{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PPMYDYJ6G2OV5DJA5IXLXQRANJ","short_pith_number":"pith:PPMYDYJ6","canonical_record":{"source":{"id":"2305.07005","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-11T17:44:29Z","cross_cats_sorted":[],"title_canon_sha256":"d612e316c80d059ef6f9cc6423493d199e78614de1d5c6f52b9090e86ae24fb9","abstract_canon_sha256":"090386af375f47a48d7c5ab55ffa3a1b8188ec0be11a59039c8110844c87b326"},"schema_version":"1.0"},"canonical_sha256":"7bd981e13e369d5e8d20ea2ebbc2206a6419a9a18a5efb0ff3018bd245a0fb9e","source":{"kind":"arxiv","id":"2305.07005","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07005","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07005v1","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07005","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"PPMYDYJ6G2OV","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"PPMYDYJ6G2OV5DJA","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"PPMYDYJ6","created_at":"2026-07-05T06:09:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PPMYDYJ6G2OV5DJA5IXLXQRANJ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.07005","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-11T17:44:29Z","cross_cats_sorted":[],"title_canon_sha256":"d612e316c80d059ef6f9cc6423493d199e78614de1d5c6f52b9090e86ae24fb9","abstract_canon_sha256":"090386af375f47a48d7c5ab55ffa3a1b8188ec0be11a59039c8110844c87b326"},"schema_version":"1.0"},"canonical_sha256":"7bd981e13e369d5e8d20ea2ebbc2206a6419a9a18a5efb0ff3018bd245a0fb9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:18.477179Z","signature_b64":"GcZHXbi3xqfoJiMiphmPsmtiUgcLkostCzp4sIRRvGS+VpZKyTIiSszigbwrKoWgJ8xqyoHhrnX8+F3hk8wfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bd981e13e369d5e8d20ea2ebbc2206a6419a9a18a5efb0ff3018bd245a0fb9e","last_reissued_at":"2026-07-05T06:09:18.476771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:18.476771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.07005","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":"2026-07-05T06:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Xc+jB/w+llseP20N1ul1/esb4vx0T7Q2J5Hi8QMsvyQ3msLeWciFFAIyZtD78N1UVGSkQ1+LQoC78ZblOfpAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:26:54.713096Z"},"content_sha256":"3b3d0f94ff7b37072e1f7413baf7036a75770fa74b418f39e93ac3d69eaca852","schema_version":"1.0","event_id":"sha256:3b3d0f94ff7b37072e1f7413baf7036a75770fa74b418f39e93ac3d69eaca852"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PPMYDYJ6G2OV5DJA5IXLXQRANJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Francois Meyer, Jan Buys","submitted_at":"2023-05-11T17:44:29Z","abstract_excerpt":"Subword segmenters like BPE operate as a preprocessing step in neural machine translation and other (conditional) language models. They are applied to datasets before training, so translation or text generation quality relies on the quality of segmentations. We propose a departure from this paradigm, called subword segmental machine translation (SSMT). SSMT unifies subword segmentation and MT in a single trainable model. It learns to segment target sentence words while jointly learning to generate target sentences. To use SSMT during inference we propose dynamic decoding, a text generation alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07005","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/2305.07005/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":"2026-07-05T06:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lVMC7ow6Qx4NzQd94YhZ5TjurCYYVNq8vOZTIJSwg3JtLN4smsd2MUMyXuSzx0DriOdiX5Nv6gblrABpz9fUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:26:54.713608Z"},"content_sha256":"d368a59e0e89e34c09c3c7f3501df69d34fb9850c88bad940d1a884f587a435d","schema_version":"1.0","event_id":"sha256:d368a59e0e89e34c09c3c7f3501df69d34fb9850c88bad940d1a884f587a435d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPMYDYJ6G2OV5DJA5IXLXQRANJ/bundle.json","state_url":"https://pith.science/pith/PPMYDYJ6G2OV5DJA5IXLXQRANJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPMYDYJ6G2OV5DJA5IXLXQRANJ/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":"2026-08-04T10:26:54Z","links":{"resolver":"https://pith.science/pith/PPMYDYJ6G2OV5DJA5IXLXQRANJ","bundle":"https://pith.science/pith/PPMYDYJ6G2OV5DJA5IXLXQRANJ/bundle.json","state":"https://pith.science/pith/PPMYDYJ6G2OV5DJA5IXLXQRANJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPMYDYJ6G2OV5DJA5IXLXQRANJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PPMYDYJ6G2OV5DJA5IXLXQRANJ","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":"090386af375f47a48d7c5ab55ffa3a1b8188ec0be11a59039c8110844c87b326","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-11T17:44:29Z","title_canon_sha256":"d612e316c80d059ef6f9cc6423493d199e78614de1d5c6f52b9090e86ae24fb9"},"schema_version":"1.0","source":{"id":"2305.07005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07005","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07005v1","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07005","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"PPMYDYJ6G2OV","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"PPMYDYJ6G2OV5DJA","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"PPMYDYJ6","created_at":"2026-07-05T06:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:d368a59e0e89e34c09c3c7f3501df69d34fb9850c88bad940d1a884f587a435d","target":"graph","created_at":"2026-07-05T06:09:18Z","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/2305.07005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Subword segmenters like BPE operate as a preprocessing step in neural machine translation and other (conditional) language models. They are applied to datasets before training, so translation or text generation quality relies on the quality of segmentations. We propose a departure from this paradigm, called subword segmental machine translation (SSMT). SSMT unifies subword segmentation and MT in a single trainable model. It learns to segment target sentence words while jointly learning to generate target sentences. To use SSMT during inference we propose dynamic decoding, a text generation alg","authors_text":"Francois Meyer, Jan Buys","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-11T17:44:29Z","title":"Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07005","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":"sha256:3b3d0f94ff7b37072e1f7413baf7036a75770fa74b418f39e93ac3d69eaca852","target":"record","created_at":"2026-07-05T06:09:18Z","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":"090386af375f47a48d7c5ab55ffa3a1b8188ec0be11a59039c8110844c87b326","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-11T17:44:29Z","title_canon_sha256":"d612e316c80d059ef6f9cc6423493d199e78614de1d5c6f52b9090e86ae24fb9"},"schema_version":"1.0","source":{"id":"2305.07005","kind":"arxiv","version":1}},"canonical_sha256":"7bd981e13e369d5e8d20ea2ebbc2206a6419a9a18a5efb0ff3018bd245a0fb9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bd981e13e369d5e8d20ea2ebbc2206a6419a9a18a5efb0ff3018bd245a0fb9e","first_computed_at":"2026-07-05T06:09:18.476771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:18.476771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GcZHXbi3xqfoJiMiphmPsmtiUgcLkostCzp4sIRRvGS+VpZKyTIiSszigbwrKoWgJ8xqyoHhrnX8+F3hk8wfDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:18.477179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b3d0f94ff7b37072e1f7413baf7036a75770fa74b418f39e93ac3d69eaca852","sha256:d368a59e0e89e34c09c3c7f3501df69d34fb9850c88bad940d1a884f587a435d"],"state_sha256":"11abb5d6dd160b99ee2b1eb3bd7becd5900daa7091e88bdbaf18983065bcac0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OIlU4tuuQRkwFFAaXkfJPYSDjJRlD+YUc8EWmFpBGiLNF8vah2HFOluWlsrS5RhWOMWca3asUy2FOQW+hFlqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:26:54.717209Z","bundle_sha256":"b9472597e7f05b0eeed67a2ae2419c9f989fc1baec2911b755461d5384950bd8"}}