{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SL54BS7C2RNQEKXNIORQY7LIIZ","short_pith_number":"pith:SL54BS7C","canonical_record":{"source":{"id":"2607.02259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-02T14:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"7edc346582df5370c6f3e6e4b9d49b6455536c2de886d9d142134dca01c10a8a","abstract_canon_sha256":"dcdc0574ff99b563cc05bee5cca50d7b7d99a8b13ba92571eedc5b2d3ada0fab"},"schema_version":"1.0"},"canonical_sha256":"92fbc0cbe2d45b022aed43a30c7d68465123659c152d2591f39bd654a41319c2","source":{"kind":"arxiv","id":"2607.02259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02259","created_at":"2026-07-03T01:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02259v1","created_at":"2026-07-03T01:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02259","created_at":"2026-07-03T01:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"SL54BS7C2RNQ","created_at":"2026-07-03T01:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"SL54BS7C2RNQEKXN","created_at":"2026-07-03T01:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"SL54BS7C","created_at":"2026-07-03T01:17:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SL54BS7C2RNQEKXNIORQY7LIIZ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.02259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-02T14:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"7edc346582df5370c6f3e6e4b9d49b6455536c2de886d9d142134dca01c10a8a","abstract_canon_sha256":"dcdc0574ff99b563cc05bee5cca50d7b7d99a8b13ba92571eedc5b2d3ada0fab"},"schema_version":"1.0"},"canonical_sha256":"92fbc0cbe2d45b022aed43a30c7d68465123659c152d2591f39bd654a41319c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:46.818329Z","signature_b64":"08MnurusQ3OcU/fxLPwhBUrUXvmrKwixAKpFbcyHzokDT1Xq2MrqqB21OU074Hw2/+nSRyCwy2HAFasGnzmlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92fbc0cbe2d45b022aed43a30c7d68465123659c152d2591f39bd654a41319c2","last_reissued_at":"2026-07-03T01:17:46.817927Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:46.817927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.02259","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":"2026-07-03T01:17:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2N7IcitL2d2PknOYaPptSRUbMrg6grwM4aKFqljXFtkvKVaonBr3duW6DDK/M6akK4NqqMxkE5nh41yy1zKKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T19:42:12.707973Z"},"content_sha256":"0cc36d9dbc6d27c76427cac1b181813e52c164a59238adf598e3c507724a66db","schema_version":"1.0","event_id":"sha256:0cc36d9dbc6d27c76427cac1b181813e52c164a59238adf598e3c507724a66db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SL54BS7C2RNQEKXNIORQY7LIIZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BamiBERT: A New BERT-based Language Model for Vietnamese","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chi Tran, Dat Quoc Nguyen, Linh The Nguyen, Thinh Pham","submitted_at":"2026-07-02T14:46:54Z","abstract_excerpt":"In this paper, we introduce BamiBERT, a new BERT-based pre-trained language model for Vietnamese that addresses key limitations of PhoBERT -- the current de facto Vietnamese text encoder. Trained from scratch on a 129GB corpus of general-domain Vietnamese text for 20 epochs, BamiBERT supports an extended context length of up to 2048 tokens and operates directly on raw input, eliminating the need for external word segmentation. Across 8 Vietnamese benchmarks, it achieves the best score on 11 of 15 metrics and the second-best on 3 others, setting a new state of the art among \"base\"-sized Vietnam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02259","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/2607.02259/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":"2026-07-03T01:17:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M6fq9AZUF9D5i8b7O3qTz7tkOSLfLloAaOd76boxyTF+Xji9ujvSwSD78dHm843QnPGQpOw6Zf7X3zPYmkqRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T19:42:12.708334Z"},"content_sha256":"839a6a474b91020fa644019b425593e89fd377c3e53ef614cdd9f870a37be91f","schema_version":"1.0","event_id":"sha256:839a6a474b91020fa644019b425593e89fd377c3e53ef614cdd9f870a37be91f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SL54BS7C2RNQEKXNIORQY7LIIZ/bundle.json","state_url":"https://pith.science/pith/SL54BS7C2RNQEKXNIORQY7LIIZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SL54BS7C2RNQEKXNIORQY7LIIZ/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":"2026-07-04T19:42:12Z","links":{"resolver":"https://pith.science/pith/SL54BS7C2RNQEKXNIORQY7LIIZ","bundle":"https://pith.science/pith/SL54BS7C2RNQEKXNIORQY7LIIZ/bundle.json","state":"https://pith.science/pith/SL54BS7C2RNQEKXNIORQY7LIIZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SL54BS7C2RNQEKXNIORQY7LIIZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SL54BS7C2RNQEKXNIORQY7LIIZ","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":"dcdc0574ff99b563cc05bee5cca50d7b7d99a8b13ba92571eedc5b2d3ada0fab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-02T14:46:54Z","title_canon_sha256":"7edc346582df5370c6f3e6e4b9d49b6455536c2de886d9d142134dca01c10a8a"},"schema_version":"1.0","source":{"id":"2607.02259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02259","created_at":"2026-07-03T01:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02259v1","created_at":"2026-07-03T01:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02259","created_at":"2026-07-03T01:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"SL54BS7C2RNQ","created_at":"2026-07-03T01:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"SL54BS7C2RNQEKXN","created_at":"2026-07-03T01:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"SL54BS7C","created_at":"2026-07-03T01:17:46Z"}],"graph_snapshots":[{"event_id":"sha256:839a6a474b91020fa644019b425593e89fd377c3e53ef614cdd9f870a37be91f","target":"graph","created_at":"2026-07-03T01:17:46Z","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/2607.02259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce BamiBERT, a new BERT-based pre-trained language model for Vietnamese that addresses key limitations of PhoBERT -- the current de facto Vietnamese text encoder. Trained from scratch on a 129GB corpus of general-domain Vietnamese text for 20 epochs, BamiBERT supports an extended context length of up to 2048 tokens and operates directly on raw input, eliminating the need for external word segmentation. Across 8 Vietnamese benchmarks, it achieves the best score on 11 of 15 metrics and the second-best on 3 others, setting a new state of the art among \"base\"-sized Vietnam","authors_text":"Chi Tran, Dat Quoc Nguyen, Linh The Nguyen, Thinh Pham","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-02T14:46:54Z","title":"BamiBERT: A New BERT-based Language Model for Vietnamese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02259","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":"sha256:0cc36d9dbc6d27c76427cac1b181813e52c164a59238adf598e3c507724a66db","target":"record","created_at":"2026-07-03T01:17:46Z","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":"dcdc0574ff99b563cc05bee5cca50d7b7d99a8b13ba92571eedc5b2d3ada0fab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-02T14:46:54Z","title_canon_sha256":"7edc346582df5370c6f3e6e4b9d49b6455536c2de886d9d142134dca01c10a8a"},"schema_version":"1.0","source":{"id":"2607.02259","kind":"arxiv","version":1}},"canonical_sha256":"92fbc0cbe2d45b022aed43a30c7d68465123659c152d2591f39bd654a41319c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92fbc0cbe2d45b022aed43a30c7d68465123659c152d2591f39bd654a41319c2","first_computed_at":"2026-07-03T01:17:46.817927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:46.817927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"08MnurusQ3OcU/fxLPwhBUrUXvmrKwixAKpFbcyHzokDT1Xq2MrqqB21OU074Hw2/+nSRyCwy2HAFasGnzmlCQ==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:46.818329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cc36d9dbc6d27c76427cac1b181813e52c164a59238adf598e3c507724a66db","sha256:839a6a474b91020fa644019b425593e89fd377c3e53ef614cdd9f870a37be91f"],"state_sha256":"6775496471d0e495558561ba613aa06e38fe3dd618fd3f035f113067cfd466e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hGExhdvUUlzpvJNryhz67KF1MxtKHirPRISrfeQa9PNseGbFVwXgEGqdhje31DjhGocIjdE/JVfUKJ8+pPXmAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T19:42:12.710461Z","bundle_sha256":"de423cd7168804cde758ddc0121206003e737dd07555928343a043e0474fa459"}}