{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GYGD7RAXUZVVORQG6DP6RT43O2","short_pith_number":"pith:GYGD7RAX","canonical_record":{"source":{"id":"2005.00956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-03T00:35:19Z","cross_cats_sorted":[],"title_canon_sha256":"131e7464b382e81278d112d59d30c65eb33fe931628649d60f13d91630c1424c","abstract_canon_sha256":"9c57816eb03099d8ad35f6b78fbff93905795af84a6890f426cbdfbd8228d758"},"schema_version":"1.0"},"canonical_sha256":"360c3fc417a66b574606f0dfe8cf9b769b18f5ecab0f4ede99d0b73ab19e6403","source":{"kind":"arxiv","id":"2005.00956","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00956","created_at":"2026-07-05T01:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00956v1","created_at":"2026-07-05T01:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00956","created_at":"2026-07-05T01:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"GYGD7RAXUZVV","created_at":"2026-07-05T01:00:02Z"},{"alias_kind":"pith_short_16","alias_value":"GYGD7RAXUZVVORQG","created_at":"2026-07-05T01:00:02Z"},{"alias_kind":"pith_short_8","alias_value":"GYGD7RAX","created_at":"2026-07-05T01:00:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GYGD7RAXUZVVORQG6DP6RT43O2","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-03T00:35:19Z","cross_cats_sorted":[],"title_canon_sha256":"131e7464b382e81278d112d59d30c65eb33fe931628649d60f13d91630c1424c","abstract_canon_sha256":"9c57816eb03099d8ad35f6b78fbff93905795af84a6890f426cbdfbd8228d758"},"schema_version":"1.0"},"canonical_sha256":"360c3fc417a66b574606f0dfe8cf9b769b18f5ecab0f4ede99d0b73ab19e6403","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:02.613732Z","signature_b64":"CHIxJdcLSMrRiIyl6AbX9L6fq8ro/rwPKtHNr7m0ttq9Hmk0lv39YvYtOkPmEPBK/xKdTeJG36ZND6ircwlFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360c3fc417a66b574606f0dfe8cf9b769b18f5ecab0f4ede99d0b73ab19e6403","last_reissued_at":"2026-07-05T01:00:02.613266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:02.613266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00956","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":"2026-07-05T01:00:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6NaGIvwL4VdQTDRQi0m0j2f89VOYwR1fmIt9YZNEfb51NaZI6dvtkbDfNyxQtoOjNDVE0nOYnK/68C169DcvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:05:10.531577Z"},"content_sha256":"68944d32c8c2fd82fafc039f91d923af32f3e911098e7feee9d81377854a30e2","schema_version":"1.0","event_id":"sha256:68944d32c8c2fd82fafc039f91d923af32f3e911098e7feee9d81377854a30e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GYGD7RAXUZVVORQG6DP6RT43O2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bootstrapping Techniques for Polysynthetic Morphological Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Steven Bird, William Lane","submitted_at":"2020-05-03T00:35:19Z","abstract_excerpt":"Polysynthetic languages have exceptionally large and sparse vocabularies, thanks to the number of morpheme slots and combinations in a word. This complexity, together with a general scarcity of written data, poses a challenge to the development of natural language technologies. To address this challenge, we offer linguistically-informed approaches for bootstrapping a neural morphological analyzer, and demonstrate its application to Kunwinjku, a polysynthetic Australian language. We generate data from a finite state transducer to train an encoder-decoder model. We improve the model by \"hallucin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00956","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/2005.00956/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":"2026-07-05T01:00:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WjpQ+/V8MwJ4xWe/HGtOIKkayyARWLWvm/mnwE58V5fhegsFuYsqHiETKtPvdpCVFCyMRtE2K7buaQNwTIEaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:05:10.532510Z"},"content_sha256":"3c394d7ef0b2275cf22228b886fda2c8986f9234a5ed12f160500eb175a982e1","schema_version":"1.0","event_id":"sha256:3c394d7ef0b2275cf22228b886fda2c8986f9234a5ed12f160500eb175a982e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2/bundle.json","state_url":