{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PSZNWOAQQHQPP5IWY632K5EOUY","short_pith_number":"pith:PSZNWOAQ","canonical_record":{"source":{"id":"2605.15081","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:05:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87c55996e9dc7a8872ee64d2709dae163ccd4b07ddc8671f5711a24177b67325","abstract_canon_sha256":"19ba42ec9d7df7d88ddc5a5956fe9887f0d3eeaea6cf8365d230c0f6c86ab398"},"schema_version":"1.0"},"canonical_sha256":"7cb2db381081e0f7f516c7b7a5748ea630a8d7c97bbf2ac2a6daa8e83d31249e","source":{"kind":"arxiv","id":"2605.15081","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15081","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15081v1","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15081","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"pith_short_12","alias_value":"PSZNWOAQQHQP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PSZNWOAQQHQPP5IW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PSZNWOAQ","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PSZNWOAQQHQPP5IWY632K5EOUY","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15081","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:05:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87c55996e9dc7a8872ee64d2709dae163ccd4b07ddc8671f5711a24177b67325","abstract_canon_sha256":"19ba42ec9d7df7d88ddc5a5956fe9887f0d3eeaea6cf8365d230c0f6c86ab398"},"schema_version":"1.0"},"canonical_sha256":"7cb2db381081e0f7f516c7b7a5748ea630a8d7c97bbf2ac2a6daa8e83d31249e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:54.154215Z","signature_b64":"UhCAbwNPc8a5si0Mt3/FslOtb0jIYpeIwkIACC1KaSlhGH6xq6DAoDyx1QfBfzNZW9kvJTqsUdxvXUJkUp0MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cb2db381081e0f7f516c7b7a5748ea630a8d7c97bbf2ac2a6daa8e83d31249e","last_reissued_at":"2026-05-17T23:38:54.153506Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:54.153506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15081","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":"2026-05-17T23:38:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nKS73SdX5PDREqzdthWB3V3atnaJ0fREPUdRPANGrNaSyKUo2daqmqFJrsjeyRTBNNeHwqLvHz8bJ7ZXDEMrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:59:36.588165Z"},"content_sha256":"cafc4150c34e933ec138c79829adb056a65f50096e4241dfa43e177a66036117","schema_version":"1.0","event_id":"sha256:cafc4150c34e933ec138c79829adb056a65f50096e4241dfa43e177a66036117"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PSZNWOAQQHQPP5IWY632K5EOUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hang Yu, Peng Di, Rui Wang, Zihan Liao, Ziyin Zhang","submitted_at":"2026-05-14T17:05:26Z","abstract_excerpt":"The development of high-quality text embeddings is increasingly drifting toward an exclusionary future, defined by three critical barriers: prohibitive computational costs, a narrow linguistic focus that neglects most of the world's languages, and a lack of transparency from closed-source or open-weight models that stifles research. To dismantle these barriers, we introduce ML-Embed, a suite of inclusive and efficient models built upon a new framework: 3-Dimensional Matryoshka Learning (3D-ML). Our framework addresses the computational challenge with comprehensive efficiency across the entire "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15081","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":""},"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":"2026-05-17T23:38:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sBPN4RqbzcNH0ZaGp5/P5SCWE9lnn9eqR/GRYm1jc8yl06tPbkrJ6ER5vq3l3CMNLha+M8PIH6TnSV75UnAjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:59:36.588520Z"},"content_sha256":"bcbc9e79893fc5b6b1661e70d3b929907cde917e36daa1a291112f8641f10e85","schema_version":"1.0","event_id":"sha256:bcbc9e79893fc5b6b1661e70d3b929907cde917e36daa1a291112f8641f10e85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PSZNWOAQQHQPP5IWY632K5EOUY/bundle.json","state_url":"https://pith.science/pith/PSZNWOAQQHQPP5IWY632K5EOUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PSZNWOAQQHQPP5IWY632K5EOUY/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":"2026-06-01T15:59:36Z","links":{"resolver":"https://pith.science/pith/PSZNWOAQQHQPP5IWY632K5EOUY","bundle":"https://pith.science/pith/PSZNWOAQQHQPP5IWY632K5EOUY/bundle.json","state":"https://pith.science/pith/PSZNWOAQQHQPP5IWY632K5EOUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PSZNWOAQQHQPP5IWY632K5EOUY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PSZNWOAQQHQPP5IWY632K5EOUY","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":"19ba42ec9d7df7d88ddc5a5956fe9887f0d3eeaea6cf8365d230c0f6c86ab398","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:05:26Z","title_canon_sha256":"87c55996e9dc7a8872ee64d2709dae163ccd4b07ddc8671f5711a24177b67325"},"schema_version":"1.0","source":{"id":"2605.15081","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15081","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15081v1","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15081","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"pith_short_12","alias_value":"PSZNWOAQQHQP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PSZNWOAQQHQPP5IW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PSZNWOAQ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:bcbc9e79893fc5b6b1661e70d3b929907cde917e36daa1a291112f8641f10e85","target":"graph","created_at":"2026-05-17T23:38:54Z","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"},"paper":{"abstract_excerpt":"The development of high-quality text embeddings is increasingly drifting toward an exclusionary future, defined by three critical barriers: prohibitive computational costs, a narrow linguistic focus that neglects most of the world's languages, and a lack of transparency from closed-source or open-weight models that stifles research. To dismantle these barriers, we introduce ML-Embed, a suite of inclusive and efficient models built upon a new framework: 3-Dimensional Matryoshka Learning (3D-ML). Our framework addresses the computational challenge with comprehensive efficiency across the entire ","authors_text":"Hang Yu, Peng Di, Rui Wang, Zihan Liao, Ziyin Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:05:26Z","title":"ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15081","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:cafc4150c34e933ec138c79829adb056a65f50096e4241dfa43e177a66036117","target":"record","created_at":"2026-05-17T23:38:54Z","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":"19ba42ec9d7df7d88ddc5a5956fe9887f0d3eeaea6cf8365d230c0f6c86ab398","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:05:26Z","title_canon_sha256":"87c55996e9dc7a8872ee64d2709dae163ccd4b07ddc8671f5711a24177b67325"},"schema_version":"1.0","source":{"id":"2605.15081","kind":"arxiv","version":1}},"canonical_sha256":"7cb2db381081e0f7f516c7b7a5748ea630a8d7c97bbf2ac2a6daa8e83d31249e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cb2db381081e0f7f516c7b7a5748ea630a8d7c97bbf2ac2a6daa8e83d31249e","first_computed_at":"2026-05-17T23:38:54.153506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:54.153506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UhCAbwNPc8a5si0Mt3/FslOtb0jIYpeIwkIACC1KaSlhGH6xq6DAoDyx1QfBfzNZW9kvJTqsUdxvXUJkUp0MDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:54.154215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15081","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cafc4150c34e933ec138c79829adb056a65f50096e4241dfa43e177a66036117","sha256:bcbc9e79893fc5b6b1661e70d3b929907cde917e36daa1a291112f8641f10e85"],"state_sha256":"434ef7ad2b48fcf6f193cd8b9ba2cc618331cd8e0877bb28dbeeac3be1773157"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GTcdSUnBGWHtRKm2l0/mhtVwNwTjVGWR8RPCFWmUZ9785NV2EBIXOtIdC/x5cMfoFOtKvMYvAIXDNy6Z8ARRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T15:59:36.590296Z","bundle_sha256":"057cba22cf9c011a1c0d16c9b81a614bcb575838a0c7949e58f5e96a9c48caa4"}}