{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2QIXR3KPKC75X7WDINLLF6E6LE","short_pith_number":"pith:2QIXR3KP","canonical_record":{"source":{"id":"2608.04670","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T10:28:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d2b9cc88cbc267fdfa394c0ff7b3de65b2597e39a632646f3b128cbd129f85f","abstract_canon_sha256":"b3ee7b55c98dfd28489309a2b5a4477ed9f8c7837fd462abea1416be67317669"},"schema_version":"1.0"},"canonical_sha256":"d41178ed4f50bfdbfec34356b2f89e5906f80925fe6330d187cd0ec065b1d2b7","source":{"kind":"arxiv","id":"2608.04670","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04670","created_at":"2026-08-06T01:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04670v1","created_at":"2026-08-06T01:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04670","created_at":"2026-08-06T01:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"2QIXR3KPKC75","created_at":"2026-08-06T01:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"2QIXR3KPKC75X7WD","created_at":"2026-08-06T01:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"2QIXR3KP","created_at":"2026-08-06T01:46:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2QIXR3KPKC75X7WDINLLF6E6LE","target":"record","payload":{"canonical_record":{"source":{"id":"2608.04670","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T10:28:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d2b9cc88cbc267fdfa394c0ff7b3de65b2597e39a632646f3b128cbd129f85f","abstract_canon_sha256":"b3ee7b55c98dfd28489309a2b5a4477ed9f8c7837fd462abea1416be67317669"},"schema_version":"1.0"},"canonical_sha256":"d41178ed4f50bfdbfec34356b2f89e5906f80925fe6330d187cd0ec065b1d2b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:46:08.220791Z","signature_b64":"cGHk02lrMM97WaRMb5pm1XNeLGkA8hUfkBYPTuGvpQkmqI9AjLM+VjEcsDO+D6zTlaZPlYPWES1KqEzJZ4xjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d41178ed4f50bfdbfec34356b2f89e5906f80925fe6330d187cd0ec065b1d2b7","last_reissued_at":"2026-08-06T01:46:08.219124Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:46:08.219124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.04670","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":"2026-08-06T01:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHG6Mhi5mKHIYcqI2Dc9DwUcBycvYTdR6Li890dAcf1oeE1I/hGxgEkMz2dk0QJ1QPm0Uy/0oyM1LRiUGPIMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:41:23.017413Z"},"content_sha256":"022883b715c6aab4081e6582d554562e69e7716d30aeeed2b3aebbf4c1979d17","schema_version":"1.0","event_id":"sha256:022883b715c6aab4081e6582d554562e69e7716d30aeeed2b3aebbf4c1979d17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2QIXR3KPKC75X7WDINLLF6E6LE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Calogero Jerik Scozzaro, Daniele Paolo Radicioni, Enrico Mensa, Lorenzo Zane, Matteo Delsanto, Tommaso Milani","submitted_at":"2026-08-05T10:28:51Z","abstract_excerpt":"Large Language Models (LLMs) have transformed computational linguistics and achieved remarkable performance across numerous natural language processing tasks, yet significant gaps persist in understanding how these systems process culturally embedded linguistic expressions. This paper introduces ProverbIT, a novel Italian benchmark comprising 100 multiple-choice questions designed to evaluate LLMs' ability to complete Italian proverbs. We assess 13 frontier models, including Large Reasoning Models (LRMs) and traditional LLMs, across three tasks: proverb completion, multiple-choice selection wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04670","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/2608.04670/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":"2026-08-06T01:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6IkfJJqKQglv4okoYlXjysYGkkWnZpfV4i0ewSzH1t2zpvMELnMxQ2kVs2dOP+sDCb/Z8D4wvX6pHXBwnbEbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:41:23.017986Z"},"content_sha256":"f38a9c054661f2d86eb77020edea9d0b76adb6d6908dba83a2168d69804492d4","schema_version":"1.0","event_id":"sha256:f38a9c054661f2d86eb77020edea9d0b76adb6d6908dba83a2168d69804492d4"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:2QIXR3KPKC75X7WDINLLF6E6LE","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2024.naacl-short.46) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"J. Etxaniz, G. Azkune, A. Soroa, O. Lopez