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYGD7RAXUZVVORQG6DP6RT43O2/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":"2026-08-05T10:05:10Z","links":{"resolver":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2","bundle":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2/bundle.json","state":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYGD7RAXUZVVORQG6DP6RT43O2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GYGD7RAXUZVVORQG6DP6RT43O2","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":"9c57816eb03099d8ad35f6b78fbff93905795af84a6890f426cbdfbd8228d758","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-03T00:35:19Z","title_canon_sha256":"131e7464b382e81278d112d59d30c65eb33fe931628649d60f13d91630c1424c"},"schema_version":"1.0","source":{"id":"2005.00956","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00956","created_at":"2026-07-05T01:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00956v1","created_at":"2026-07-05T01:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00956","created_at":"2026-07-05T01:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"GYGD7RAXUZVV","created_at":"2026-07-05T01:00:02Z"},{"alias_kind":"pith_short_16","alias_value":"GYGD7RAXUZVVORQG","created_at":"2026-07-05T01:00:02Z"},{"alias_kind":"pith_short_8","alias_value":"GYGD7RAX","created_at":"2026-07-05T01:00:02Z"}],"graph_snapshots":[{"event_id":"sha256:3c394d7ef0b2275cf22228b886fda2c8986f9234a5ed12f160500eb175a982e1","target":"graph","created_at":"2026-07-05T01:00:02Z","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/2005.00956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Polysynthetic languages have exceptionally large and sparse vocabularies, thanks to the number of morpheme slots and combinations in a word. This complexity, together with a general scarcity of written data, poses a challenge to the development of natural language technologies. To address this challenge, we offer linguistically-informed approaches for bootstrapping a neural morphological analyzer, and demonstrate its application to Kunwinjku, a polysynthetic Australian language. We generate data from a finite state transducer to train an encoder-decoder model. We improve the model by \"hallucin","authors_text":"Steven Bird, William Lane","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-03T00:35:19Z","title":"Bootstrapping Techniques for Polysynthetic Morphological Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00956","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":"sha256:68944d32c8c2fd82fafc039f91d923af32f3e911098e7feee9d81377854a30e2","target":"record","created_at":"2026-07-05T01:00:02Z","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":"9c57816eb03099d8ad35f6b78fbff93905795af84a6890f426cbdfbd8228d758","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-03T00:35:19Z","title_canon_sha256":"131e7464b382e81278d112d59d30c65eb33fe931628649d60f13d91630c1424c"},"schema_version":"1.0","source":{"id":"2005.00956","kind":"arxiv","version":1}},"canonical_sha256":"360c3fc417a66b574606f0dfe8cf9b769b18f5ecab0f4ede99d0b73ab19e6403","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"360c3fc417a66b574606f0dfe8cf9b769b18f5ecab0f4ede99d0b73ab19e6403","first_computed_at":"2026-07-05T01:00:02.613266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:02.613266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CHIxJdcLSMrRiIyl6AbX9L6fq8ro/rwPKtHNr7m0ttq9Hmk0lv39YvYtOkPmEPBK/xKdTeJG36ZND6ircwlFBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:02.613732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00956","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68944d32c8c2fd82fafc039f91d923af32f3e911098e7feee9d81377854a30e2","sha256:3c394d7ef0b2275cf22228b886fda2c8986f9234a5ed12f160500eb175a982e1"],"state_sha256":"165f1595c7b941e9c3d2c7ac5629cd69fe1b1adac8494c641712a1b43ee612a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GWZ2bngOoEv/Y/8NeYIQBTe4DVZKSQUwo1iav7hQjUFrlJysb8PXxbF6Bklg5kB9On713tY71eTCG1gr5F1CCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:05:10.591641Z","bundle_sha256":"428ae3c9b5131ce2782734294d079c1c78758c36a832351038c65598a881d4f9"}}