{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KETK6U34NFLOT2IZDNFXWCLA7E","short_pith_number":"pith:KETK6U34","canonical_record":{"source":{"id":"2605.26683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T08:20:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b7c10b5710e6f3de6e71be4f7f30405a8ee4a2be350a15738a152ce0dab6bea","abstract_canon_sha256":"2580ba0719838e2c09ec7c10e0d9edbb196f0a17cb918db1e43699f533b5a43b"},"schema_version":"1.0"},"canonical_sha256":"5126af537c6956e9e9191b4b7b0960f93ed4995f60fb69c25723f44ef3507ab0","source":{"kind":"arxiv","id":"2605.26683","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26683","created_at":"2026-05-27T01:06:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26683v1","created_at":"2026-05-27T01:06:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26683","created_at":"2026-05-27T01:06:05Z"},{"alias_kind":"pith_short_12","alias_value":"KETK6U34NFLO","created_at":"2026-05-27T01:06:05Z"},{"alias_kind":"pith_short_16","alias_value":"KETK6U34NFLOT2IZ","created_at":"2026-05-27T01:06:05Z"},{"alias_kind":"pith_short_8","alias_value":"KETK6U34","created_at":"2026-05-27T01:06:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KETK6U34NFLOT2IZDNFXWCLA7E","target":"record","payload":{"canonical_record":{"source":{"id":"2605.26683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T08:20:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b7c10b5710e6f3de6e71be4f7f30405a8ee4a2be350a15738a152ce0dab6bea","abstract_canon_sha256":"2580ba0719838e2c09ec7c10e0d9edbb196f0a17cb918db1e43699f533b5a43b"},"schema_version":"1.0"},"canonical_sha256":"5126af537c6956e9e9191b4b7b0960f93ed4995f60fb69c25723f44ef3507ab0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:05.914922Z","signature_b64":"AZ1wmz12TuTQve3Fq1HC3T0Gsq2MAeWptp/Ahuwdt/w/AFINb7MV7DgT4aM5Gi/p/+e1oylwDNUrSRo4TE4VBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5126af537c6956e9e9191b4b7b0960f93ed4995f60fb69c25723f44ef3507ab0","last_reissued_at":"2026-05-27T01:06:05.914264Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:05.914264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.26683","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":"2026-05-27T01:06:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Hn/ReZe2O9of+u3OqRCcL+u7y1KRpFze8wXa8bNnxZ8fJ4/wKeiPJ51wE1+tr7jYDofuLZB4T5X9116oMR7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T04:58:41.336742Z"},"content_sha256":"c26c9f9f0598716b6f65d9a7e0439a43810a71e46abe93dcd14a9d1d34cfbf01","schema_version":"1.0","event_id":"sha256:c26c9f9f0598716b6f65d9a7e0439a43810a71e46abe93dcd14a9d1d34cfbf01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KETK6U34NFLOT2IZDNFXWCLA7E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An In-Vitro Study on Cross-Lingual Generalization in Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adrian Cosma","submitted_at":"2026-05-26T08:20:20Z","abstract_excerpt":"Cross-lingual transfer in language models is difficult to study in natural corpora because lexical overlap, morphology, data imbalance, and tokenization are entangled. We introduce an in-vitro framework with two procedurally generated languages that share the same ontology, typed grammar, and compositional structure, but differ in surface realization. This lets us independently vary lexical distance, minority-language proportion, tokenizer training regime, and vocabulary size, while evaluating transfer on a masked minority-language condition whose lexical forms are never observed during traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26683","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/2605.26683/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":"2026-05-27T01:06:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YpPZgCugf2dKB15HXVDRih/S59aEexKIDzV7hY4aNfLtERayFq0tsD0jonTCcxDGO7WIAjD9y38+jpEvbAdJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T04:58:41.337123Z"},"content_sha256":"1b73bcae207adb7c05147cd7f1e947853b02862d7f777f754f9d0fff76c09f5d","schema_version":"1.0","event_id":"sha256:1b73bcae207adb7c05147cd7f1e947853b02862d7f777f754f9d0fff76c09f5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KETK6U34NFLOT2IZDNFXWCLA7E/bundle.json","state_url":"https