10:38:32.171728Z"},"content_sha256":"6ee5c1d9f535bd2a03c123bfe3ec345d8f007a75ee23dab353a5ea126def2499","schema_version":"1.0","event_id":"sha256:6ee5c1d9f535bd2a03c123bfe3ec345d8f007a75ee23dab353a5ea126def2499"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/52SKZCPUKRXFTPRSTMRE6OCRTA/bundle.json","state_url":"https://pith.science/pith/52SKZCPUKRXFTPRSTMRE6OCRTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/52SKZCPUKRXFTPRSTMRE6OCRTA/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":"2026-08-13T10:38:32Z","links":{"resolver":"https://pith.science/pith/52SKZCPUKRXFTPRSTMRE6OCRTA","bundle":"https://pith.science/pith/52SKZCPUKRXFTPRSTMRE6OCRTA/bundle.json","state":"https://pith.science/pith/52SKZCPUKRXFTPRSTMRE6OCRTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/52SKZCPUKRXFTPRSTMRE6OCRTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:52SKZCPUKRXFTPRSTMRE6OCRTA","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":"6b33e1049971e2efacbe2c41f0dbe95c8d21e3a4d5abf2e7d53d18c4215bd3a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:25:09Z","title_canon_sha256":"f39007266b033b1ae000776f67a3a51029fe1f46f705588cc7b922e715da639f"},"schema_version":"1.0","source":{"id":"2406.11275","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11275","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11275v2","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11275","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"52SKZCPUKRXF","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"52SKZCPUKRXFTPRS","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"52SKZCPU","created_at":"2026-07-05T09:34:14Z"}],"graph_snapshots":[{"event_id":"sha256:6ee5c1d9f535bd2a03c123bfe3ec345d8f007a75ee23dab353a5ea126def2499","target":"graph","created_at":"2026-07-05T09:34:14Z","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/2406.11275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its own labels and selectively trains on unknown data samples identified through a reference-free consistency method. Empirical evaluations demonstrate significant improvements in reducing hallucination in generation across multiple subjects. Furthermore, the selective training framework mitigates catastrophic forgetting in out-of-distribution benchmarks, address","authors_text":"Erik Cambria, Przemyslaw Kazienko, Ranjan Satapathy, Teddy Ferdinan, Wei Jie Yeo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:25:09Z","title":"Self-training Large Language Models through Knowledge Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11275","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:df1b6048e56395fdeb7283da2eca4d8bd5b966c128871b264bc112bb2224ab60","target":"record","created_at":"2026-07-05T09:34:14Z","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":"6b33e1049971e2efacbe2c41f0dbe95c8d21e3a4d5abf2e7d53d18c4215bd3a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:25:09Z","title_canon_sha256":"f39007266b033b1ae000776f67a3a51029fe1f46f705588cc7b922e715da639f"},"schema_version":"1.0","source":{"id":"2406.11275","kind":"arxiv","version":2}},"canonical_sha256":"eea4ac89f4546e59be329b224f38519804a2e9bbe515d5a9e06f32a8713076db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eea4ac89f4546e59be329b224f38519804a2e9bbe515d5a9e06f32a8713076db","first_computed_at":"2026-07-05T09:34:14.963930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:14.963930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qMBTZ6Ai5JO5z7qwCcv77maO/3VkAa7bAkkjp1Ek+I+n8xzb3b3PxvVskoHVhG7+Hy177Mi1h1KNK6G2+uMEBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:14.964387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11275","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df1b6048e56395fdeb7283da2eca4d8bd5b966c128871b264bc112bb2224ab60","sha256:6ee5c1d9f535bd2a03c123bfe3ec345d8f007a75ee23dab353a5ea126def2499"],"state_sha256":"5b99685aa7374c30037f502469150ce35f716c4315b2b75a07bb0646452da6f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06OTTymnZBj9BBHkuVO7oRQiBepTOp5v2GQjpkIG4o2rpspbzxqG4CP8sr3kOtp3BUC8Rydo8WzkBUSR7ozOBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T10:38:32.180645Z","bundle_sha256":"768b6247cc169fcb335bc3d1752a21104538c8a92a0c9e66b6f33633e17d7509"}}