{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EBDWRJFUHP2IASMEBXPDW7DPOM","short_pith_number":"pith:EBDWRJFU","canonical_record":{"source":{"id":"2405.18308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T16:01:19Z","cross_cats_sorted":[],"title_canon_sha256":"047f82a042b15d3933d4d81dfde7bb039be3d72a3c86b8a60d91c716b2d4b94d","abstract_canon_sha256":"4c1f33e91ab49cc06463a9944039383fdb34054441de2ea9c61d433a84b7c5e5"},"schema_version":"1.0"},"canonical_sha256":"204768a4b43bf48049840dde3b7c6f7314659138ca24aa05f92c0f68cdc2fbe5","source":{"kind":"arxiv","id":"2405.18308","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18308","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18308v1","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18308","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"EBDWRJFUHP2I","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"EBDWRJFUHP2IASME","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"EBDWRJFU","created_at":"2026-07-05T08:24:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EBDWRJFUHP2IASMEBXPDW7DPOM","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T16:01:19Z","cross_cats_sorted":[],"title_canon_sha256":"047f82a042b15d3933d4d81dfde7bb039be3d72a3c86b8a60d91c716b2d4b94d","abstract_canon_sha256":"4c1f33e91ab49cc06463a9944039383fdb34054441de2ea9c61d433a84b7c5e5"},"schema_version":"1.0"},"canonical_sha256":"204768a4b43bf48049840dde3b7c6f7314659138ca24aa05f92c0f68cdc2fbe5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:18.273811Z","signature_b64":"a7Lgi8Unh7aGACXin9f6zgkoPi//3ddlZ4n98AfZqwJS2NF5CJmts4sU7KhF7rzblYxRNBl+MCR+ftzmRg/GCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"204768a4b43bf48049840dde3b7c6f7314659138ca24aa05f92c0f68cdc2fbe5","last_reissued_at":"2026-07-05T08:24:18.273373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:18.273373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18308","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":"2026-07-05T08:24:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w/b0vOJtqChSvH8CDUansrV9pYMqf+Le1UBFVRtYuXvP5HaV6QFT8qYmu7baW4BFeuKuh9J2ovF2XgQ83yHgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:10:46.123208Z"},"content_sha256":"3a99dbf6be6ef326bc57d738358ed6fc4ecd6ecb49e9a932a84b9e0bf56167c4","schema_version":"1.0","event_id":"sha256:3a99dbf6be6ef326bc57d738358ed6fc4ecd6ecb49e9a932a84b9e0bf56167c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EBDWRJFUHP2IASMEBXPDW7DPOM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Lemmatization and Morphological Tagging with LEMMING","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Fraser, Hinrich Sch\\\"utze, Ryan Cotterell, Thomas Muller","submitted_at":"2024-05-28T16:01:19Z","abstract_excerpt":"We present LEMMING, a modular log-linear model that jointly models lemmatization and tagging and supports the integration of arbitrary global features. It is trainable on corpora annotated with gold standard tags and lemmata and does not rely on morphological dictionaries or analyzers. LEMMING sets the new state of the art in token-based statistical lemmatization on six languages; e.g., for Czech lemmatization, we reduce the error by 60%, from 4.05 to 1.58. We also give empirical evidence that jointly modeling morphological tags and lemmata is mutually beneficial."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18308","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/2405.18308/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":"2026-07-05T08:24:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R2nnyIcaYI0fi1ULPXgb62L2Yo2dRfYftVTK8rlZEL3PRfMsZR+k7/4D3AsWNb3LL86hOuOjxoZB5aZmMPnuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:10:46.124131Z"},"content_sha256":"111610e031e2074c4e435cde6ed48272045e156e098e498249ad5b6241caed5f","schema_version":"1.0","event_id":"sha256:111610e031e2074c4e435cde6ed48272045e156e098e498249ad5b6241caed5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBDWRJFUHP2IASMEBXPDW7DPOM/bundle.json","state_url":"https://pith.science/pith