{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DFAZLAKSH7LJNCBKLZHE3TZWWV","short_pith_number":"pith:DFAZLAKS","canonical_record":{"source":{"id":"2311.00658","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:02:49Z","cross_cats_sorted":[],"title_canon_sha256":"a7c61ae9c86fc76460150734bfce4e1cd9ab16f145c7767996cd1b72b2e5524e","abstract_canon_sha256":"65677458ff90387e3d6b9c7511dd19a5d4619c5f4c816ca6f75994dc88a180e1"},"schema_version":"1.0"},"canonical_sha256":"19419581523fd696882a5e4e4dcf36b57fd55216a3e9218e6c1d25ea58f0376c","source":{"kind":"arxiv","id":"2311.00658","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00658","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00658v1","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00658","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"DFAZLAKSH7LJ","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"DFAZLAKSH7LJNCBK","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"DFAZLAKS","created_at":"2026-07-05T07:08:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DFAZLAKSH7LJNCBKLZHE3TZWWV","target":"record","payload":{"canonical_record":{"source":{"id":"2311.00658","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:02:49Z","cross_cats_sorted":[],"title_canon_sha256":"a7c61ae9c86fc76460150734bfce4e1cd9ab16f145c7767996cd1b72b2e5524e","abstract_canon_sha256":"65677458ff90387e3d6b9c7511dd19a5d4619c5f4c816ca6f75994dc88a180e1"},"schema_version":"1.0"},"canonical_sha256":"19419581523fd696882a5e4e4dcf36b57fd55216a3e9218e6c1d25ea58f0376c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:01.391690Z","signature_b64":"YrUWrvgg/EfX19KohZfPHM03ttruGke3B9PtvFEzYgEnsri8NJxO3E6/AHwOqsRhJ+gdsvPPnxoDweBgCZBRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19419581523fd696882a5e4e4dcf36b57fd55216a3e9218e6c1d25ea58f0376c","last_reissued_at":"2026-07-05T07:08:01.391132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:01.391132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.00658","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":"2026-07-05T07:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVE+k8pQZ5+mc4Jnl3kgO8MhQRjMetihXoedm3nDLX8giS3R0/bgsT4zJyXbrHswZc3LF5DAKFt3jMAuqeG+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:47:36.420081Z"},"content_sha256":"eeb8c0bc22d829ed38a2268f5fcaf1c219d766626f2ae9f2470b47216a3429f2","schema_version":"1.0","event_id":"sha256:eeb8c0bc22d829ed38a2268f5fcaf1c219d766626f2ae9f2470b47216a3429f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DFAZLAKSH7LJNCBKLZHE3TZWWV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explicit Morphological Knowledge Improves Pre-training of Language Models for Hebrew","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eylon Gueta, Omer Goldman, Reut Tsarfaty","submitted_at":"2023-11-01T17:02:49Z","abstract_excerpt":"Pre-trained language models (PLMs) have shown remarkable successes in acquiring a wide range of linguistic knowledge, relying solely on self-supervised training on text streams. Nevertheless, the effectiveness of this language-agnostic approach has been frequently questioned for its sub-optimal performance when applied to morphologically-rich languages (MRLs). We investigate the hypothesis that incorporating explicit morphological knowledge in the pre-training phase can improve the performance of PLMs for MRLs. We propose various morphologically driven tokenization methods enabling the model t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00658","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/2311.00658/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":"2026-07-05T07:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUvzKfxQS3nMKY5Z+92giLHOUPnAPyzoCyklWKGMyqHzcoe7bxXejG5okJwkHDNXuqgQxUZgKuvRU+Ar7wJ4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:47:36.420708Z"},"content_sha256":"2b84be1b8c8f874ebcd0a417d6ba47ef7b7329f82926f0af81eb69ecab28f21b","schema_version":"1.0","event_id":"sha256:2b84be1b8c8f874ebcd0a417d6ba47ef7b7329f82926f0af81eb69ecab28f21b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DFAZLAKSH7LJNCBKLZHE3TZWWV/bundle.json","state_url":"