{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A2G2FIO2UA3RPJ6XCHYJ64UOH2","short_pith_number":"pith:A2G2FIO2","canonical_record":{"source":{"id":"2608.05850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T10:24:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2fa70477d6c2f5484697b20e5a16a1270ba0d3dd262af4b7cd199ee0e033cd11","abstract_canon_sha256":"65646a75ce36a2682aa4a967065a74a031d4a020833e758b9bcb6f3d544451de"},"schema_version":"1.0"},"canonical_sha256":"068da2a1daa03717a7d711f09f728e3e9925124f3347c403beab64a123a7ea07","source":{"kind":"arxiv","id":"2608.05850","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05850","created_at":"2026-08-07T00:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05850v1","created_at":"2026-08-07T00:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05850","created_at":"2026-08-07T00:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"A2G2FIO2UA3R","created_at":"2026-08-07T00:52:55Z"},{"alias_kind":"pith_short_16","alias_value":"A2G2FIO2UA3RPJ6X","created_at":"2026-08-07T00:52:55Z"},{"alias_kind":"pith_short_8","alias_value":"A2G2FIO2","created_at":"2026-08-07T00:52:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A2G2FIO2UA3RPJ6XCHYJ64UOH2","target":"record","payload":{"canonical_record":{"source":{"id":"2608.05850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T10:24:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2fa70477d6c2f5484697b20e5a16a1270ba0d3dd262af4b7cd199ee0e033cd11","abstract_canon_sha256":"65646a75ce36a2682aa4a967065a74a031d4a020833e758b9bcb6f3d544451de"},"schema_version":"1.0"},"canonical_sha256":"068da2a1daa03717a7d711f09f728e3e9925124f3347c403beab64a123a7ea07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:55.786490Z","signature_b64":"kb4nh+0Ei0O/WkQNXVThwwiUAcxqGKJ9qR8La1UYDLbMDEKo97FqpaaZa+xcII+TusvHL7zAsubJLqCqzwAPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"068da2a1daa03717a7d711f09f728e3e9925124f3347c403beab64a123a7ea07","last_reissued_at":"2026-08-07T00:52:55.785038Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:55.785038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.05850","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":"2026-08-07T00:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2sga3hxby1UAIqnShy8UjXtw2/h9msS58pZyHg5FqIZNCJWlHZbNVkBvRCSbft+6l3Z7wuq7f7oot5672y7sAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:34:33.013354Z"},"content_sha256":"43fc540956ae88b93b814ca6a79221acd83c66c2a36ec87e560006faca9d2354","schema_version":"1.0","event_id":"sha256:43fc540956ae88b93b814ca6a79221acd83c66c2a36ec87e560006faca9d2354"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A2G2FIO2UA3RPJ6XCHYJ64UOH2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MameLoshnLM: Yiddish Language Model and Evaluation Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Noah A. Smith, Omer Goldman, Reut Tsarfaty, Tomasz Limisiewicz, Uri Katz","submitted_at":"2026-08-06T10:24:08Z","abstract_excerpt":"We present MameLoshnLM, the first open-source 8B-parameter language model built specifically for Yiddish. Despite Yiddish's rich textual tradition, its limited digital presence and the scarcity of reliable evaluation resources have constrained progress in Yiddish language modeling. Existing multilingual corpora and benchmarks are often poor proxies for the language, containing substantial amounts of noisy, machine-translated, and misclassified text. We address these gaps by introducing Oytser, a high-quality Yiddish pretraining corpus that combines contemporary web-native sources with literary"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05850","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/2608.05850/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":"2026-08-07T00:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RHrcdWADqiAOO4191Ie7zPybzmf/tnq4gJYplVP0jFVjaCgaHcw8hn5gP6WkZwDCRTD9AB6SRJdcGfGyHdk8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:34:33.014274Z"},"content_sha256":"922b89e126263971dadc9a935dce23d3af32d794c3102cfb093c301e94087f58","schema_version":"1.0","event_id":"sha256:922b89e126263971dadc9a935dce23d3af32d794c3102cfb093c301e94087f58"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:A2G2FIO2UA3RPJ6XCHYJ64UOH2","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2020.acl-main.747) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzm \\'a n, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. Unsupervised cross-lingual representation learning at scale. In