/EBDWRJFUHP2IASMEBXPDW7DPOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBDWRJFUHP2IASMEBXPDW7DPOM/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":"2026-08-08T09:10:46Z","links":{"resolver":"https://pith.science/pith/EBDWRJFUHP2IASMEBXPDW7DPOM","bundle":"https://pith.science/pith/EBDWRJFUHP2IASMEBXPDW7DPOM/bundle.json","state":"https://pith.science/pith/EBDWRJFUHP2IASMEBXPDW7DPOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBDWRJFUHP2IASMEBXPDW7DPOM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EBDWRJFUHP2IASMEBXPDW7DPOM","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":"4c1f33e91ab49cc06463a9944039383fdb34054441de2ea9c61d433a84b7c5e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T16:01:19Z","title_canon_sha256":"047f82a042b15d3933d4d81dfde7bb039be3d72a3c86b8a60d91c716b2d4b94d"},"schema_version":"1.0","source":{"id":"2405.18308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18308","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18308v1","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18308","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"EBDWRJFUHP2I","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"EBDWRJFUHP2IASME","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"EBDWRJFU","created_at":"2026-07-05T08:24:18Z"}],"graph_snapshots":[{"event_id":"sha256:111610e031e2074c4e435cde6ed48272045e156e098e498249ad5b6241caed5f","target":"graph","created_at":"2026-07-05T08:24:18Z","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/2405.18308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present LEMMING, a modular log-linear model that jointly models lemmatization and tagging and supports the integration of arbitrary global features. It is trainable on corpora annotated with gold standard tags and lemmata and does not rely on morphological dictionaries or analyzers. LEMMING sets the new state of the art in token-based statistical lemmatization on six languages; e.g., for Czech lemmatization, we reduce the error by 60%, from 4.05 to 1.58. We also give empirical evidence that jointly modeling morphological tags and lemmata is mutually beneficial.","authors_text":"Alexander Fraser, Hinrich Sch\\\"utze, Ryan Cotterell, Thomas Muller","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T16:01:19Z","title":"Joint Lemmatization and Morphological Tagging with LEMMING"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18308","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":"sha256:3a99dbf6be6ef326bc57d738358ed6fc4ecd6ecb49e9a932a84b9e0bf56167c4","target":"record","created_at":"2026-07-05T08:24:18Z","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":"4c1f33e91ab49cc06463a9944039383fdb34054441de2ea9c61d433a84b7c5e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T16:01:19Z","title_canon_sha256":"047f82a042b15d3933d4d81dfde7bb039be3d72a3c86b8a60d91c716b2d4b94d"},"schema_version":"1.0","source":{"id":"2405.18308","kind":"arxiv","version":1}},"canonical_sha256":"204768a4b43bf48049840dde3b7c6f7314659138ca24aa05f92c0f68cdc2fbe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"204768a4b43bf48049840dde3b7c6f7314659138ca24aa05f92c0f68cdc2fbe5","first_computed_at":"2026-07-05T08:24:18.273373Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:18.273373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a7Lgi8Unh7aGACXin9f6zgkoPi//3ddlZ4n98AfZqwJS2NF5CJmts4sU7KhF7rzblYxRNBl+MCR+ftzmRg/GCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:18.273811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a99dbf6be6ef326bc57d738358ed6fc4ecd6ecb49e9a932a84b9e0bf56167c4","sha256:111610e031e2074c4e435cde6ed48272045e156e098e498249ad5b6241caed5f"],"state_sha256":"d987f04d04501a966683e0463af8de164e07a56bef7a9fdf2c591b8654b4af6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UA982lFeCGlXVTEM0PvJ/zqO+A/O11+EibFxY2WLMd48G5m4IC+prR4/XaF8aTCAGXXIOaWdIe9LOIhRr0grBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:10:46.130416Z","bundle_sha256":"12dcd49834083d37a6674318095cf75fc08d8ace2d6887f79289c342af961143"}}