{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XXTNMKMBLX474OVG4BXLLMWK7S","short_pith_number":"pith:XXTNMKMB","canonical_record":{"source":{"id":"2411.17679","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T18:44:39Z","cross_cats_sorted":[],"title_canon_sha256":"b4d6161edbc95b77cdf7f7ebf7ddcdb670a8ed2042be97e6cc15316e92f5953f","abstract_canon_sha256":"5cb784e2d925855c3e457f00a41489bdac6f06804a3a2c7d08122b5e63a3ad4d"},"schema_version":"1.0"},"canonical_sha256":"bde6d629815df9fe3aa6e06eb5b2cafcb2764fb24503c4c878d912116e6b8f71","source":{"kind":"arxiv","id":"2411.17679","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17679","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17679v5","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17679","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"XXTNMKMBLX47","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"XXTNMKMBLX474OVG","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"XXTNMKMB","created_at":"2026-07-05T11:18:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XXTNMKMBLX474OVG4BXLLMWK7S","target":"record","payload":{"canonical_record":{"source":{"id":"2411.17679","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T18:44:39Z","cross_cats_sorted":[],"title_canon_sha256":"b4d6161edbc95b77cdf7f7ebf7ddcdb670a8ed2042be97e6cc15316e92f5953f","abstract_canon_sha256":"5cb784e2d925855c3e457f00a41489bdac6f06804a3a2c7d08122b5e63a3ad4d"},"schema_version":"1.0"},"canonical_sha256":"bde6d629815df9fe3aa6e06eb5b2cafcb2764fb24503c4c878d912116e6b8f71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:16.092551Z","signature_b64":"p9KBZIMPvULPDdVYho2eBX0z1nd9BxykhPdF6Mm8FIrhrLQAfsoD7mWrLxCn6E4I1s90Ex3VcwnqlgpwzSlvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bde6d629815df9fe3aa6e06eb5b2cafcb2764fb24503c4c878d912116e6b8f71","last_reissued_at":"2026-07-05T11:18:16.092009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:16.092009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.17679","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8NutEFhe1rMLZC3PesZLHcela9rN6JuHZxOZAno7MLG/0gVVMBSpkH6VucNGP7G24RfxVKnXfWI5IITILsG0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:17:54.591088Z"},"content_sha256":"05fc0e83915b52299278be8efd35f12885fe18b2252e727a546d5ffe23399014","schema_version":"1.0","event_id":"sha256:05fc0e83915b52299278be8efd35f12885fe18b2252e727a546d5ffe23399014"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XXTNMKMBLX474OVG4BXLLMWK7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Conglin Liu, Fei Liu, Jian He, Quanwei Shen, Yuchi Liu, Yu Kuang, Zhiqiang Zhao, Zhu Xu, Zihan Zhang","submitted_at":"2024-11-26T18:44:39Z","abstract_excerpt":"Tokenization methods like Byte-Pair Encoding (BPE) enhance computational efficiency in large language models (LLMs) but often obscure internal character structures within tokens. This limitation hinders LLMs' ability to predict precise character positions, which is crucial in tasks like Chinese Spelling Correction (CSC) where identifying the positions of misspelled characters accelerates correction processes. We propose Token Internal Position Awareness (TIPA), a method that significantly improves models' ability to capture character positions within tokens by training them on reverse characte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17679","kind":"arxiv","version":5},"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/2411.17679/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":"2026-07-05T11:18:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vc66RsrTvqllYbBqIy3WYgFRkrE10NF+l1tEwwsaDyGzFoUbw0gfysGCLmx67S6nQByxlh/La1FELJbCHUjzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:17:54.591580Z"},"content_sha256":"ce99f4e91cdce910c828218d92b6f3822ea0d0d7e930e42ea21cbd2e25897d4a","schema_version":"1.0","event_id":"sha256:ce99f4e91cdce910c828218d92b6f3822ea0d0d7e930e42ea21cbd2e25897d4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XXTNMKMBLX474OVG4BXLLMWK7S/bundle.json","state_url":"https://pith.science/pith/XXTNMKMBLX474OVG4BXLLMWK7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