{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XUA3DGC5M6WQVHLLWRQEJ3YDVQ","short_pith_number":"pith:XUA3DGC5","canonical_record":{"source":{"id":"2505.24581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T13:29:03Z","cross_cats_sorted":[],"title_canon_sha256":"221a10be0f676a0c17fe3b4f41ecd813c14d37a9ea00cc04aecb0d362169a49b","abstract_canon_sha256":"e26185a436cdaa79ba3eaa7ecfb5c610b62e3841f4e29507df5531e615885be3"},"schema_version":"1.0"},"canonical_sha256":"bd01b1985d67ad0a9d6bb46044ef03ac358acb0db5ade3037e49f257745ec703","source":{"kind":"arxiv","id":"2505.24581","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24581","created_at":"2026-07-05T11:12:52Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24581v1","created_at":"2026-07-05T11:12:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24581","created_at":"2026-07-05T11:12:52Z"},{"alias_kind":"pith_short_12","alias_value":"XUA3DGC5M6WQ","created_at":"2026-07-05T11:12:52Z"},{"alias_kind":"pith_short_16","alias_value":"XUA3DGC5M6WQVHLL","created_at":"2026-07-05T11:12:52Z"},{"alias_kind":"pith_short_8","alias_value":"XUA3DGC5","created_at":"2026-07-05T11:12:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XUA3DGC5M6WQVHLLWRQEJ3YDVQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T13:29:03Z","cross_cats_sorted":[],"title_canon_sha256":"221a10be0f676a0c17fe3b4f41ecd813c14d37a9ea00cc04aecb0d362169a49b","abstract_canon_sha256":"e26185a436cdaa79ba3eaa7ecfb5c610b62e3841f4e29507df5531e615885be3"},"schema_version":"1.0"},"canonical_sha256":"bd01b1985d67ad0a9d6bb46044ef03ac358acb0db5ade3037e49f257745ec703","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:52.616219Z","signature_b64":"q2BXa1QgbV5XT81SyOqIdEpKoSN/DcSXJO6JjHm6BpeiETQN9IGkHqYlRztcZpcyxYcnWhmmexrmH9cn514LAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd01b1985d67ad0a9d6bb46044ef03ac358acb0db5ade3037e49f257745ec703","last_reissued_at":"2026-07-05T11:12:52.615700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:52.615700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24581","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":"2026-07-05T11:12:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yuSFDbxYhqpOnwZ0HoqC6mQMPs43hcBrFUKNOA/nzgRc3fgEhASPshfJJ3nFjKNXtULPb1MJsmqrCQXo0pkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:20:48.591655Z"},"content_sha256":"ff787cfe10bed8d9cfd47e865646df86a526708e0369bc8f1eb7f157f710c5c7","schema_version":"1.0","event_id":"sha256:ff787cfe10bed8d9cfd47e865646df86a526708e0369bc8f1eb7f157f710c5c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XUA3DGC5M6WQVHLLWRQEJ3YDVQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adel Ammar, Anis Koubaa, Omer Nacar, Serry Sibaee, Wadii Boulila, Yasser Al-Habashi","submitted_at":"2025-05-30T13:29:03Z","abstract_excerpt":"Semantic textual similarity (STS) is a critical task in natural language processing (NLP), enabling applications in retrieval, clustering, and understanding semantic relationships between texts. However, research in this area for the Arabic language remains limited due to the lack of high-quality datasets and pre-trained models. This scarcity of resources has restricted the accurate evaluation and advance of semantic similarity in Arabic text. This paper introduces General Arabic Text Embedding (GATE) models that achieve state-of-the-art performance on the Semantic Textual Similarity task with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24581","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/2505.24581/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":"2026-07-05T11:12:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OkwPZkFZrprnj//SEGQU/U00N2FfkLu05g2EVv7UKzHke/V3VfF8okpMmN4xeYaRipySipVgk/hl1DLlFWjECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:20:48.592287Z"},"content_sha256":"7b0ac5eace51403c257c04fa680b910854fcf69552f3847368d54a2863dfcd3d","schema_version":"1.0","event_id":"sha256:7b0ac5eace51403c257c04fa680b910854fcf69552f3847368d54a2863dfcd3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUA3DGC5M6WQVHLLWRQEJ3YDVQ/bundle.json","state_url":"https://pith.science/pith/XUA3DGC5M6WQVHLLWRQEJ3YDVQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUA3DGC5M6WQVHLLWRQEJ3YDVQ/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":"2026-08-10T04:20:48Z","links":{"resolver":"https://pith.science/pith/XUA3DGC5M6WQVHLLWRQEJ3YDVQ","bundle":"https://pith.science/pith/XUA3DGC5M6WQVHLLWRQEJ3YDVQ/bundle.json","state":"https://pith.science/pith/XUA3DGC5M6WQVHLLWRQEJ3YDVQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUA3DGC5M6WQVHLLWRQEJ3YDVQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XUA3DGC5M6WQVHLLWRQEJ3YDVQ","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":"e26185a436cdaa79ba3eaa7ecfb5c610b62e3841f4e29507df5531e615885be3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T13:29:03Z","title_canon_sha256":"221a10be0f676a0c17fe3b4f41ecd813c14d37a9ea00cc04aecb0d362169a49b"},"schema_version":"1.0","source":{"id":"2505.24581","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24581","created_at":"2026-07-05T11:12:52Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24581v1","created_at":"2026-07-05T11:12:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24581","created_at":"2026-07-05T11:12:52Z"},{"alias_kind":"pith_short_12","alias_value":"XUA3DGC5M6WQ","created_at":"2026-07-05T11:12:52Z"},{"alias_kind":"pith_short_16","alias_value":"XUA3DGC5M6WQVHLL","created_at":"2026-07-05T11:12:52Z"},{"alias_kind":"pith_short_8","alias_value":"XUA3DGC5","created_at":"2026-07-05T11:12:52Z"}],"graph_snapshots":[{"event_id":"sha256:7b0ac5eace51403c257c04fa680b910854fcf69552f3847368d54a2863dfcd3d","target":"graph","created_at":"2026-07-05T11:12:52Z","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/2505.24581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic textual similarity (STS) is a critical task in natural language processing (NLP), enabling applications in retrieval, clustering, and understanding semantic relationships between texts. However, research in this area for the Arabic language remains limited due to the lack of high-quality datasets and pre-trained models. This scarcity of resources has restricted the accurate evaluation and advance of semantic similarity in Arabic text. This paper introduces General Arabic Text Embedding (GATE) models that achieve state-of-the-art performance on the Semantic Textual Similarity task with","authors_text":"Adel Ammar, Anis Koubaa, Omer Nacar, Serry Sibaee, Wadii Boulila, Yasser Al-Habashi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T13:29:03Z","title":"GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24581","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:ff787cfe10bed8d9cfd47e865646df86a526708e0369bc8f1eb7f157f710c5c7","target":"record","created_at":"2026-07-05T11:12:52Z","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":"e26185a436cdaa79ba3eaa7ecfb5c610b62e3841f4e29507df5531e615885be3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T13:29:03Z","title_canon_sha256":"221a10be0f676a0c17fe3b4f41ecd813c14d37a9ea00cc04aecb0d362169a49b"},"schema_version":"1.0","source":{"id":"2505.24581","kind":"arxiv","version":1}},"canonical_sha256":"bd01b1985d67ad0a9d6bb46044ef03ac358acb0db5ade3037e49f257745ec703","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd01b1985d67ad0a9d6bb46044ef03ac358acb0db5ade3037e49f257745ec703","first_computed_at":"2026-07-05T11:12:52.615700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:52.615700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q2BXa1QgbV5XT81SyOqIdEpKoSN/DcSXJO6JjHm6BpeiETQN9IGkHqYlRztcZpcyxYcnWhmmexrmH9cn514LAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:52.616219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24581","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff787cfe10bed8d9cfd47e865646df86a526708e0369bc8f1eb7f157f710c5c7","sha256:7b0ac5eace51403c257c04fa680b910854fcf69552f3847368d54a2863dfcd3d"],"state_sha256":"a4a7991bf7cd8155b255556c1f4dd0dac890c972fd848ef3ecd7c9d1f84f520a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s0IbiNAP9pxZYwOcrudBxcFzbGv57KF44tnG+08dXZeOk6jeaU9cc53DZp+yO4/JIQc3Y4+swAtL202m38feCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:20:48.595971Z","bundle_sha256":"02dade8e153dcc4f954f71853fd7ab9d27b289307469334c886f3476aa6de6da"}}