https://pith.science/pith/DFAZLAKSH7LJNCBKLZHE3TZWWV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DFAZLAKSH7LJNCBKLZHE3TZWWV/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":"2026-08-15T18:47:36Z","links":{"resolver":"https://pith.science/pith/DFAZLAKSH7LJNCBKLZHE3TZWWV","bundle":"https://pith.science/pith/DFAZLAKSH7LJNCBKLZHE3TZWWV/bundle.json","state":"https://pith.science/pith/DFAZLAKSH7LJNCBKLZHE3TZWWV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DFAZLAKSH7LJNCBKLZHE3TZWWV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DFAZLAKSH7LJNCBKLZHE3TZWWV","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":"65677458ff90387e3d6b9c7511dd19a5d4619c5f4c816ca6f75994dc88a180e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:02:49Z","title_canon_sha256":"a7c61ae9c86fc76460150734bfce4e1cd9ab16f145c7767996cd1b72b2e5524e"},"schema_version":"1.0","source":{"id":"2311.00658","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00658","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00658v1","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00658","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"DFAZLAKSH7LJ","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"DFAZLAKSH7LJNCBK","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"DFAZLAKS","created_at":"2026-07-05T07:08:01Z"}],"graph_snapshots":[{"event_id":"sha256:2b84be1b8c8f874ebcd0a417d6ba47ef7b7329f82926f0af81eb69ecab28f21b","target":"graph","created_at":"2026-07-05T07:08:01Z","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/2311.00658/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models (PLMs) have shown remarkable successes in acquiring a wide range of linguistic knowledge, relying solely on self-supervised training on text streams. Nevertheless, the effectiveness of this language-agnostic approach has been frequently questioned for its sub-optimal performance when applied to morphologically-rich languages (MRLs). We investigate the hypothesis that incorporating explicit morphological knowledge in the pre-training phase can improve the performance of PLMs for MRLs. We propose various morphologically driven tokenization methods enabling the model t","authors_text":"Eylon Gueta, Omer Goldman, Reut Tsarfaty","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:02:49Z","title":"Explicit Morphological Knowledge Improves Pre-training of Language Models for Hebrew"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00658","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:eeb8c0bc22d829ed38a2268f5fcaf1c219d766626f2ae9f2470b47216a3429f2","target":"record","created_at":"2026-07-05T07:08:01Z","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":"65677458ff90387e3d6b9c7511dd19a5d4619c5f4c816ca6f75994dc88a180e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:02:49Z","title_canon_sha256":"a7c61ae9c86fc76460150734bfce4e1cd9ab16f145c7767996cd1b72b2e5524e"},"schema_version":"1.0","source":{"id":"2311.00658","kind":"arxiv","version":1}},"canonical_sha256":"19419581523fd696882a5e4e4dcf36b57fd55216a3e9218e6c1d25ea58f0376c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19419581523fd696882a5e4e4dcf36b57fd55216a3e9218e6c1d25ea58f0376c","first_computed_at":"2026-07-05T07:08:01.391132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:01.391132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YrUWrvgg/EfX19KohZfPHM03ttruGke3B9PtvFEzYgEnsri8NJxO3E6/AHwOqsRhJ+gdsvPPnxoDweBgCZBRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:01.391690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00658","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeb8c0bc22d829ed38a2268f5fcaf1c219d766626f2ae9f2470b47216a3429f2","sha256:2b84be1b8c8f874ebcd0a417d6ba47ef7b7329f82926f0af81eb69ecab28f21b"],"state_sha256":"b914cc2cc96717f431d4199a2e6e30d44b823703d3ae3a186b3c5bab53012c35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"51fMQzYqr84GP/JSAkiDRYpqAIGpy1aCzX/x1BgT7Ch1cr6AlkAU9U85MXb/S2ceNrPg8OkbAseMtWSMabVyAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:47:36.429163Z","bundle_sha256":"eac77a0542df232fd0b86f902886c2fe6bce1496871f792d8f055ebd3448758d"}}