{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q6S3N2LF3MRY37HTX5NAFT3ELF","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":"00fe4fb4947383773c316fbcc4b49da21aa9b53dcdd02ec4ad166e45fc390258","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T14:55:00Z","title_canon_sha256":"ae2f1de4650ffa734c7cddc612c4e21c48559d86fa3f0b1356e871aedf9cf9d0"},"schema_version":"1.0","source":{"id":"2506.07833","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07833","created_at":"2026-07-05T11:20:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07833v2","created_at":"2026-07-05T11:20:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07833","created_at":"2026-07-05T11:20:55Z"},{"alias_kind":"pith_short_12","alias_value":"Q6S3N2LF3MRY","created_at":"2026-07-05T11:20:55Z"},{"alias_kind":"pith_short_16","alias_value":"Q6S3N2LF3MRY37HT","created_at":"2026-07-05T11:20:55Z"},{"alias_kind":"pith_short_8","alias_value":"Q6S3N2LF","created_at":"2026-07-05T11:20:55Z"}],"graph_snapshots":[{"event_id":"sha256:90e9966f3259f4a75c93afa11e5a6acdeee3e401e02fcdd59fcb68864a0ccca4","target":"graph","created_at":"2026-07-05T11:20:55Z","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/2506.07833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have become the cornerstone of modern AI. However, the existing paradigm of next-token prediction fundamentally limits their ability to form coherent, high-level concepts, making it a critical barrier to human-like understanding and reasoning. Take the phrase \"ribonucleic acid\" as an example: an LLM will first decompose it into tokens, i.e., artificial text fragments (\"rib\", \"on\", ...), then learn each token sequentially, rather than grasping the phrase as a unified, coherent semantic entity. This fragmented representation hinders deeper conceptual understanding an","authors_text":"Dacheng Tao, Jiaxing Huang, Michael K. Chen, Xikun Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T14:55:00Z","title":"Improving Large Language Models with Concept-Aware Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07833","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:d9e7106ad68cace485fcb97feacbe8116ac2e5d95476cdafc49049c44496f599","target":"record","created_at":"2026-07-05T11:20:55Z","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":"00fe4fb4947383773c316fbcc4b49da21aa9b53dcdd02ec4ad166e45fc390258","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T14:55:00Z","title_canon_sha256":"ae2f1de4650ffa734c7cddc612c4e21c48559d86fa3f0b1356e871aedf9cf9d0"},"schema_version":"1.0","source":{"id":"2506.07833","kind":"arxiv","version":2}},"canonical_sha256":"87a5b6e965db238dfcf3bf5a02cf64595ac82c2efbe32b88e5ead3d2eefe7250","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87a5b6e965db238dfcf3bf5a02cf64595ac82c2efbe32b88e5ead3d2eefe7250","first_computed_at":"2026-07-05T11:20:55.857920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:55.857920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0nvm938tUQqU1WF5bdtRghlkYcmnRtRKJGjs74lvkmd6bHVzOGpq1AkjfoQtBHyFluXCKvgEdXQ1XS7zPMWbCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:55.858555Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07833","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9e7106ad68cace485fcb97feacbe8116ac2e5d95476cdafc49049c44496f599","sha256:90e9966f3259f4a75c93afa11e5a6acdeee3e401e02fcdd59fcb68864a0ccca4"],"state_sha256":"35b650e9e8dcb02a6a47c149b6394a4ccfb3396ae79b266508c3fe080c6d5bf6"}