{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JEEE7YFM6VT2MR7LIMT6RHRU46","short_pith_number":"pith:JEEE7YFM","canonical_record":{"source":{"id":"2305.13641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T03:19:21Z","cross_cats_sorted":[],"title_canon_sha256":"196d46bd767fdeb216e61616f93cc11d424e4dee846b70710072ff008c46892d","abstract_canon_sha256":"41f33b441081c2633126b888034bf53efa524d6b661e73170c848324212fe549"},"schema_version":"1.0"},"canonical_sha256":"49084fe0acf567a647eb4327e89e34e78cac225fb1fbf41b0d7b08f36b58e2ad","source":{"kind":"arxiv","id":"2305.13641","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13641","created_at":"2026-07-05T06:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13641v1","created_at":"2026-07-05T06:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13641","created_at":"2026-07-05T06:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"JEEE7YFM6VT2","created_at":"2026-07-05T06:12:55Z"},{"alias_kind":"pith_short_16","alias_value":"JEEE7YFM6VT2MR7L","created_at":"2026-07-05T06:12:55Z"},{"alias_kind":"pith_short_8","alias_value":"JEEE7YFM","created_at":"2026-07-05T06:12:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JEEE7YFM6VT2MR7LIMT6RHRU46","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T03:19:21Z","cross_cats_sorted":[],"title_canon_sha256":"196d46bd767fdeb216e61616f93cc11d424e4dee846b70710072ff008c46892d","abstract_canon_sha256":"41f33b441081c2633126b888034bf53efa524d6b661e73170c848324212fe549"},"schema_version":"1.0"},"canonical_sha256":"49084fe0acf567a647eb4327e89e34e78cac225fb1fbf41b0d7b08f36b58e2ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:55.441490Z","signature_b64":"SDPCPqqunR6KbDJq81PE4aVi/OQ8XMvmiIjqvtvEyblIGSjLTj5z+USZbGm4kcJT+savEcSck43BD/c6VRP6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49084fe0acf567a647eb4327e89e34e78cac225fb1fbf41b0d7b08f36b58e2ad","last_reissued_at":"2026-07-05T06:12:55.440969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:55.440969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13641","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":"2026-07-05T06:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6kCN3nIMEae9RyzVCF1BW8WYpiiudYf6nK5JCP7Tsq1Drj2TVqetigFD2rUxl3JREx5UwcZKBhLjuk3Hn/rADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:34:47.611368Z"},"content_sha256":"6810582b3978509ccafa66ed95d63189b48f320334e339bd1d615a57789e089f","schema_version":"1.0","event_id":"sha256:6810582b3978509ccafa66ed95d63189b48f320334e339bd1d615a57789e089f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JEEE7YFM6VT2MR7LIMT6RHRU46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhijnan Nath, Nikhil Krishnaswamy, Sheikh Mannan","submitted_at":"2023-05-23T03:19:21Z","abstract_excerpt":"Despite their successes in NLP, Transformer-based language models still require extensive computing resources and suffer in low-resource or low-compute settings. In this paper, we present AxomiyaBERTa, a novel BERT model for Assamese, a morphologically-rich low-resource language (LRL) of Eastern India. AxomiyaBERTa is trained only on the masked language modeling (MLM) task, without the typical additional next sentence prediction (NSP) objective, and our results show that in resource-scarce settings for very low-resource languages like Assamese, MLM alone can be successfully leveraged for a ran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13641","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/2305.13641/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":"2026-07-05T06:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Puun6SRZ8+qgv9MV2phttMTWs3S6D1+gWYpDPYEBOeNLBVe9PE1Q2iIJIKhH4HJU2fEEjauqMdNwfV/Dg6e6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:34:47.611847Z"},"content_sha256":"701cda9c7dffcc6dc1a61585f5c1eb69f780337b87a69f605b8893aca91c6a34","schema_version":"1.0","event_id":"sha256:701cda9c7dffcc6dc1a61585f5c1eb69f780337b87a69f605b8893aca91c6a34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JEEE7YFM6VT2MR7LIMT6RHRU46/bundle.json","state_url":"https://pith.science/pith/JEEE7YFM6VT2MR7LIMT6RHRU