{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HIML4IUWPZ2UZKGOLUJA6UDDZG","short_pith_number":"pith:HIML4IUW","canonical_record":{"source":{"id":"2509.09101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T02:25:49Z","cross_cats_sorted":[],"title_canon_sha256":"32182621459a05180c090d3e78af297f9c064a12ffd030c1127fca2ae56b87f3","abstract_canon_sha256":"4ca3a76d4ffa593adb05c9892eac720385da9760e1e212b05f784dbc009df054"},"schema_version":"1.0"},"canonical_sha256":"3a18be22967e754ca8ce5d120f5063c999e5c3b3dcf21a2f3df3137159c4f296","source":{"kind":"arxiv","id":"2509.09101","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09101","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09101v1","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09101","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"HIML4IUWPZ2U","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"HIML4IUWPZ2UZKGO","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"HIML4IUW","created_at":"2026-07-05T12:09:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HIML4IUWPZ2UZKGOLUJA6UDDZG","target":"record","payload":{"canonical_record":{"source":{"id":"2509.09101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T02:25:49Z","cross_cats_sorted":[],"title_canon_sha256":"32182621459a05180c090d3e78af297f9c064a12ffd030c1127fca2ae56b87f3","abstract_canon_sha256":"4ca3a76d4ffa593adb05c9892eac720385da9760e1e212b05f784dbc009df054"},"schema_version":"1.0"},"canonical_sha256":"3a18be22967e754ca8ce5d120f5063c999e5c3b3dcf21a2f3df3137159c4f296","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:29.399063Z","signature_b64":"82MYTlhpNFV33lRmtBOyX60TcQfYD/NRQIdS26QSI/myPE0fjWfI9HJBVOhonUoyMHom24YHinZEUXrOv/34Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a18be22967e754ca8ce5d120f5063c999e5c3b3dcf21a2f3df3137159c4f296","last_reissued_at":"2026-07-05T12:09:29.398569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:29.398569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.09101","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":"2026-07-05T12:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x0v1uVjJcHgesiOyO4J83fRQyJIrSirGRiXysr0yuoQU3PvadbcHcPLpqBjlfedEN13eeGl+tQK+OXpogvG5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:16:00.674306Z"},"content_sha256":"27936c7f01964675b7d6a1ad74514ad550b6806348268990d65a7a5a6eabed77","schema_version":"1.0","event_id":"sha256:27936c7f01964675b7d6a1ad74514ad550b6806348268990d65a7a5a6eabed77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HIML4IUWPZ2UZKGOLUJA6UDDZG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Marcos Zampieri, Nishat Raihan","submitted_at":"2025-09-11T02:25:49Z","abstract_excerpt":"Despite being the 5th most spoken language, Bangla remains underrepresented in Large Language Models (LLMs), particularly for code generation. This primarily stems from the scarcity of high-quality data to pre-train and/or finetune such models. Hence, we introduce the first dedicated family of Code LLMs for Bangla (1B & 9B). We offer three major contributions: (1) a comprehensive Bangla code instruction datasets for programming domain adaptation; (2) MBPP-Bangla, an evaluation benchmark for Bangla code generation; and (3) the TigerCoder-family of Code LLMs, achieving significant ~11-18% perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09101","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/2509.09101/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":"2026-07-05T12:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h3roV0JB2EdwjJvioCkfV2DcPPUqT78ScZtW6LmVo3cKcWtBlJ8kOJa6P/+fH/hLokUBHAqXhCl4kOjxeSXdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:16:00.674640Z"},"content_sha256":"2bca7331f0ec4f00d9628439b2f971b684af0304f65950256e50553b4962bf0c","schema_version":"1.0","event_id":"sha256:2bca7331f0ec4f00d9628439b2f971b684af0304f65950256e50553b4962bf0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HIML4IUWPZ2UZKGOLUJA6UDDZG/bundle.json","state_url":"https://pith.science/pith/HIML4IUWPZ2UZKGOLUJA6UDDZG