{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RSDZJK23UIFVEF5U5ZVSX3KSHT","short_pith_number":"pith:RSDZJK23","canonical_record":{"source":{"id":"2410.06898","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T13:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"a9e95c4cd497e872f3b9bfdfaa2d9edfc5205b60520db45159f81b191a56c044","abstract_canon_sha256":"5db84301b311358f807a3a35b719d291977834838a8e60e97e661fe786110379"},"schema_version":"1.0"},"canonical_sha256":"8c8794ab5ba20b5217b4ee6b2bed523cc4d72fef741b83d2b546e20f1359ec17","source":{"kind":"arxiv","id":"2410.06898","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06898","created_at":"2026-07-05T09:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06898v1","created_at":"2026-07-05T09:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06898","created_at":"2026-07-05T09:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"RSDZJK23UIFV","created_at":"2026-07-05T09:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"RSDZJK23UIFVEF5U","created_at":"2026-07-05T09:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"RSDZJK23","created_at":"2026-07-05T09:18:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RSDZJK23UIFVEF5U5ZVSX3KSHT","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06898","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T13:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"a9e95c4cd497e872f3b9bfdfaa2d9edfc5205b60520db45159f81b191a56c044","abstract_canon_sha256":"5db84301b311358f807a3a35b719d291977834838a8e60e97e661fe786110379"},"schema_version":"1.0"},"canonical_sha256":"8c8794ab5ba20b5217b4ee6b2bed523cc4d72fef741b83d2b546e20f1359ec17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:08.352193Z","signature_b64":"JJF00Y3idJdoObASHraDH4zqD+D/XB0GrHfsX+cg4TDcHu2oS15QY6L8f3MGXiK1Xyp+tvgnf+zrnPbPiTknAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c8794ab5ba20b5217b4ee6b2bed523cc4d72fef741b83d2b546e20f1359ec17","last_reissued_at":"2026-07-05T09:18:08.351633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:08.351633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06898","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":"2026-07-05T09:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOsCVZv6U6aDYGetOfdBubU3fcQR9zHnaVkUewpKzD1EuZzT9HlG4vk1vInqovYF9kZLQEh+DCWbhAemsrtwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:27.054740Z"},"content_sha256":"496e97487c09c7b78c01b9c03a7fdcd6392b24ed5d7810935d274320ba54ca14","schema_version":"1.0","event_id":"sha256:496e97487c09c7b78c01b9c03a7fdcd6392b24ed5d7810935d274320ba54ca14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RSDZJK23UIFVEF5U5ZVSX3KSHT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Model for Less-Resourced Language with 1 billion parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alja\\v{z} Poto\\v{c}nik, Domen Vre\\v{s}, Marko Robnik-\\v{S}ikonja, Martin Bo\\v{z}i\\v{c}, Toma\\v{z} Martin\\v{c}i\\v{c}","submitted_at":"2024-10-09T13:59:34Z","abstract_excerpt":"Large language models (LLMs) are a basic infrastructure for modern natural language processing. Many commercial and open-source LLMs exist for English, e.g., ChatGPT, Llama, Falcon, and Mistral. As these models are trained on mostly English texts, their fluency and knowledge of low-resource languages and societies are superficial. We present the development of large generative language models for a less-resourced language. GaMS 1B - Generative Model for Slovene with 1 billion parameters was created by continuing pretraining of the existing English OPT model. We developed a new tokenizer adapte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06898","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/2410.06898/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":"2026-07-05T09:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7g+mu6ymMuFakIYv8MKQKmR1WYpf1L5YaATlP84iH4EYITm+Vx2/ZKXhMujE44GdJtbrJ8XBPUS6IbYxL8/6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:27.055266Z"},"content_sha256":"455db9725123bf33d4c7b0b885d108e1883ad48f59d7e3a69021285d38d17601","schema_version":"1.0","event_id":"sha256:455db9725123bf33d4c7b0b885d108e1883ad48f59d7e3a69021285d38d17601"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RSDZJK23UIFVEF5U5ZVSX3KSHT/bundle.json","state_url":"https://pith.science/pith/RSDZJK23UIFVEF5U5ZVSX3KSHT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RSDZJK23UIFVEF5U5ZVSX3KSHT/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":"2026-08-08T13:57:27Z","links":{"resolver":"https://pith.science/pith/RSDZJK23UIFVEF5U5ZVSX3KSHT","bundle":"https://pith.science/pith/RSDZJK23UIFVEF5U5ZVSX3KSHT/bundle.json","state":"https://pith.science/pith/RSDZJK23UIFVEF5U5ZVSX3KSHT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RSDZJK23UIFVEF5U5ZVSX3KSHT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RSDZJK23UIFVEF5U5ZVSX3KSHT","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":"5db84301b311358f807a3a35b719d291977834838a8e60e97e661fe786110379","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T13:59:34Z","title_canon_sha256":"a9e95c4cd497e872f3b9bfdfaa2d9edfc5205b60520db45159f81b191a56c044"},"schema_version":"1.0","source":{"id":"2410.06898","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06898","created_at":"2026-07-05T09:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06898v1","created_at":"2026-07-05T09:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06898","created_at":"2026-07-05T09:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"RSDZJK23UIFV","created_at":"2026-07-05T09:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"RSDZJK23UIFVEF5U","created_at":"2026-07-05T09:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"RSDZJK23","created_at":"2026-07-05T09:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:455db9725123bf33d4c7b0b885d108e1883ad48f59d7e3a69021285d38d17601","target":"graph","created_at":"2026-07-05T09:18:08Z","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/2410.06898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are a basic infrastructure for modern natural language processing. Many commercial and open-source LLMs exist for English, e.g., ChatGPT, Llama, Falcon, and Mistral. As these models are trained on mostly English texts, their fluency and knowledge of low-resource languages and societies are superficial. We present the development of large generative language models for a less-resourced language. GaMS 1B - Generative Model for Slovene with 1 billion parameters was created by continuing pretraining of the existing English OPT model. We developed a new tokenizer adapte","authors_text":"Alja\\v{z} Poto\\v{c}nik, Domen Vre\\v{s}, Marko Robnik-\\v{S}ikonja, Martin Bo\\v{z}i\\v{c}, Toma\\v{z} Martin\\v{c}i\\v{c}","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T13:59:34Z","title":"Generative Model for Less-Resourced Language with 1 billion parameters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06898","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":"sha256:496e97487c09c7b78c01b9c03a7fdcd6392b24ed5d7810935d274320ba54ca14","target":"record","created_at":"2026-07-05T09:18:08Z","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":"5db84301b311358f807a3a35b719d291977834838a8e60e97e661fe786110379","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T13:59:34Z","title_canon_sha256":"a9e95c4cd497e872f3b9bfdfaa2d9edfc5205b60520db45159f81b191a56c044"},"schema_version":"1.0","source":{"id":"2410.06898","kind":"arxiv","version":1}},"canonical_sha256":"8c8794ab5ba20b5217b4ee6b2bed523cc4d72fef741b83d2b546e20f1359ec17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c8794ab5ba20b5217b4ee6b2bed523cc4d72fef741b83d2b546e20f1359ec17","first_computed_at":"2026-07-05T09:18:08.351633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:08.351633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JJF00Y3idJdoObASHraDH4zqD+D/XB0GrHfsX+cg4TDcHu2oS15QY6L8f3MGXiK1Xyp+tvgnf+zrnPbPiTknAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:08.352193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06898","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:496e97487c09c7b78c01b9c03a7fdcd6392b24ed5d7810935d274320ba54ca14","sha256:455db9725123bf33d4c7b0b885d108e1883ad48f59d7e3a69021285d38d17601"],"state_sha256":"72e1ef17efe0075165f6e1c5211484dca8097eedfb19972aef89189186c9d711"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x73UIs92K6TNkeZMZdPCcJ2tWqcHFTkXdo1+VH0bWB4swgOWnSjuQNwwMwPepmbVPIzrz2r+efVwiep9tZP4Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:57:27.059028Z","bundle_sha256":"4fdc97a726b5c30218a82526cfbd8054e38139634a54f75e740143f091888dbb"}}