{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ICLBZFD3JYU4GFPFURSVT3WWPL","short_pith_number":"pith:ICLBZFD3","canonical_record":{"source":{"id":"2502.11187","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T16:22:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae5c6690291b985a9e7559929ca46739ff4a9fe9209f686883d495ba7a347345","abstract_canon_sha256":"04eec8cd62ab3339df14955d7d8f7d0400f4f8ddfba2d6f00072a9c779410cf3"},"schema_version":"1.0"},"canonical_sha256":"40961c947b4e29c315e5a46559eed67ae8246eab59ef025ee901e07b11a30464","source":{"kind":"arxiv","id":"2502.11187","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11187","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11187v3","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11187","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"ICLBZFD3JYU4","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"ICLBZFD3JYU4GFPF","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"ICLBZFD3","created_at":"2026-07-05T11:16:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ICLBZFD3JYU4GFPFURSVT3WWPL","target":"record","payload":{"canonical_record":{"source":{"id":"2502.11187","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T16:22:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae5c6690291b985a9e7559929ca46739ff4a9fe9209f686883d495ba7a347345","abstract_canon_sha256":"04eec8cd62ab3339df14955d7d8f7d0400f4f8ddfba2d6f00072a9c779410cf3"},"schema_version":"1.0"},"canonical_sha256":"40961c947b4e29c315e5a46559eed67ae8246eab59ef025ee901e07b11a30464","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:55.100519Z","signature_b64":"BV1AbAys0zUr2w+z3nfsYCGYayLowKefymO4uiXS7ZI/BigwaaLBD/RGTe2cEoAU3LwxYq8eQW0q3nEoH63hCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40961c947b4e29c315e5a46559eed67ae8246eab59ef025ee901e07b11a30464","last_reissued_at":"2026-07-05T11:16:55.099940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:55.099940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.11187","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Av7a21xZuGOFok7E62zZMNewsV/d/WQOIoLMK6faZMj/vLCawcoSsYKCtIid4dhnIzttseiODJkSZtIdWGzhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T06:59:01.405307Z"},"content_sha256":"8f822a1b2ab81bb222ea32bdc330c30b216fb682c04c8486c9747cc0a12eccb9","schema_version":"1.0","event_id":"sha256:8f822a1b2ab81bb222ea32bdc330c30b216fb682c04c8486c9747cc0a12eccb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ICLBZFD3JYU4GFPFURSVT3WWPL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Apu Chandraw Shill, Firoj Alam, Md Ibrahim, Md Kowsher, Mehadi Hasan Menon, Quazi Sarwar Muhtaseem, Rabindra Nath Nandi, Sagor Sarker, Shahriar Kabir Nahin, Tareq Al Muntasir","submitted_at":"2025-02-16T16:22:23Z","abstract_excerpt":"In this paper, we present TituLLMs, the first large pretrained Bangla LLMs, available in 1b and 3b parameter sizes. Due to computational constraints during both training and inference, we focused on smaller models. To train TituLLMs, we collected a pretraining dataset of approximately ~37 billion tokens. We extended the Llama-3.2 tokenizer to incorporate language- and culture-specific knowledge, which also enables faster training and inference. There was a lack of benchmarking datasets to benchmark LLMs for Bangla. To address this gap, we developed five benchmarking datasets. We benchmarked va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11187","kind":"arxiv","version":3},"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/2502.11187/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":"2026-07-05T11:16:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SSavdaXnVdH7B1rn7WRyVt7CvxqpEOjBVcQ7MrYvKt9zuQLOWEG14iP5kOjI6y8ifl5Ce9iDmvqzEZSfMm/CAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T06:59:01.405702Z"},"content_sha256":"01843082eea82f093bab3a4777d16fd416c4e8c12c3bae5464cefd71ce6d3029","schema_version":"1.0","event_id":"sha256:01843082eea82f093bab3a4777d16fd416c4e8c12c3bae5464cefd71ce6d3029"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICLBZFD3JYU4GFPFURSVT3WWPL/bundle.json","state_url":"https://pith.science/pith/ICLBZFD3JYU4GFPFURSVT3WWPL