46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JEEE7YFM6VT2MR7LIMT6RHRU46/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":"2026-08-15T00:34:47Z","links":{"resolver":"https://pith.science/pith/JEEE7YFM6VT2MR7LIMT6RHRU46","bundle":"https://pith.science/pith/JEEE7YFM6VT2MR7LIMT6RHRU46/bundle.json","state":"https://pith.science/pith/JEEE7YFM6VT2MR7LIMT6RHRU46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JEEE7YFM6VT2MR7LIMT6RHRU46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JEEE7YFM6VT2MR7LIMT6RHRU46","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":"41f33b441081c2633126b888034bf53efa524d6b661e73170c848324212fe549","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T03:19:21Z","title_canon_sha256":"196d46bd767fdeb216e61616f93cc11d424e4dee846b70710072ff008c46892d"},"schema_version":"1.0","source":{"id":"2305.13641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13641","created_at":"2026-07-05T06:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13641v1","created_at":"2026-07-05T06:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13641","created_at":"2026-07-05T06:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"JEEE7YFM6VT2","created_at":"2026-07-05T06:12:55Z"},{"alias_kind":"pith_short_16","alias_value":"JEEE7YFM6VT2MR7L","created_at":"2026-07-05T06:12:55Z"},{"alias_kind":"pith_short_8","alias_value":"JEEE7YFM","created_at":"2026-07-05T06:12:55Z"}],"graph_snapshots":[{"event_id":"sha256:701cda9c7dffcc6dc1a61585f5c1eb69f780337b87a69f605b8893aca91c6a34","target":"graph","created_at":"2026-07-05T06:12:55Z","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/2305.13641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their successes in NLP, Transformer-based language models still require extensive computing resources and suffer in low-resource or low-compute settings. In this paper, we present AxomiyaBERTa, a novel BERT model for Assamese, a morphologically-rich low-resource language (LRL) of Eastern India. AxomiyaBERTa is trained only on the masked language modeling (MLM) task, without the typical additional next sentence prediction (NSP) objective, and our results show that in resource-scarce settings for very low-resource languages like Assamese, MLM alone can be successfully leveraged for a ran","authors_text":"Abhijnan Nath, Nikhil Krishnaswamy, Sheikh Mannan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T03:19:21Z","title":"AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13641","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":"sha256:6810582b3978509ccafa66ed95d63189b48f320334e339bd1d615a57789e089f","target":"record","created_at":"2026-07-05T06:12:55Z","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":"41f33b441081c2633126b888034bf53efa524d6b661e73170c848324212fe549","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T03:19:21Z","title_canon_sha256":"196d46bd767fdeb216e61616f93cc11d424e4dee846b70710072ff008c46892d"},"schema_version":"1.0","source":{"id":"2305.13641","kind":"arxiv","version":1}},"canonical_sha256":"49084fe0acf567a647eb4327e89e34e78cac225fb1fbf41b0d7b08f36b58e2ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49084fe0acf567a647eb4327e89e34e78cac225fb1fbf41b0d7b08f36b58e2ad","first_computed_at":"2026-07-05T06:12:55.440969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:55.440969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SDPCPqqunR6KbDJq81PE4aVi/OQ8XMvmiIjqvtvEyblIGSjLTj5z+USZbGm4kcJT+savEcSck43BD/c6VRP6Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:55.441490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6810582b3978509ccafa66ed95d63189b48f320334e339bd1d615a57789e089f","sha256:701cda9c7dffcc6dc1a61585f5c1eb69f780337b87a69f605b8893aca91c6a34"],"state_sha256":"aa0eaca46d6a58ce8586bbf7b40202cfd3ff018096aea179d710807edb5031b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+UEu1RD7Ckmw2b/8Mf7i10Yey3VZX4qbs6GrhU5xMH2UO1bklK6/Iz0weOkd7w44AWzDVs80BNvUEDKO9OUqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T00:34:47.615302Z","bundle_sha256":"0d156b622fc529c1097e56c706807fd9d3a36d7ee4acbafecb3eedebc2ebe1d5"}}