{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:L2RMGFTMUIPTVQ7T5F55Y7SX46","short_pith_number":"pith:L2RMGFTM","canonical_record":{"source":{"id":"2012.11657","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-21T19:47:04Z","cross_cats_sorted":[],"title_canon_sha256":"c98dda0d105f2d3a15c01b75c95ad7caaace67e692e7c98280f3e9198882e5f9","abstract_canon_sha256":"dbe86ec798881055aba4d0c4ea34d0e8f0c9a839c040519c5a26d5741f95f643"},"schema_version":"1.0"},"canonical_sha256":"5ea2c3166ca21f3ac3f3e97bdc7e57e7b5297999989c6b412c0873a48bcfa1f4","source":{"kind":"arxiv","id":"2012.11657","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.11657","created_at":"2026-07-05T02:49:52Z"},{"alias_kind":"arxiv_version","alias_value":"2012.11657v2","created_at":"2026-07-05T02:49:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11657","created_at":"2026-07-05T02:49:52Z"},{"alias_kind":"pith_short_12","alias_value":"L2RMGFTMUIPT","created_at":"2026-07-05T02:49:52Z"},{"alias_kind":"pith_short_16","alias_value":"L2RMGFTMUIPTVQ7T","created_at":"2026-07-05T02:49:52Z"},{"alias_kind":"pith_short_8","alias_value":"L2RMGFTM","created_at":"2026-07-05T02:49:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:L2RMGFTMUIPTVQ7T5F55Y7SX46","target":"record","payload":{"canonical_record":{"source":{"id":"2012.11657","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-21T19:47:04Z","cross_cats_sorted":[],"title_canon_sha256":"c98dda0d105f2d3a15c01b75c95ad7caaace67e692e7c98280f3e9198882e5f9","abstract_canon_sha256":"dbe86ec798881055aba4d0c4ea34d0e8f0c9a839c040519c5a26d5741f95f643"},"schema_version":"1.0"},"canonical_sha256":"5ea2c3166ca21f3ac3f3e97bdc7e57e7b5297999989c6b412c0873a48bcfa1f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:52.295795Z","signature_b64":"EB3sN++5MlODjX+4F55TBwJcgL8AxyQGWmR4AcJYKxBz0iv79aajBe2Z+S9G0poMKIi7SakBf4zciI3zq4IrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ea2c3166ca21f3ac3f3e97bdc7e57e7b5297999989c6b412c0873a48bcfa1f4","last_reissued_at":"2026-07-05T02:49:52.295302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:52.295302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.11657","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:49:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ob6v2fn3pHgEqOE9EVfMdQBFIKt3tVleqlLEtnP9efLuPRB02VCA6fwCjAsWuWdoVu8TI0N7bQPTEQuEYVq6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:49:58.437894Z"},"content_sha256":"500155a3ca0d0d487f557e96d97a9a5fc548e412bffa2899ddac061d4249581f","schema_version":"1.0","event_id":"sha256:500155a3ca0d0d487f557e96d97a9a5fc548e412bffa2899ddac061d4249581f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:L2RMGFTMUIPTVQ7T5F55Y7SX46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Subword Sampling for Low Resource Word Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher Ringlstetter, Ehsaneddin Asgari, Hinrich Sch\\\"utze, Masoud Jalili Sabet, Philipp Dufter","submitted_at":"2020-12-21T19:47:04Z","abstract_excerpt":"Annotation projection is an important area in NLP that can greatly contribute to creating language resources for low-resource languages. Word alignment plays a key role in this setting. However, most of the existing word alignment methods are designed for a high resource setting in machine translation where millions of parallel sentences are available. This amount reduces to a few thousands of sentences when dealing with low-resource languages failing the existing established IBM models. In this paper, we propose subword sampling-based alignment of text units. This method's hypothesis is that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11657","kind":"arxiv","version":2},"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/2012.11657/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":"2026-07-05T02:49:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jmmULmJY8BB2wgpKMSf2mHZ6NkMdIEgD+kkZIu536j+S+/OdMC7DuJ7RME2qorBvuQdfMHNvUQy7Ivi0zggGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:49:58.438401Z"},"content_sha256":"a98000b9140f17ec91383e14bac84095030fe93929305102ec14dded3a0b742a","schema_version":"1.0","event_id":"sha256:a98000b9140f17ec91383e14bac84095030fe93929305102ec14dded3a0b742a