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICLBZFD3JYU4GFPFURSVT3WWPL/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":"2026-07-10T06:59:01Z","links":{"resolver":"https://pith.science/pith/ICLBZFD3JYU4GFPFURSVT3WWPL","bundle":"https://pith.science/pith/ICLBZFD3JYU4GFPFURSVT3WWPL/bundle.json","state":"https://pith.science/pith/ICLBZFD3JYU4GFPFURSVT3WWPL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICLBZFD3JYU4GFPFURSVT3WWPL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ICLBZFD3JYU4GFPFURSVT3WWPL","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":"04eec8cd62ab3339df14955d7d8f7d0400f4f8ddfba2d6f00072a9c779410cf3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T16:22:23Z","title_canon_sha256":"ae5c6690291b985a9e7559929ca46739ff4a9fe9209f686883d495ba7a347345"},"schema_version":"1.0","source":{"id":"2502.11187","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11187","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11187v3","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11187","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"ICLBZFD3JYU4","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"ICLBZFD3JYU4GFPF","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"ICLBZFD3","created_at":"2026-07-05T11:16:55Z"}],"graph_snapshots":[{"event_id":"sha256:01843082eea82f093bab3a4777d16fd416c4e8c12c3bae5464cefd71ce6d3029","target":"graph","created_at":"2026-07-05T11:16:55Z","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/2502.11187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present TituLLMs, the first large pretrained Bangla LLMs, available in 1b and 3b parameter sizes. Due to computational constraints during both training and inference, we focused on smaller models. To train TituLLMs, we collected a pretraining dataset of approximately ~37 billion tokens. We extended the Llama-3.2 tokenizer to incorporate language- and culture-specific knowledge, which also enables faster training and inference. There was a lack of benchmarking datasets to benchmark LLMs for Bangla. To address this gap, we developed five benchmarking datasets. We benchmarked va","authors_text":"Apu Chandraw Shill, Firoj Alam, Md Ibrahim, Md Kowsher, Mehadi Hasan Menon, Quazi Sarwar Muhtaseem, Rabindra Nath Nandi, Sagor Sarker, Shahriar Kabir Nahin, Tareq Al Muntasir","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T16:22:23Z","title":"TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11187","kind":"arxiv","version":3},"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":"sha256:8f822a1b2ab81bb222ea32bdc330c30b216fb682c04c8486c9747cc0a12eccb9","target":"record","created_at":"2026-07-05T11:16:55Z","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":"04eec8cd62ab3339df14955d7d8f7d0400f4f8ddfba2d6f00072a9c779410cf3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T16:22:23Z","title_canon_sha256":"ae5c6690291b985a9e7559929ca46739ff4a9fe9209f686883d495ba7a347345"},"schema_version":"1.0","source":{"id":"2502.11187","kind":"arxiv","version":3}},"canonical_sha256":"40961c947b4e29c315e5a46559eed67ae8246eab59ef025ee901e07b11a30464","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40961c947b4e29c315e5a46559eed67ae8246eab59ef025ee901e07b11a30464","first_computed_at":"2026-07-05T11:16:55.099940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:55.099940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BV1AbAys0zUr2w+z3nfsYCGYayLowKefymO4uiXS7ZI/BigwaaLBD/RGTe2cEoAU3LwxYq8eQW0q3nEoH63hCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:55.100519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11187","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f822a1b2ab81bb222ea32bdc330c30b216fb682c04c8486c9747cc0a12eccb9","sha256:01843082eea82f093bab3a4777d16fd416c4e8c12c3bae5464cefd71ce6d3029"],"state_sha256":"84cc534b3e61f8d786d176d8dd3712a78c4a1dd9e73068205c672d957908cf66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JV64eST4rTd0WgPapyR9h3I7FQi3mn4YCHLyjN+RmVRqEK7riKtAkR0S8A9QbGCcKCt6EMdQXbtLhbKpglJOBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T06:59:01.407675Z","bundle_sha256":"fab703bcae4d40341cb8b981f6daeaf979e95b46fc21352c0a5bdd72cb81fd5c"}}