Da","arxiv_id":"2608.05850","detector":"doi_compliance","evidence":{"ref_index":38,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/2020.ac","reconstructed_doi":"10.18653/v1/2020.acl-main.747"},"severity":"advisory","ref_index":38,"audited_at":"2026-08-07T22:28:11.561127Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2020.acl-main.747","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"90f8ef6cb1a17844e6a8f27189a808c629e06e5e07cce59b83fd25590348e8f6","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18557,"payload_sha256":"df05830cf8c966b40a02e0e791fb33a8c26d8ffdc2249d31a5dfbd30e643809e","signature_b64":"lJWg3xc1a7jVM1F6fkSZ99ccaWhZhWiVMcQBwNAOmh0V+KT8JFePIeZAEvGSOuBp/LV2Xp76kqFZOM7fdCAOBA==","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":"2026-08-07T22:28:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ejwV8EoRXGICrA1TL1osPyhuxnOUwXCbsrFqJrbfN4z04dwtLJ3p/97P4C2S23+c2nNyyJceYKdv+rUkVJODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:34:33.017687Z"},"content_sha256":"7afe51452673d1666f443ed72cc9a650cf5d3834771f24ff586ed37ce9a36f59","schema_version":"1.0","event_id":"sha256:7afe51452673d1666f443ed72cc9a650cf5d3834771f24ff586ed37ce9a36f59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A2G2FIO2UA3RPJ6XCHYJ64UOH2/bundle.json","state_url":"https://pith.science/pith/A2G2FIO2UA3RPJ6XCHYJ64UOH2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A2G2FIO2UA3RPJ6XCHYJ64UOH2/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":"2026-08-09T14:34:33Z","links":{"resolver":"https://pith.science/pith/A2G2FIO2UA3RPJ6XCHYJ64UOH2","bundle":"https://pith.science/pith/A2G2FIO2UA3RPJ6XCHYJ64UOH2/bundle.json","state":"https://pith.science/pith/A2G2FIO2UA3RPJ6XCHYJ64UOH2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A2G2FIO2UA3RPJ6XCHYJ64UOH2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A2G2FIO2UA3RPJ6XCHYJ64UOH2","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"65646a75ce36a2682aa4a967065a74a031d4a020833e758b9bcb6f3d544451de","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T10:24:08Z","title_canon_sha256":"2fa70477d6c2f5484697b20e5a16a1270ba0d3dd262af4b7cd199ee0e033cd11"},"schema_version":"1.0","source":{"id":"2608.05850","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05850","created_at":"2026-08-07T00:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05850v1","created_at":"2026-08-07T00:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05850","created_at":"2026-08-07T00:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"A2G2FIO2UA3R","created_at":"2026-08-07T00:52:55Z"},{"alias_kind":"pith_short_16","alias_value":"A2G2FIO2UA3RPJ6X","created_at":"2026-08-07T00:52:55Z"},{"alias_kind":"pith_short_8","alias_value":"A2G2FIO2","created_at":"2026-08-07T00:52:55Z"}],"graph_snapshots":[{"event_id":"sha256:922b89e126263971dadc9a935dce23d3af32d794c3102cfb093c301e94087f58","target":"graph","created_at":"2026-08-07T00:52:55Z","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/2608.05850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MameLoshnLM, the first open-source 8B-parameter language model built specifically for Yiddish. Despite Yiddish's rich textual tradition, its limited digital presence and the scarcity of reliable evaluation resources have constrained progress in Yiddish language modeling. Existing multilingual corpora and benchmarks are often poor proxies for the language, containing substantial amounts of noisy, machine-translated, and misclassified text. We address these gaps by introducing Oytser, a high-quality Yiddish pretraining corpus that combines contemporary web-native sources with literary","authors_text":"Noah A. Smith, Omer Goldman, Reut Tsarfaty, Tomasz Limisiewicz, Uri Katz","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T10:24:08Z","title":"MameLoshnLM: Yiddish Language Model and Evaluation Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05850","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":"sha256:43fc540956ae88b93b814ca6a79221acd83c66c2a36ec87e560006faca9d2354","target":"record","created_at":"2026-08-07T00:52:55Z","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":"65646a75ce36a2682aa4a967065a74a031d4a020833e758b9bcb6f3d544451de","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T10:24:08Z","title_canon_sha256":"2fa70477d6c2f5484697b20e5a16a1270ba0d3dd262af4b7cd199ee0e033cd11"},"schema_version":"1.0","source":{"id":"2608.05850","kind":"arxiv","version":1}},"canonical_sha256":"068da2a1daa03717a7d711f09f728e3e9925124f3347c403beab64a123a7ea07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"068da2a1daa03717a7d711f09f728e3e9925124f3347c403beab64a123a7ea07","first_computed_at":"2026-08-07T00:52:55.785038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:52:55.785038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kb4nh+0Ei0O/WkQNXVThwwiUAcxqGKJ9qR8La1UYDLbMDEKo97FqpaaZa+xcII+TusvHL7zAsubJLqCqzwAPCw==","signature_status":"signed_v1","signed_at":"2026-08-07T00:52:55.786490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05850","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43fc540956ae88b93b814ca6a79221acd83c66c2a36ec87e560006faca9d2354","sha256:922b89e126263971dadc9a935dce23d3af32d794c3102cfb093c301e94087f58","sha256:7afe51452673d1666f443ed72cc9a650cf5d3834771f24ff586ed37ce9a36f59"],"state_sha256":"85d211df9b621f89c9e2ea5b25db65e8493d6af9745e1157b61c089a77d1a568"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Krtv8+FfVPYAwMniil+YOrJnRJ1Pu/AkFtWBU0rYJceC/hWrAIkhN44XhZpQFqYPTfFw9JAC83lp+18h90SBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:34:33.021549Z","bundle_sha256":"bbbb5e2d3f8fed651e9ca7c8a38c6e28a7794eb1e10ae682290293364977ed8e"}}