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HIML4IUWPZ2UZKGOLUJA6UDDZG/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":"2026-08-05T12:16:00Z","links":{"resolver":"https://pith.science/pith/HIML4IUWPZ2UZKGOLUJA6UDDZG","bundle":"https://pith.science/pith/HIML4IUWPZ2UZKGOLUJA6UDDZG/bundle.json","state":"https://pith.science/pith/HIML4IUWPZ2UZKGOLUJA6UDDZG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HIML4IUWPZ2UZKGOLUJA6UDDZG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HIML4IUWPZ2UZKGOLUJA6UDDZG","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":"4ca3a76d4ffa593adb05c9892eac720385da9760e1e212b05f784dbc009df054","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T02:25:49Z","title_canon_sha256":"32182621459a05180c090d3e78af297f9c064a12ffd030c1127fca2ae56b87f3"},"schema_version":"1.0","source":{"id":"2509.09101","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09101","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09101v1","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09101","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"HIML4IUWPZ2U","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"HIML4IUWPZ2UZKGO","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"HIML4IUW","created_at":"2026-07-05T12:09:29Z"}],"graph_snapshots":[{"event_id":"sha256:2bca7331f0ec4f00d9628439b2f971b684af0304f65950256e50553b4962bf0c","target":"graph","created_at":"2026-07-05T12:09:29Z","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/2509.09101/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite being the 5th most spoken language, Bangla remains underrepresented in Large Language Models (LLMs), particularly for code generation. This primarily stems from the scarcity of high-quality data to pre-train and/or finetune such models. Hence, we introduce the first dedicated family of Code LLMs for Bangla (1B & 9B). We offer three major contributions: (1) a comprehensive Bangla code instruction datasets for programming domain adaptation; (2) MBPP-Bangla, an evaluation benchmark for Bangla code generation; and (3) the TigerCoder-family of Code LLMs, achieving significant ~11-18% perfor","authors_text":"Antonios Anastasopoulos, Marcos Zampieri, Nishat Raihan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T02:25:49Z","title":"TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09101","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":"sha256:27936c7f01964675b7d6a1ad74514ad550b6806348268990d65a7a5a6eabed77","target":"record","created_at":"2026-07-05T12:09:29Z","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":"4ca3a76d4ffa593adb05c9892eac720385da9760e1e212b05f784dbc009df054","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T02:25:49Z","title_canon_sha256":"32182621459a05180c090d3e78af297f9c064a12ffd030c1127fca2ae56b87f3"},"schema_version":"1.0","source":{"id":"2509.09101","kind":"arxiv","version":1}},"canonical_sha256":"3a18be22967e754ca8ce5d120f5063c999e5c3b3dcf21a2f3df3137159c4f296","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a18be22967e754ca8ce5d120f5063c999e5c3b3dcf21a2f3df3137159c4f296","first_computed_at":"2026-07-05T12:09:29.398569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:29.398569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"82MYTlhpNFV33lRmtBOyX60TcQfYD/NRQIdS26QSI/myPE0fjWfI9HJBVOhonUoyMHom24YHinZEUXrOv/34Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:29.399063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09101","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27936c7f01964675b7d6a1ad74514ad550b6806348268990d65a7a5a6eabed77","sha256:2bca7331f0ec4f00d9628439b2f971b684af0304f65950256e50553b4962bf0c"],"state_sha256":"1a06efeb0e728612344f726be782844e8579529610dab082cb9895771b69714c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V3s+E4fRe5wPFWNW2FHY0tu0bko+Bp84k6ZFdPvfykhwkbSmrJwYPECufcsbE23JMogDZLo1ETCVlDRk3WGoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:16:00.677675Z","bundle_sha256":"a697413c90d3681270c6d1aab3e3d6272d966318bc7f8a6b413d3abe741dc6a0"}}