{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NLHJHOWSS5HBY677AAEG7IY4M3","short_pith_number":"pith:NLHJHOWS","canonical_record":{"source":{"id":"2508.17953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T12:16:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9709865cb8552cab52c0c9850fa42c51b5c1767d02b2acb5629e611f85473d1a","abstract_canon_sha256":"dee0afab126d632aa3a6411b21d6f7f2b629a37f0495cd41b90ff128852252d1"},"schema_version":"1.0"},"canonical_sha256":"6ace93bad2974e1c7bff00086fa31c66cc3632053aaaab1d2073222d9d78c9b3","source":{"kind":"arxiv","id":"2508.17953","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17953","created_at":"2026-07-05T11:58:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17953v1","created_at":"2026-07-05T11:58:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17953","created_at":"2026-07-05T11:58:50Z"},{"alias_kind":"pith_short_12","alias_value":"NLHJHOWSS5HB","created_at":"2026-07-05T11:58:50Z"},{"alias_kind":"pith_short_16","alias_value":"NLHJHOWSS5HBY677","created_at":"2026-07-05T11:58:50Z"},{"alias_kind":"pith_short_8","alias_value":"NLHJHOWS","created_at":"2026-07-05T11:58:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NLHJHOWSS5HBY677AAEG7IY4M3","target":"record","payload":{"canonical_record":{"source":{"id":"2508.17953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T12:16:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9709865cb8552cab52c0c9850fa42c51b5c1767d02b2acb5629e611f85473d1a","abstract_canon_sha256":"dee0afab126d632aa3a6411b21d6f7f2b629a37f0495cd41b90ff128852252d1"},"schema_version":"1.0"},"canonical_sha256":"6ace93bad2974e1c7bff00086fa31c66cc3632053aaaab1d2073222d9d78c9b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:50.906713Z","signature_b64":"xMk6391heLQj1XparbqBzy2WmkI52myvQcBC32LCfOOk3Pg3lBi4DVYxvpNPBRTxxdDgPL77fNn8ufM/CLz7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ace93bad2974e1c7bff00086fa31c66cc3632053aaaab1d2073222d9d78c9b3","last_reissued_at":"2026-07-05T11:58:50.906203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:50.906203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.17953","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:58:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P3XaS6lMESrG7bpkauAy1oyyRfGMTKdLwtYSwabLZg/Tlb8522JNf8bIRVkM/K4DnoX/TAQGT6v6Hsi607HYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:02:16.694945Z"},"content_sha256":"e10dcc871500969e4d190e840a39c689cea65a6027291a4e02e04420195f4998","schema_version":"1.0","event_id":"sha256:e10dcc871500969e4d190e840a39c689cea65a6027291a4e02e04420195f4998"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NLHJHOWSS5HBY677AAEG7IY4M3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Subword Compositionality of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anders S{\\o}gaard, Qiwei Peng, Yekun Chai","submitted_at":"2025-08-25T12:16:56Z","abstract_excerpt":"Large language models (LLMs) take sequences of subwords as input, requiring them to effective compose subword representations into meaningful word-level representations. In this paper, we present a comprehensive set of experiments to probe how LLMs compose subword information, focusing on three key aspects: structural similarity, semantic decomposability, and form retention. Our analysis of the experiments suggests that these five LLM families can be classified into three distinct groups, likely reflecting difference in their underlying composition strategies. Specifically, we observe (i) thre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17953","kind":"arxiv","version":1},"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/2508.17953/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":"2026-07-05T11:58:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G2O0p58TY8zxyb4+adsD4NgLitoZXKgM0Ewmsq3Q1f2FMvU7FwLhUpIjP7fBojI4zz97rDTj6SacicFvkrGbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:02:16.695566Z"},"content_sha256":"70542cbbf3f68e97ace702af39d5afafbfb170cbedc1838ebb90d513473a2e66","schema_version":"1.0","event_id":"sha256:70542cbbf3f68e97ace702af39d5afafbfb170cbedc1838ebb90d513473a2e66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLHJHOWSS5HBY677AAEG7IY4M3/bundle.json","state_url":"https://pith