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/bundle.json","state_url":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/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":"2026-08-11T14:49:58Z","links":{"resolver":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46","bundle":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/bundle.json","state":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:L2RMGFTMUIPTVQ7T5F55Y7SX46","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":"dbe86ec798881055aba4d0c4ea34d0e8f0c9a839c040519c5a26d5741f95f643","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-21T19:47:04Z","title_canon_sha256":"c98dda0d105f2d3a15c01b75c95ad7caaace67e692e7c98280f3e9198882e5f9"},"schema_version":"1.0","source":{"id":"2012.11657","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.11657","created_at":"2026-07-05T02:49:52Z"},{"alias_kind":"arxiv_version","alias_value":"2012.11657v2","created_at":"2026-07-05T02:49:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11657","created_at":"2026-07-05T02:49:52Z"},{"alias_kind":"pith_short_12","alias_value":"L2RMGFTMUIPT","created_at":"2026-07-05T02:49:52Z"},{"alias_kind":"pith_short_16","alias_value":"L2RMGFTMUIPTVQ7T","created_at":"2026-07-05T02:49:52Z"},{"alias_kind":"pith_short_8","alias_value":"L2RMGFTM","created_at":"2026-07-05T02:49:52Z"}],"graph_snapshots":[{"event_id":"sha256:a98000b9140f17ec91383e14bac84095030fe93929305102ec14dded3a0b742a","target":"graph","created_at":"2026-07-05T02:49:52Z","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/2012.11657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Annotation projection is an important area in NLP that can greatly contribute to creating language resources for low-resource languages. Word alignment plays a key role in this setting. However, most of the existing word alignment methods are designed for a high resource setting in machine translation where millions of parallel sentences are available. This amount reduces to a few thousands of sentences when dealing with low-resource languages failing the existing established IBM models. In this paper, we propose subword sampling-based alignment of text units. This method's hypothesis is that ","authors_text":"Christopher Ringlstetter, Ehsaneddin Asgari, Hinrich Sch\\\"utze, Masoud Jalili Sabet, Philipp Dufter","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-21T19:47:04Z","title":"Subword Sampling for Low Resource Word Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11657","kind":"arxiv","version":2},"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":"sha256:500155a3ca0d0d487f557e96d97a9a5fc548e412bffa2899ddac061d4249581f","target":"record","created_at":"2026-07-05T02:49:52Z","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":"dbe86ec798881055aba4d0c4ea34d0e8f0c9a839c040519c5a26d5741f95f643","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-21T19:47:04Z","title_canon_sha256":"c98dda0d105f2d3a15c01b75c95ad7caaace67e692e7c98280f3e9198882e5f9"},"schema_version":"1.0","source":{"id":"2012.11657","kind":"arxiv","version":2}},"canonical_sha256":"5ea2c3166ca21f3ac3f3e97bdc7e57e7b5297999989c6b412c0873a48bcfa1f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ea2c3166ca21f3ac3f3e97bdc7e57e7b5297999989c6b412c0873a48bcfa1f4","first_computed_at":"2026-07-05T02:49:52.295302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:52.295302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EB3sN++5MlODjX+4F55TBwJcgL8AxyQGWmR4AcJYKxBz0iv79aajBe2Z+S9G0poMKIi7SakBf4zciI3zq4IrBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:52.295795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.11657","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:500155a3ca0d0d487f557e96d97a9a5fc548e412bffa2899ddac061d4249581f","sha256:a98000b9140f17ec91383e14bac84095030fe93929305102ec14dded3a0b742a"],"state_sha256":"e6eb7cdc0085b08eb7f89390e95b412a374fc6e43d292d54f4f6ffc1ced126a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TGzjUz4WLg8V4g/jgberRy/bfA1xXHmM7lSPprxCCsSayJciHJ1bY+1Dj7uIklGCGJsOvppq1VVxTCytdNpiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:49:58.443571Z","bundle_sha256":"a4ff708b8fa7844c2eb061280ad3259892228a1b1d3088aee89917dc2a877e09"}}