://pith.science/pith/KETK6U34NFLOT2IZDNFXWCLA7E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KETK6U34NFLOT2IZDNFXWCLA7E/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":"2026-06-30T04:58:41Z","links":{"resolver":"https://pith.science/pith/KETK6U34NFLOT2IZDNFXWCLA7E","bundle":"https://pith.science/pith/KETK6U34NFLOT2IZDNFXWCLA7E/bundle.json","state":"https://pith.science/pith/KETK6U34NFLOT2IZDNFXWCLA7E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KETK6U34NFLOT2IZDNFXWCLA7E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KETK6U34NFLOT2IZDNFXWCLA7E","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":"2580ba0719838e2c09ec7c10e0d9edbb196f0a17cb918db1e43699f533b5a43b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T08:20:20Z","title_canon_sha256":"8b7c10b5710e6f3de6e71be4f7f30405a8ee4a2be350a15738a152ce0dab6bea"},"schema_version":"1.0","source":{"id":"2605.26683","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26683","created_at":"2026-05-27T01:06:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26683v1","created_at":"2026-05-27T01:06:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26683","created_at":"2026-05-27T01:06:05Z"},{"alias_kind":"pith_short_12","alias_value":"KETK6U34NFLO","created_at":"2026-05-27T01:06:05Z"},{"alias_kind":"pith_short_16","alias_value":"KETK6U34NFLOT2IZ","created_at":"2026-05-27T01:06:05Z"},{"alias_kind":"pith_short_8","alias_value":"KETK6U34","created_at":"2026-05-27T01:06:05Z"}],"graph_snapshots":[{"event_id":"sha256:1b73bcae207adb7c05147cd7f1e947853b02862d7f777f754f9d0fff76c09f5d","target":"graph","created_at":"2026-05-27T01:06:05Z","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/2605.26683/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual transfer in language models is difficult to study in natural corpora because lexical overlap, morphology, data imbalance, and tokenization are entangled. We introduce an in-vitro framework with two procedurally generated languages that share the same ontology, typed grammar, and compositional structure, but differ in surface realization. This lets us independently vary lexical distance, minority-language proportion, tokenizer training regime, and vocabulary size, while evaluating transfer on a masked minority-language condition whose lexical forms are never observed during traini","authors_text":"Adrian Cosma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T08:20:20Z","title":"An In-Vitro Study on Cross-Lingual Generalization in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26683","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:c26c9f9f0598716b6f65d9a7e0439a43810a71e46abe93dcd14a9d1d34cfbf01","target":"record","created_at":"2026-05-27T01:06:05Z","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":"2580ba0719838e2c09ec7c10e0d9edbb196f0a17cb918db1e43699f533b5a43b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T08:20:20Z","title_canon_sha256":"8b7c10b5710e6f3de6e71be4f7f30405a8ee4a2be350a15738a152ce0dab6bea"},"schema_version":"1.0","source":{"id":"2605.26683","kind":"arxiv","version":1}},"canonical_sha256":"5126af537c6956e9e9191b4b7b0960f93ed4995f60fb69c25723f44ef3507ab0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5126af537c6956e9e9191b4b7b0960f93ed4995f60fb69c25723f44ef3507ab0","first_computed_at":"2026-05-27T01:06:05.914264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:05.914264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AZ1wmz12TuTQve3Fq1HC3T0Gsq2MAeWptp/Ahuwdt/w/AFINb7MV7DgT4aM5Gi/p/+e1oylwDNUrSRo4TE4VBw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:05.914922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26683","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c26c9f9f0598716b6f65d9a7e0439a43810a71e46abe93dcd14a9d1d34cfbf01","sha256:1b73bcae207adb7c05147cd7f1e947853b02862d7f777f754f9d0fff76c09f5d"],"state_sha256":"1eaf013cc4bb83a5423c23a4644d94025ccf3ce60becb4c6d527637c09351a1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qmx+jMHExcoBQGRV2b59uIrScVrteSkWNqwsh5YElKeYxdvr2BZggMZVyTsUza4kp3F2xlXwRAsJC2WnGvUJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T04:58:41.339213Z","bundle_sha256":"27c2c7e9a9a7cc439a55b2cbdc12263ebd0a555faf33f1701179a84091c767c5"}}