{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KFFHRESAHQBJTLP5EYQTZU4VMH","short_pith_number":"pith:KFFHRESA","canonical_record":{"source":{"id":"2606.03027","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T02:05:14Z","cross_cats_sorted":[],"title_canon_sha256":"ba557e50ae08b0e480181977d1221137d7abec463714aeea090b6eec0c97687b","abstract_canon_sha256":"f272ed522827ec93cdd847546d7a49e7f16ef9d8de4a8c1fe0499f78f5ca6040"},"schema_version":"1.0"},"canonical_sha256":"514a7892403c0299adfd26213cd39561e7fcfc23a367d6c1e8bd9d5b380201a2","source":{"kind":"arxiv","id":"2606.03027","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03027","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03027v1","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03027","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"pith_short_12","alias_value":"KFFHRESAHQBJ","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"pith_short_16","alias_value":"KFFHRESAHQBJTLP5","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"pith_short_8","alias_value":"KFFHRESA","created_at":"2026-06-03T01:05:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KFFHRESAHQBJTLP5EYQTZU4VMH","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03027","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T02:05:14Z","cross_cats_sorted":[],"title_canon_sha256":"ba557e50ae08b0e480181977d1221137d7abec463714aeea090b6eec0c97687b","abstract_canon_sha256":"f272ed522827ec93cdd847546d7a49e7f16ef9d8de4a8c1fe0499f78f5ca6040"},"schema_version":"1.0"},"canonical_sha256":"514a7892403c0299adfd26213cd39561e7fcfc23a367d6c1e8bd9d5b380201a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:29.649385Z","signature_b64":"kccnpqVVDcQLeetV68KaQKKnb4z4ImHDdFRbJf9T++Z2YTZ8wG8FhpcQToRUXg6R5HNON6kKKiHNaZfI1vBOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"514a7892403c0299adfd26213cd39561e7fcfc23a367d6c1e8bd9d5b380201a2","last_reissued_at":"2026-06-03T01:05:29.648942Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:29.648942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03027","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":"2026-06-03T01:05:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6sEH7mUOLTMqHJkA2Zb6j7RFefXxzDyav8Vpo2mEMF4UYIBDRKbC0QEiDGmTXymdCobdM+ynmG3RjcsxOXvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T01:20:00.123525Z"},"content_sha256":"8de65d621195f74fec66bdf7f3e2025e576d3c9ac5628677e7971dceb828e626","schema_version":"1.0","event_id":"sha256:8de65d621195f74fec66bdf7f3e2025e576d3c9ac5628677e7971dceb828e626"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KFFHRESAHQBJTLP5EYQTZU4VMH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEA-Embedding: Open and Reproducible Text Embeddings for Southeast Asia","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jian Gang Ngui, Peerat Limkonchotiwat, Raymond Ng, Sarana Nutanong","submitted_at":"2026-06-02T02:05:14Z","abstract_excerpt":"Text embeddings are fundamental to many downstream applications, making robustness important for real-world NLP. However, most recent state-of-the-art embedding models are not reproducible because they rely on closed or undisclosed training data, and they remain insufficiently robust for Southeast Asian languages. We present SEA-Embedding, a fully open and reproducible text-embedding pipeline for Southeast Asian languages trained only on publicly available data, and use it to study three core factors of robust embedding design: data composition, training objective, and base encoder initializat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03027","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/2606.03027/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":"2026-06-03T01:05:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQvgU/RVNyt6WDl5Gb/yQ8bQnBMb5gex+3DLh0CiLHh8/8Lk8wjduyV8rayvaXE02A6/hBvpgtqyxSNq8JJvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T01:20:00.123893Z"},"content_sha256":"478ee93e70613e44e9c151b8baba6f9ca61e50302a079c3a83d19d142d70c105","schema_version":"1.0","event_id":"sha256:478ee93e70613e44e9c151b8baba6f9ca61e50302a079c3a83d19d142d70c105"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KFFHRESAHQBJTLP5EYQTZU4VMH/bundle.json","state_url":"https://pith.science/pith