XXTNMKMBLX474OVG4BXLLMWK7S/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":"2026-08-13T01:17:54Z","links":{"resolver":"https://pith.science/pith/XXTNMKMBLX474OVG4BXLLMWK7S","bundle":"https://pith.science/pith/XXTNMKMBLX474OVG4BXLLMWK7S/bundle.json","state":"https://pith.science/pith/XXTNMKMBLX474OVG4BXLLMWK7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XXTNMKMBLX474OVG4BXLLMWK7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XXTNMKMBLX474OVG4BXLLMWK7S","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":"5cb784e2d925855c3e457f00a41489bdac6f06804a3a2c7d08122b5e63a3ad4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T18:44:39Z","title_canon_sha256":"b4d6161edbc95b77cdf7f7ebf7ddcdb670a8ed2042be97e6cc15316e92f5953f"},"schema_version":"1.0","source":{"id":"2411.17679","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17679","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17679v5","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17679","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"XXTNMKMBLX47","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"XXTNMKMBLX474OVG","created_at":"2026-07-05T11:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"XXTNMKMB","created_at":"2026-07-05T11:18:16Z"}],"graph_snapshots":[{"event_id":"sha256:ce99f4e91cdce910c828218d92b6f3822ea0d0d7e930e42ea21cbd2e25897d4a","target":"graph","created_at":"2026-07-05T11:18:16Z","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/2411.17679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization methods like Byte-Pair Encoding (BPE) enhance computational efficiency in large language models (LLMs) but often obscure internal character structures within tokens. This limitation hinders LLMs' ability to predict precise character positions, which is crucial in tasks like Chinese Spelling Correction (CSC) where identifying the positions of misspelled characters accelerates correction processes. We propose Token Internal Position Awareness (TIPA), a method that significantly improves models' ability to capture character positions within tokens by training them on reverse characte","authors_text":"Conglin Liu, Fei Liu, Jian He, Quanwei Shen, Yuchi Liu, Yu Kuang, Zhiqiang Zhao, Zhu Xu, Zihan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T18:44:39Z","title":"Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17679","kind":"arxiv","version":5},"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":"sha256:05fc0e83915b52299278be8efd35f12885fe18b2252e727a546d5ffe23399014","target":"record","created_at":"2026-07-05T11:18:16Z","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":"5cb784e2d925855c3e457f00a41489bdac6f06804a3a2c7d08122b5e63a3ad4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T18:44:39Z","title_canon_sha256":"b4d6161edbc95b77cdf7f7ebf7ddcdb670a8ed2042be97e6cc15316e92f5953f"},"schema_version":"1.0","source":{"id":"2411.17679","kind":"arxiv","version":5}},"canonical_sha256":"bde6d629815df9fe3aa6e06eb5b2cafcb2764fb24503c4c878d912116e6b8f71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bde6d629815df9fe3aa6e06eb5b2cafcb2764fb24503c4c878d912116e6b8f71","first_computed_at":"2026-07-05T11:18:16.092009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:16.092009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p9KBZIMPvULPDdVYho2eBX0z1nd9BxykhPdF6Mm8FIrhrLQAfsoD7mWrLxCn6E4I1s90Ex3VcwnqlgpwzSlvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:16.092551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17679","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05fc0e83915b52299278be8efd35f12885fe18b2252e727a546d5ffe23399014","sha256:ce99f4e91cdce910c828218d92b6f3822ea0d0d7e930e42ea21cbd2e25897d4a"],"state_sha256":"b66e02c07dd8701ac51b98ff21306b89201446fbddc54f30ccd3238fa625a576"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m7uXrLc3jLLjt2sWHEXJyLWF1CmG5cAv9rAnvnCR2Niz0gu6+CJLFix5MoAeGugut2lKpdkcBL7hP8cTk/IkDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T01:17:54.596372Z","bundle_sha256":"2f9a4238578e062a9d17a21380d49f7c05fcbb5ba62f157e6ccce2d7254b05eb"}}