{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YLH57M47S4O5ANWTXEVSMMVQ4M","short_pith_number":"pith:YLH57M47","canonical_record":{"source":{"id":"2101.00204","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T09:28:45Z","cross_cats_sorted":[],"title_canon_sha256":"6efb2868193f967358c15290b45c97b370b3eab7b765f1435e39b3ba71a3ed22","abstract_canon_sha256":"70aef5491f4dd678905c2fce7b7e619b234e0277cf3cabca3a55c891110e8820"},"schema_version":"1.0"},"canonical_sha256":"c2cfdfb39f971dd036d3b92b2632b0e33a0751e3f82840a89c8a2e3cad3232c1","source":{"kind":"arxiv","id":"2101.00204","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00204","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00204v4","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00204","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"YLH57M47S4O5","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"YLH57M47S4O5ANWT","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"YLH57M47","created_at":"2026-07-05T04:21:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YLH57M47S4O5ANWTXEVSMMVQ4M","target":"record","payload":{"canonical_record":{"source":{"id":"2101.00204","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T09:28:45Z","cross_cats_sorted":[],"title_canon_sha256":"6efb2868193f967358c15290b45c97b370b3eab7b765f1435e39b3ba71a3ed22","abstract_canon_sha256":"70aef5491f4dd678905c2fce7b7e619b234e0277cf3cabca3a55c891110e8820"},"schema_version":"1.0"},"canonical_sha256":"c2cfdfb39f971dd036d3b92b2632b0e33a0751e3f82840a89c8a2e3cad3232c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:44.323349Z","signature_b64":"TZFG4Mf+nbR51SHTrTCXA0g007s2N+fuoEQEOTtVFEhxHWRXawEcoF0xOLZ20qsEK0KSAOCtmCkAODUq5w8FCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2cfdfb39f971dd036d3b92b2632b0e33a0751e3f82840a89c8a2e3cad3232c1","last_reissued_at":"2026-07-05T04:21:44.322850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:44.322850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.00204","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:21:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0bCRnPtV6gSV+xwyCxtWPQohfpolvz6OkwVQdtwwMk2olGKmjWxfNpjoTYPQFNSrbHHChPF2CjpaCJEqmHHODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:17:47.596948Z"},"content_sha256":"12ffe458bb50fc867341d0eb2a3c92eeb6f3664f9f82488670e08f044819e486","schema_version":"1.0","event_id":"sha256:12ffe458bb50fc867341d0eb2a3c92eeb6f3664f9f82488670e08f044819e486"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YLH57M47S4O5ANWTXEVSMMVQ4M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhik Bhattacharjee, Anindya Iqbal, Kazi Samin, Md Saiful Islam, M. Sohel Rahman, Rifat Shahriyar, Tahmid Hasan, Wasi Uddin Ahmad","submitted_at":"2021-01-01T09:28:45Z","abstract_excerpt":"In this work, we introduce BanglaBERT, a BERT-based Natural Language Understanding (NLU) model pretrained in Bangla, a widely spoken yet low-resource language in the NLP literature. To pretrain BanglaBERT, we collect 27.5 GB of Bangla pretraining data (dubbed `Bangla2B+') by crawling 110 popular Bangla sites. We introduce two downstream task datasets on natural language inference and question answering and benchmark on four diverse NLU tasks covering text classification, sequence labeling, and span prediction. In the process, we bring them under the first-ever Bangla Language Understanding Ben"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00204","kind":"arxiv","version":4},"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/2101.00204/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":"2026-07-05T04:21:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0evF4LUreL8ZrRwWxr5qRJR6QgYQ21Q0ahGNV/XYQZNjE1g/yJ1rLgZmCGvb/01J2pWmhvceTNPo7yHMksNZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:17:47.597461Z"},"content_sha256":"d0c6a25f583fa5c62be291498fd1d3eadbe8fe5895d44b6f65cf78c01cb93060","schema_version":"1.0","event_id":"sha256:d0c6a25f583fa5c62be291498fd1d3eadbe8fe5895d44b6f65cf78c01cb93060"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLH57M47S4O5ANWTXEVSMMVQ4M/bundle.json","state_url":"https://pith.science/pith/YLH57M47S4O5ANWTXEVSMMVQ4M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLH57M47S4O5ANWTXEVSMMVQ4M/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":"2026-08-22T09:17:47Z","links":{"resolver":"https://pith.science/pith/YLH57M47S4O5ANWTXEVSMMVQ4M","bundle":"https://pith.science/pith/YLH57M47S4O5ANWTXEVSMMVQ4M/bundle.json","state":"https://pith.science/pith/YLH57M47S4O5ANWTXEVSMMVQ4M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLH57M47S4O5ANWTXEVSMMVQ4M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YLH57M47S4O5ANWTXEVSMMVQ4M","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":"70aef5491f4dd678905c2fce7b7e619b234e0277cf3cabca3a55c891110e8820","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T09:28:45Z","title_canon_sha256":"6efb2868193f967358c15290b45c97b370b3eab7b765f1435e39b3ba71a3ed22"},"schema_version":"1.0","source":{"id":"2101.00204","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00204","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00204v4","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00204","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"YLH57M47S4O5","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"YLH57M47S4O5ANWT","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"YLH57M47","created_at":"2026-07-05T04:21:44Z"}],"graph_snapshots":[{"event_id":"sha256:d0c6a25f583fa5c62be291498fd1d3eadbe8fe5895d44b6f65cf78c01cb93060","target":"graph","created_at":"2026-07-05T04:21:44Z","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/2101.00204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we introduce BanglaBERT, a BERT-based Natural Language Understanding (NLU) model pretrained in Bangla, a widely spoken yet low-resource language in the NLP literature. To pretrain BanglaBERT, we collect 27.5 GB of Bangla pretraining data (dubbed `Bangla2B+') by crawling 110 popular Bangla sites. We introduce two downstream task datasets on natural language inference and question answering and benchmark on four diverse NLU tasks covering text classification, sequence labeling, and span prediction. In the process, we bring them under the first-ever Bangla Language Understanding Ben","authors_text":"Abhik Bhattacharjee, Anindya Iqbal, Kazi Samin, Md Saiful Islam, M. Sohel Rahman, Rifat Shahriyar, Tahmid Hasan, Wasi Uddin Ahmad","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T09:28:45Z","title":"BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00204","kind":"arxiv","version":4},"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":"sha256:12ffe458bb50fc867341d0eb2a3c92eeb6f3664f9f82488670e08f044819e486","target":"record","created_at":"2026-07-05T04:21:44Z","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":"70aef5491f4dd678905c2fce7b7e619b234e0277cf3cabca3a55c891110e8820","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T09:28:45Z","title_canon_sha256":"6efb2868193f967358c15290b45c97b370b3eab7b765f1435e39b3ba71a3ed22"},"schema_version":"1.0","source":{"id":"2101.00204","kind":"arxiv","version":4}},"canonical_sha256":"c2cfdfb39f971dd036d3b92b2632b0e33a0751e3f82840a89c8a2e3cad3232c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2cfdfb39f971dd036d3b92b2632b0e33a0751e3f82840a89c8a2e3cad3232c1","first_computed_at":"2026-07-05T04:21:44.322850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:21:44.322850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TZFG4Mf+nbR51SHTrTCXA0g007s2N+fuoEQEOTtVFEhxHWRXawEcoF0xOLZ20qsEK0KSAOCtmCkAODUq5w8FCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:21:44.323349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.00204","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12ffe458bb50fc867341d0eb2a3c92eeb6f3664f9f82488670e08f044819e486","sha256:d0c6a25f583fa5c62be291498fd1d3eadbe8fe5895d44b6f65cf78c01cb93060"],"state_sha256":"4142bb471baae56f0600fe7e7d8c98393d1264b86afccc9fcbc338fa8768cb3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BbYGm/8Lg0BnVKJWZS2AWpwMK96b0QqoQfviMMcSzXDnw0WAIgmBraYLcWlFsRpctSa47g3OydaYYhWyYCWPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T09:17:47.601213Z","bundle_sha256":"366194fd10a31ee2601a4d278f5afeed983d5bb0f25f0c0927128cddcd0a1365"}}