de Lacalle, M. Artetxe, Do multilingual language models think better in English?, in: K. Duh, H. Gomez, S. Bethard (Eds.), Proceedings of the 2024 Conference of the North American Chap- ter of the A","arxiv_id":"2608.04670","detector":"doi_compliance","evidence":{"ref_index":35,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/2024.naac","reconstructed_doi":"10.18653/v1/2024.naacl-short.46"},"severity":"advisory","ref_index":35,"audited_at":"2026-08-06T19:28:11.635351Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2024.naacl-short.46","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"37a61c23dd1613814ed077785a04ce76c3504a1b49238a43a444ed1f7e31bbf9","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18353,"payload_sha256":"93f9d095db8daa7a894031fcbab62274c5072d8364a16d0534a2754eeaaeef8b","signature_b64":"jtS8DVGfsjxClap2nGyPwc+ZhIcqBGu7YB1O4HkKo2vDdT9jspFx4LqkkHuz0a9sDxSRkPGIZ8m6djZwkxsRDA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T19:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BzyrgAAM5Xl3cQwBadqFT6ioD64n84hp6tc5jU5bpP2FXRPO7wZzTdlaWE3XnWaWKPsCA7amph+WPsMPC9HYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:41:23.020962Z"},"content_sha256":"6e7b905ddc5bd2656d3a95a5c98052b9d6ca7a46e1152d4bc5bdd281784438bd","schema_version":"1.0","event_id":"sha256:6e7b905ddc5bd2656d3a95a5c98052b9d6ca7a46e1152d4bc5bdd281784438bd"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:2QIXR3KPKC75X7WDINLLF6E6LE","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1007/3-540-45715-1_1) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"I. A. Sag, T. Baldwin, F. Bond, A. Copestake, D. Flickinger, Multiword Expressions: A Pain in the Neck for NLP, Springer Berlin Heidelberg, 2002, p. 1–15. URL: http://dx.doi.org/10.1007/3-540-45715- 1_1. doi:10.1007/3-540-45715-1_1","arxiv_id":"2608.04670","detector":"doi_compliance","evidence":{"ref_index":16,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1007/3-540-45715-","reconstructed_doi":"10.1007/3-540-45715-1_1"},"severity":"advisory","ref_index":16,"audited_at":"2026-08-06T19:28:11.635351Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/3-540-45715-1_1","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"555e6a02392c9344c46c8586c58e7bba40a20cc3a6d8b2384dcd4a66d8df117c","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18352,"payload_sha256":"55cd118fa69906456475ad4bc68670eba39c8b8170622b04ebf6c5aeacd00e3b","signature_b64":"FYI4YPp8J7y/l+B31YsEjxVTmOJITReQrW4YOLkZyrKc36sIGEm8UnWiIWVV7mSMWQzVDvyGBpV8Z5Ym4HKlAw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T19:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GJ1V0e1fi0JlyYp2UYoo8y6rCp8C+iDPzvByeOk6NWwXrdaIdLFKTujewVathdzBHSp+fdmOrTwcE7F+dlBIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:41:23.021370Z"},"content_sha256":"06d98725892da9bde2041c2669b5fb1e459d2e4dd5567c2cb5ce6f02cd2b85c0","schema_version":"1.0","event_id":"sha256:06d98725892da9bde2041c2669b5fb1e459d2e4dd5567c2cb5ce6f02cd2b85c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2QIXR3KPKC75X7WDINLLF6E6LE/bundle.json","state_url":"https://pith.science/pith/2QIXR3KPKC75X7WDINLLF6E6LE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2QIXR3KPKC75X7WDINLLF6E6LE/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":"2026-08-11T05:41:23Z","links":{"resolver":"https://pith.science/pith/2QIXR3KPKC75X7WDINLLF6E6LE","bundle":"https://pith.science/pith/2QIXR3KPKC75X7WDINLLF6E6LE/bundle.json","state":"https://pith.science/pith/2QIXR3KPKC75X7WDINLLF6E6LE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2QIXR3KPKC75X7WDINLLF6E6LE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2QIXR3KPKC75X7WDINLLF6E6LE","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b3ee7b55c98dfd28489309a2b5a4477ed9f8c7837fd462abea1416be67317669","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T10:28:51Z","title_canon_sha256":"8d2b9cc88cbc267fdfa394c0ff7b3de65b2597e39a632646f3b128cbd129f85f"},"schema_version":"1.0","source":{"id":"2608.04670","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04670","created_at":"2026-08-06T01:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04670v1","created_at":"2026-08-06T01:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04670","created_at":"2026-08-06T01:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"2QIXR3KPKC75","created_at":"2026-08-06T01:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"2QIXR3KPKC75X7WD","created_at":"2026-08-06T01:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"2QIXR3KP","created_at":"2026-08-06T01:46:08Z"}],"graph_snapshots":[{"event_id":"sha256:f38a9c054661f2d86eb77020edea9d0b76adb6d6908dba83a2168d69804492d4","target":"graph","created_at":"2026-08-06T01:46:08Z","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/2608.04670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have transformed computational linguistics and achieved remarkable performance across numerous natural language processing tasks, yet significant gaps persist in understanding how these systems process culturally embedded linguistic expressions. This paper introduces ProverbIT, a novel Italian benchmark comprising 100 multiple-choice questions designed to evaluate LLMs' ability to complete Italian proverbs. We assess 13 frontier models, including Large Reasoning Models (LRMs) and traditional LLMs, across three tasks: proverb completion, multiple-choice selection wi","authors_text":"Calogero Jerik Scozzaro, Daniele Paolo Radicioni, Enrico Mensa, Lorenzo Zane, Matteo Delsanto, Tommaso Milani","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T10:28:51Z","title":"Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04670","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":"sha256:022883b715c6aab4081e6582d554562e69e7716d30aeeed2b3aebbf4c1979d17","target":"record","created_at":"2026-08-06T01:46:08Z","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":"b3ee7b55c98dfd28489309a2b5a4477ed9f8c7837fd462abea1416be67317669","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T10:28:51Z","title_canon_sha256":"8d2b9cc88cbc267fdfa394c0ff7b3de65b2597e39a632646f3b128cbd129f85f"},"schema_version":"1.0","source":{"id":"2608.04670","kind":"arxiv","version":1}},"canonical_sha256":"d41178ed4f50bfdbfec34356b2f89e5906f80925fe6330d187cd0ec065b1d2b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d41178ed4f50bfdbfec34356b2f89e5906f80925fe6330d187cd0ec065b1d2b7","first_computed_at":"2026-08-06T01:46:08.219124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:46:08.219124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cGHk02lrMM97WaRMb5pm1XNeLGkA8hUfkBYPTuGvpQkmqI9AjLM+VjEcsDO+D6zTlaZPlYPWES1KqEzJZ4xjAA==","signature_status":"signed_v1","signed_at":"2026-08-06T01:46:08.220791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04670","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:06d98725892da9bde2041c2669b5fb1e459d2e4dd5567c2cb5ce6f02cd2b85c0","sha256:6e7b905ddc5bd2656d3a95a5c98052b9d6ca7a46e1152d4bc5bdd281784438bd"]}],"invalid_events":[],"applied_event_ids":["sha256:022883b715c6aab4081e6582d554562e69e7716d30aeeed2b3aebbf4c1979d17","sha256:f38a9c054661f2d86eb77020edea9d0b76adb6d6908dba83a2168d69804492d4"],"state_sha256":"73432fa224f9bbcbb324fe30e35bbe2f5f753761174e6643c4c1fa5186d94e91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OqDwtqfVAPt4aLGB6P933+2URLZkDFiKW0INsJJSqvJKBv0h0PNAPYbRafW6ZaTZlofquN7ogxLMGNVSl9CNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T05:41:23.024114Z","bundle_sha256":"ca35fa788767f195f2535a2f7d6b329b49b9bc43ccbdcbe6838d394f93650f94"}}