{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q4NVFRZRV6VJBQYANLFKBBFMEH","short_pith_number":"pith:Q4NVFRZR","canonical_record":{"source":{"id":"2412.11385","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T02:27:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"663c6b5f3fa6b1a9e32ab4f3a8950dfa5cd926be0a3627a00643f7a1a83413cb","abstract_canon_sha256":"03950bae49c19b180c1ea6e38c50e82e4063d9a79bc50005a857941bdbfe4013"},"schema_version":"1.0"},"canonical_sha256":"871b52c731afaa90c3006acaa084ac21fed1f5eb671a31f315a7d9dd64a3b5dc","source":{"kind":"arxiv","id":"2412.11385","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11385","created_at":"2026-07-05T09:49:31Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11385v1","created_at":"2026-07-05T09:49:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11385","created_at":"2026-07-05T09:49:31Z"},{"alias_kind":"pith_short_12","alias_value":"Q4NVFRZRV6VJ","created_at":"2026-07-05T09:49:31Z"},{"alias_kind":"pith_short_16","alias_value":"Q4NVFRZRV6VJBQYA","created_at":"2026-07-05T09:49:31Z"},{"alias_kind":"pith_short_8","alias_value":"Q4NVFRZR","created_at":"2026-07-05T09:49:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q4NVFRZRV6VJBQYANLFKBBFMEH","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11385","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T02:27:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"663c6b5f3fa6b1a9e32ab4f3a8950dfa5cd926be0a3627a00643f7a1a83413cb","abstract_canon_sha256":"03950bae49c19b180c1ea6e38c50e82e4063d9a79bc50005a857941bdbfe4013"},"schema_version":"1.0"},"canonical_sha256":"871b52c731afaa90c3006acaa084ac21fed1f5eb671a31f315a7d9dd64a3b5dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:31.834598Z","signature_b64":"8qe5DxYH88XtzmuwaLtd3Gv/BjX102IFiGb1TtrpiNiQRfweiigFdSDFyl4VfFjGNuIczJU3PPOwmtWlgd2MDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"871b52c731afaa90c3006acaa084ac21fed1f5eb671a31f315a7d9dd64a3b5dc","last_reissued_at":"2026-07-05T09:49:31.834139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:31.834139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11385","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":"2026-07-05T09:49:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fMjLGtJ/eDlJFNezKVCx7bTN98PBmWpayy8IAjovYZlwCnz8yAeEc0SIW5rfmFqzQhy1ZvZflluHVBNh9yZBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:03:17.708019Z"},"content_sha256":"b1ad80c1814d85d04e277ac072221367f8adb3ea1dda2995093f0875b201dc1e","schema_version":"1.0","event_id":"sha256:b1ad80c1814d85d04e277ac072221367f8adb3ea1dda2995093f0875b201dc1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q4NVFRZRV6VJBQYANLFKBBFMEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Does ChatGPT \"Delve\" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Tom S. Juzek, Zina B. Ward","submitted_at":"2024-12-16T02:27:59Z","abstract_excerpt":"Scientific English is currently undergoing rapid change, with words like \"delve,\" \"intricate,\" and \"underscore\" appearing far more frequently than just a few years ago. It is widely assumed that scientists' use of large language models (LLMs) is responsible for such trends. We develop a formal, transferable method to characterize these linguistic changes. Application of our method yields 21 focal words whose increased occurrence in scientific abstracts is likely the result of LLM usage. We then pose \"the puzzle of lexical overrepresentation\": WHY are such words overused by LLMs? We fail to fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11385","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/2412.11385/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":"2026-07-05T09:49:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lm7Iu2kINjjQ2HUDBYSVn31Ui5aEUAT0Ul5nJVf+JacnIgvQ6jeZGbigXMu7TRQq7/1uUA+63zFmiJHJrtI4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:03:17.709284Z"},"content_sha256":"d8348825171222795dcb5cfcb338fd217a3cc8bacf561eec18eab93c590e4fee","schema_version":"1.0","event_id":"sha256:d8348825171222795dcb5cfcb338fd217a3cc8bacf561eec18eab93c590e4fee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4NVFRZRV6VJBQYANLFKBBFMEH/bundle.json","state_url":"https://pith.science