{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:PRSSTBUEWH4CGX5V63EG5RLIDC","short_pith_number":"pith:PRSSTBUE","canonical_record":{"source":{"id":"2210.06525","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-12T18:41:00Z","cross_cats_sorted":[],"title_canon_sha256":"cfaf6ba1966940d2df288360573450c9196de367d823cf8c598822d961de5e16","abstract_canon_sha256":"4c5e8d1c0297e98f701dcc0a4a66f9421b4d81a910f95244fc467fce8b939d3a"},"schema_version":"1.0"},"canonical_sha256":"7c65298684b1f8235fb5f6c86ec5681891cb5f784a6e72f1a9f99cd7a120bffb","source":{"kind":"arxiv","id":"2210.06525","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06525","created_at":"2026-07-05T05:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06525v1","created_at":"2026-07-05T05:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06525","created_at":"2026-07-05T05:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"PRSSTBUEWH4C","created_at":"2026-07-05T05:06:01Z"},{"alias_kind":"pith_short_16","alias_value":"PRSSTBUEWH4CGX5V","created_at":"2026-07-05T05:06:01Z"},{"alias_kind":"pith_short_8","alias_value":"PRSSTBUE","created_at":"2026-07-05T05:06:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:PRSSTBUEWH4CGX5V63EG5RLIDC","target":"record","payload":{"canonical_record":{"source":{"id":"2210.06525","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-12T18:41:00Z","cross_cats_sorted":[],"title_canon_sha256":"cfaf6ba1966940d2df288360573450c9196de367d823cf8c598822d961de5e16","abstract_canon_sha256":"4c5e8d1c0297e98f701dcc0a4a66f9421b4d81a910f95244fc467fce8b939d3a"},"schema_version":"1.0"},"canonical_sha256":"7c65298684b1f8235fb5f6c86ec5681891cb5f784a6e72f1a9f99cd7a120bffb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:01.908486Z","signature_b64":"FSGXWVJZx6HsmA2ns7NDdt+rTbynlrL5YLSg/DfRuXgFWgfN1ZR5FOW98jhOxbGszPEUoanm1Ee04V4bYeRzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c65298684b1f8235fb5f6c86ec5681891cb5f784a6e72f1a9f99cd7a120bffb","last_reissued_at":"2026-07-05T05:06:01.907981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:01.907981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.06525","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":"2026-07-05T05:06:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rlYeT0I4MzNI+Y8PFvARi511Z8njj1z+luGb8ieGLWEcCWHeouOkC3Rf6vi+X11Dt31UoHUVQKeEhDxL2+O+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:22:13.076540Z"},"content_sha256":"d4f3fe3eab0dd99dfd0289005f84c08e739bb2033fb08042040ff205b0e57b49","schema_version":"1.0","event_id":"sha256:d4f3fe3eab0dd99dfd0289005f84c08e739bb2033fb08042040ff205b0e57b49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:PRSSTBUEWH4CGX5V63EG5RLIDC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Subword Segmental Language Modelling for Nguni Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Francois Meyer, Jan Buys","submitted_at":"2022-10-12T18:41:00Z","abstract_excerpt":"Subwords have become the standard units of text in NLP, enabling efficient open-vocabulary models. With algorithms like byte-pair encoding (BPE), subword segmentation is viewed as a preprocessing step applied to the corpus before training. This can lead to sub-optimal segmentations for low-resource languages with complex morphologies. We propose a subword segmental language model (SSLM) that learns how to segment words while being trained for autoregressive language modelling. By unifying subword segmentation and language modelling, our model learns subwords that optimise LM performance. We tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06525","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/2210.06525/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":"2026-07-05T05:06:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7faUfNeD75LnQ62cr3OUMsMgmNd72gCPaBtAd9wRmlwj0Ybu273hVtgziM11RictWDKhnzSGGRFRcNVtyQbUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:22:13.077080Z"},"content_sha256":"4ee1cf2fd1c4acd8aef566c2b38af7033df275eca3af20e4cf9c758b50c91f65","schema_version":"1.0","event_id":"sha256:4ee1cf2fd1c4acd8aef566c2b38af7033df275eca3af20e4cf9c758b50c91f65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PRSSTBUEWH4CGX5V63EG5RLIDC/bundle.json","state_url":"https://pith.science/pith/PRSSTBUEWH4CGX5V63EG5RLIDC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PRSSTBUEWH4CGX5V63EG5RLIDC/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":"2026-08-04T12:22:13Z","links":{"resolver":"https://pith.science/pith/PRSSTBUEWH4CGX5V63EG5RLIDC","bundle":"https://pith.science/pith/PRSSTBUEWH4CGX5V63EG5RLIDC/bundle.json","state":"https://pith.science/pith/PRSSTBUEWH4CGX5V63EG5RLIDC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PRSSTBUEWH4CGX5V63EG5RLIDC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PRSSTBUEWH4CGX5V63EG5RLIDC","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":"4c5e8d1c0297e98f701dcc0a4a66f9421b4d81a910f95244fc467fce8b939d3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-12T18:41:00Z","title_canon_sha256":"cfaf6ba1966940d2df288360573450c9196de367d823cf8c598822d961de5e16"},"schema_version":"1.0","source":{"id":"2210.06525","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06525","created_at":"2026-07-05T05:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06525v1","created_at":"2026-07-05T05:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06525","created_at":"2026-07-05T05:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"PRSSTBUEWH4C","created_at":"2026-07-05T05:06:01Z"},{"alias_kind":"pith_short_16","alias_value":"PRSSTBUEWH4CGX5V","created_at":"2026-07-05T05:06:01Z"},{"alias_kind":"pith_short_8","alias_value":"PRSSTBUE","created_at":"2026-07-05T05:06:01Z"}],"graph_snapshots":[{"event_id":"sha256:4ee1cf2fd1c4acd8aef566c2b38af7033df275eca3af20e4cf9c758b50c91f65","target":"graph","created_at":"2026-07-05T05:06:01Z","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/2210.06525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Subwords have become the standard units of text in NLP, enabling efficient open-vocabulary models. With algorithms like byte-pair encoding (BPE), subword segmentation is viewed as a preprocessing step applied to the corpus before training. This can lead to sub-optimal segmentations for low-resource languages with complex morphologies. We propose a subword segmental language model (SSLM) that learns how to segment words while being trained for autoregressive language modelling. By unifying subword segmentation and language modelling, our model learns subwords that optimise LM performance. We tr","authors_text":"Francois Meyer, Jan Buys","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-12T18:41:00Z","title":"Subword Segmental Language Modelling for Nguni Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06525","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:d4f3fe3eab0dd99dfd0289005f84c08e739bb2033fb08042040ff205b0e57b49","target":"record","created_at":"2026-07-05T05:06:01Z","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":"4c5e8d1c0297e98f701dcc0a4a66f9421b4d81a910f95244fc467fce8b939d3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-12T18:41:00Z","title_canon_sha256":"cfaf6ba1966940d2df288360573450c9196de367d823cf8c598822d961de5e16"},"schema_version":"1.0","source":{"id":"2210.06525","kind":"arxiv","version":1}},"canonical_sha256":"7c65298684b1f8235fb5f6c86ec5681891cb5f784a6e72f1a9f99cd7a120bffb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c65298684b1f8235fb5f6c86ec5681891cb5f784a6e72f1a9f99cd7a120bffb","first_computed_at":"2026-07-05T05:06:01.907981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:01.907981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FSGXWVJZx6HsmA2ns7NDdt+rTbynlrL5YLSg/DfRuXgFWgfN1ZR5FOW98jhOxbGszPEUoanm1Ee04V4bYeRzAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:01.908486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.06525","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4f3fe3eab0dd99dfd0289005f84c08e739bb2033fb08042040ff205b0e57b49","sha256:4ee1cf2fd1c4acd8aef566c2b38af7033df275eca3af20e4cf9c758b50c91f65"],"state_sha256":"a265833b2e673f3f6dca63ecec7b54708cda6a5db94abc6854774b016b2eaa10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6woJ/pVXRZYNU4Bo2xA0HPakGbgpXC9ZMXubl6rtr1tyuSTfU4EpQdpK+dy18RoEqdAj1EfjyfzuLpwgfiG9CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:22:13.082120Z","bundle_sha256":"918c22bb49ab42c1baf0d346dc1af28760d3859ea4dc66492c4040427fb6fc51"}}