.science/pith/NLHJHOWSS5HBY677AAEG7IY4M3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLHJHOWSS5HBY677AAEG7IY4M3/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":"2026-07-06T15:02:16Z","links":{"resolver":"https://pith.science/pith/NLHJHOWSS5HBY677AAEG7IY4M3","bundle":"https://pith.science/pith/NLHJHOWSS5HBY677AAEG7IY4M3/bundle.json","state":"https://pith.science/pith/NLHJHOWSS5HBY677AAEG7IY4M3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLHJHOWSS5HBY677AAEG7IY4M3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NLHJHOWSS5HBY677AAEG7IY4M3","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":"dee0afab126d632aa3a6411b21d6f7f2b629a37f0495cd41b90ff128852252d1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T12:16:56Z","title_canon_sha256":"9709865cb8552cab52c0c9850fa42c51b5c1767d02b2acb5629e611f85473d1a"},"schema_version":"1.0","source":{"id":"2508.17953","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17953","created_at":"2026-07-05T11:58:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17953v1","created_at":"2026-07-05T11:58:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17953","created_at":"2026-07-05T11:58:50Z"},{"alias_kind":"pith_short_12","alias_value":"NLHJHOWSS5HB","created_at":"2026-07-05T11:58:50Z"},{"alias_kind":"pith_short_16","alias_value":"NLHJHOWSS5HBY677","created_at":"2026-07-05T11:58:50Z"},{"alias_kind":"pith_short_8","alias_value":"NLHJHOWS","created_at":"2026-07-05T11:58:50Z"}],"graph_snapshots":[{"event_id":"sha256:70542cbbf3f68e97ace702af39d5afafbfb170cbedc1838ebb90d513473a2e66","target":"graph","created_at":"2026-07-05T11:58:50Z","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/2508.17953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) take sequences of subwords as input, requiring them to effective compose subword representations into meaningful word-level representations. In this paper, we present a comprehensive set of experiments to probe how LLMs compose subword information, focusing on three key aspects: structural similarity, semantic decomposability, and form retention. Our analysis of the experiments suggests that these five LLM families can be classified into three distinct groups, likely reflecting difference in their underlying composition strategies. Specifically, we observe (i) thre","authors_text":"Anders S{\\o}gaard, Qiwei Peng, Yekun Chai","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T12:16:56Z","title":"Understanding Subword Compositionality of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17953","kind":"arxiv","version":1},"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:e10dcc871500969e4d190e840a39c689cea65a6027291a4e02e04420195f4998","target":"record","created_at":"2026-07-05T11:58:50Z","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":"dee0afab126d632aa3a6411b21d6f7f2b629a37f0495cd41b90ff128852252d1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T12:16:56Z","title_canon_sha256":"9709865cb8552cab52c0c9850fa42c51b5c1767d02b2acb5629e611f85473d1a"},"schema_version":"1.0","source":{"id":"2508.17953","kind":"arxiv","version":1}},"canonical_sha256":"6ace93bad2974e1c7bff00086fa31c66cc3632053aaaab1d2073222d9d78c9b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ace93bad2974e1c7bff00086fa31c66cc3632053aaaab1d2073222d9d78c9b3","first_computed_at":"2026-07-05T11:58:50.906203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:50.906203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xMk6391heLQj1XparbqBzy2WmkI52myvQcBC32LCfOOk3Pg3lBi4DVYxvpNPBRTxxdDgPL77fNn8ufM/CLz7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:50.906713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17953","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e10dcc871500969e4d190e840a39c689cea65a6027291a4e02e04420195f4998","sha256:70542cbbf3f68e97ace702af39d5afafbfb170cbedc1838ebb90d513473a2e66"],"state_sha256":"ac8962cd0c6dee924ccfde1256b1784df6312864b5a4b13c016e74ceea35f718"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"whLs0raxWSXkNXhWuxguMHMwnD6llvQpXZeJodMniEnh4piEpvAFbJ6uUbluPdQBFuzG9raei6yOAJEcUvq/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:02:16.698562Z","bundle_sha256":"6ecd300ce5299623c5bc98b98bd8b0f2fcfd1cb249f6df17d6bc3d40be334a21"}}