/pith/Q4NVFRZRV6VJBQYANLFKBBFMEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4NVFRZRV6VJBQYANLFKBBFMEH/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":"2026-08-04T13:03:17Z","links":{"resolver":"https://pith.science/pith/Q4NVFRZRV6VJBQYANLFKBBFMEH","bundle":"https://pith.science/pith/Q4NVFRZRV6VJBQYANLFKBBFMEH/bundle.json","state":"https://pith.science/pith/Q4NVFRZRV6VJBQYANLFKBBFMEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4NVFRZRV6VJBQYANLFKBBFMEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q4NVFRZRV6VJBQYANLFKBBFMEH","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":"03950bae49c19b180c1ea6e38c50e82e4063d9a79bc50005a857941bdbfe4013","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T02:27:59Z","title_canon_sha256":"663c6b5f3fa6b1a9e32ab4f3a8950dfa5cd926be0a3627a00643f7a1a83413cb"},"schema_version":"1.0","source":{"id":"2412.11385","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11385","created_at":"2026-07-05T09:49:31Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11385v1","created_at":"2026-07-05T09:49:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11385","created_at":"2026-07-05T09:49:31Z"},{"alias_kind":"pith_short_12","alias_value":"Q4NVFRZRV6VJ","created_at":"2026-07-05T09:49:31Z"},{"alias_kind":"pith_short_16","alias_value":"Q4NVFRZRV6VJBQYA","created_at":"2026-07-05T09:49:31Z"},{"alias_kind":"pith_short_8","alias_value":"Q4NVFRZR","created_at":"2026-07-05T09:49:31Z"}],"graph_snapshots":[{"event_id":"sha256:d8348825171222795dcb5cfcb338fd217a3cc8bacf561eec18eab93c590e4fee","target":"graph","created_at":"2026-07-05T09:49:31Z","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/2412.11385/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scientific English is currently undergoing rapid change, with words like \"delve,\" \"intricate,\" and \"underscore\" appearing far more frequently than just a few years ago. It is widely assumed that scientists' use of large language models (LLMs) is responsible for such trends. We develop a formal, transferable method to characterize these linguistic changes. Application of our method yields 21 focal words whose increased occurrence in scientific abstracts is likely the result of LLM usage. We then pose \"the puzzle of lexical overrepresentation\": WHY are such words overused by LLMs? We fail to fin","authors_text":"Tom S. Juzek, Zina B. Ward","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T02:27:59Z","title":"Why Does ChatGPT \"Delve\" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11385","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:b1ad80c1814d85d04e277ac072221367f8adb3ea1dda2995093f0875b201dc1e","target":"record","created_at":"2026-07-05T09:49:31Z","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":"03950bae49c19b180c1ea6e38c50e82e4063d9a79bc50005a857941bdbfe4013","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T02:27:59Z","title_canon_sha256":"663c6b5f3fa6b1a9e32ab4f3a8950dfa5cd926be0a3627a00643f7a1a83413cb"},"schema_version":"1.0","source":{"id":"2412.11385","kind":"arxiv","version":1}},"canonical_sha256":"871b52c731afaa90c3006acaa084ac21fed1f5eb671a31f315a7d9dd64a3b5dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"871b52c731afaa90c3006acaa084ac21fed1f5eb671a31f315a7d9dd64a3b5dc","first_computed_at":"2026-07-05T09:49:31.834139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:31.834139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8qe5DxYH88XtzmuwaLtd3Gv/BjX102IFiGb1TtrpiNiQRfweiigFdSDFyl4VfFjGNuIczJU3PPOwmtWlgd2MDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:31.834598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11385","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1ad80c1814d85d04e277ac072221367f8adb3ea1dda2995093f0875b201dc1e","sha256:d8348825171222795dcb5cfcb338fd217a3cc8bacf561eec18eab93c590e4fee"],"state_sha256":"e2a1f7a4bfbbadac3f6e3894675b40f75f79d9b47814a9c19102ab71bf1ca3bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jAE79ZqVX//sTguCqjH26w+v2xuoVafcstAFiv5ZWoDYIvA7/5xrBrwWWmJZu7c4OXN+YbZaQm0WeJ+tlCWBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:03:17.715396Z","bundle_sha256":"7755cca090428b1a89d832340873f72d7d0af6009088c82cee5b2846fe7f94ab"}}