/KFFHRESAHQBJTLP5EYQTZU4VMH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KFFHRESAHQBJTLP5EYQTZU4VMH/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":"2026-06-22T01:20:00Z","links":{"resolver":"https://pith.science/pith/KFFHRESAHQBJTLP5EYQTZU4VMH","bundle":"https://pith.science/pith/KFFHRESAHQBJTLP5EYQTZU4VMH/bundle.json","state":"https://pith.science/pith/KFFHRESAHQBJTLP5EYQTZU4VMH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KFFHRESAHQBJTLP5EYQTZU4VMH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KFFHRESAHQBJTLP5EYQTZU4VMH","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":"f272ed522827ec93cdd847546d7a49e7f16ef9d8de4a8c1fe0499f78f5ca6040","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T02:05:14Z","title_canon_sha256":"ba557e50ae08b0e480181977d1221137d7abec463714aeea090b6eec0c97687b"},"schema_version":"1.0","source":{"id":"2606.03027","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03027","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03027v1","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03027","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"pith_short_12","alias_value":"KFFHRESAHQBJ","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"pith_short_16","alias_value":"KFFHRESAHQBJTLP5","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"pith_short_8","alias_value":"KFFHRESA","created_at":"2026-06-03T01:05:29Z"}],"graph_snapshots":[{"event_id":"sha256:478ee93e70613e44e9c151b8baba6f9ca61e50302a079c3a83d19d142d70c105","target":"graph","created_at":"2026-06-03T01:05:29Z","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/2606.03027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text embeddings are fundamental to many downstream applications, making robustness important for real-world NLP. However, most recent state-of-the-art embedding models are not reproducible because they rely on closed or undisclosed training data, and they remain insufficiently robust for Southeast Asian languages. We present SEA-Embedding, a fully open and reproducible text-embedding pipeline for Southeast Asian languages trained only on publicly available data, and use it to study three core factors of robust embedding design: data composition, training objective, and base encoder initializat","authors_text":"Jian Gang Ngui, Peerat Limkonchotiwat, Raymond Ng, Sarana Nutanong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T02:05:14Z","title":"SEA-Embedding: Open and Reproducible Text Embeddings for Southeast Asia"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03027","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":"sha256:8de65d621195f74fec66bdf7f3e2025e576d3c9ac5628677e7971dceb828e626","target":"record","created_at":"2026-06-03T01:05:29Z","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":"f272ed522827ec93cdd847546d7a49e7f16ef9d8de4a8c1fe0499f78f5ca6040","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T02:05:14Z","title_canon_sha256":"ba557e50ae08b0e480181977d1221137d7abec463714aeea090b6eec0c97687b"},"schema_version":"1.0","source":{"id":"2606.03027","kind":"arxiv","version":1}},"canonical_sha256":"514a7892403c0299adfd26213cd39561e7fcfc23a367d6c1e8bd9d5b380201a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"514a7892403c0299adfd26213cd39561e7fcfc23a367d6c1e8bd9d5b380201a2","first_computed_at":"2026-06-03T01:05:29.648942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:29.648942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kccnpqVVDcQLeetV68KaQKKnb4z4ImHDdFRbJf9T++Z2YTZ8wG8FhpcQToRUXg6R5HNON6kKKiHNaZfI1vBOCw==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:29.649385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03027","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8de65d621195f74fec66bdf7f3e2025e576d3c9ac5628677e7971dceb828e626","sha256:478ee93e70613e44e9c151b8baba6f9ca61e50302a079c3a83d19d142d70c105"],"state_sha256":"b2bc8b23590fd6e86afd064d00bdb4ad13e0d02c9a3de83f1cfe015a9f5d17d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ifBnrIyAVEWECnmzJraZcHwowqMzkdpxwIDQsIQql95pZCQU6OgHLb+B2q2e3wfaEWg6F6JJvN8fpEagSMKcBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T01:20:00.125824Z","bundle_sha256":"b93c40ef6195defc579f604de5573696103c4f0903e4451ecc35b7ad8bfd1b75"}}