{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7BMFS2J6RH7B4GLEZQ2VUWTWXZ","short_pith_number":"pith:7BMFS2J6","canonical_record":{"source":{"id":"2305.13658","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T04:02:54Z","cross_cats_sorted":[],"title_canon_sha256":"d556421a4839b49c337031ce3cf2a3f18407d3339fa936e47ffb64d6f6a46275","abstract_canon_sha256":"37728abdf680d5c870430a660d609f4d33dabfbb33f1373795099913769e06c7"},"schema_version":"1.0"},"canonical_sha256":"f85859693e89fe1e1964cc355a5a76be441ef9559a5a57000aa7ee2df502999e","source":{"kind":"arxiv","id":"2305.13658","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13658","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13658v2","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13658","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"7BMFS2J6RH7B","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"7BMFS2J6RH7B4GLE","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"7BMFS2J6","created_at":"2026-07-05T07:04:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7BMFS2J6RH7B4GLEZQ2VUWTWXZ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13658","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T04:02:54Z","cross_cats_sorted":[],"title_canon_sha256":"d556421a4839b49c337031ce3cf2a3f18407d3339fa936e47ffb64d6f6a46275","abstract_canon_sha256":"37728abdf680d5c870430a660d609f4d33dabfbb33f1373795099913769e06c7"},"schema_version":"1.0"},"canonical_sha256":"f85859693e89fe1e1964cc355a5a76be441ef9559a5a57000aa7ee2df502999e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:16.027893Z","signature_b64":"8TEB0avKM9aotzISM2JIDuMlDtY3AbyVZXRTXnMM2mARpht0SmFfQTS4HpURxA+W4X8Me2UH1nMjALMLgwoFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f85859693e89fe1e1964cc355a5a76be441ef9559a5a57000aa7ee2df502999e","last_reissued_at":"2026-07-05T07:04:16.027431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:16.027431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13658","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":"2026-07-05T07:04:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o2T2nIUWSjQg24NfHgDQaFPb/LvHgN4Qstj8grLI93mktMRoQq3sCYTonQzviT0pHElK8JPkW2+tztzMl+jzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:40:19.659153Z"},"content_sha256":"879259226a965b5924e099ba0b470d3cd443c904cfc86ef8709963a561ffb07a","schema_version":"1.0","event_id":"sha256:879259226a965b5924e099ba0b470d3cd443c904cfc86ef8709963a561ffb07a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7BMFS2J6RH7B4GLEZQ2VUWTWXZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Farhan Samir, Miikka Silfverberg","submitted_at":"2023-05-23T04:02:54Z","abstract_excerpt":"Data augmentation techniques are widely used in low-resource automatic morphological inflection to overcome data sparsity. However, the full implications of these techniques remain poorly understood. In this study, we aim to shed light on the theoretical aspects of the prominent data augmentation strategy StemCorrupt (Silfverberg et al., 2017; Anastasopoulos and Neubig, 2019), a method that generates synthetic examples by randomly substituting stem characters in gold standard training examples. To begin, we conduct an information-theoretic analysis, arguing that StemCorrupt improves compositio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13658","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/2305.13658/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":"2026-07-05T07:04:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JPvovDRNOw0yB3gp60H0smvcQV+kmMRneuaxM1EibQICThQl8b0HE3wWIyJ6mOGHLbyYDOyPbkDmqaSruuu+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:40:19.660046Z"},"content_sha256":"47feaea84780e4160cdb84c49fb0914fe07c976fb565e38ebd900545d84eb42c","schema_version":"1.0","event_id":"sha256:47feaea84780e4160cdb84c49fb0914fe07c976fb565e38ebd900545d84eb42c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7BMFS2J6RH7B4GLEZQ2VUWTWXZ/bundle.json","state_url":"https://pith.science/pith/7BMFS2J6RH7B4GLEZQ2VUWTWXZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7BMFS2J6RH7B4GLEZQ2VUWTWXZ/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":"2026-08-12T15:40:19Z","links":{"resolver":"https://pith.science/pith/7BMFS2J6RH7B4GLEZQ2VUWTWXZ","bundle":"https://pith.science/pith/7BMFS2J6RH7B4GLEZQ2VUWTWXZ/bundle.json","state":"https://pith.science/pith/7BMFS2J6RH7B4GLEZQ2VUWTWXZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7BMFS2J6RH7B4GLEZQ2VUWTWXZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7BMFS2J6RH7B4GLEZQ2VUWTWXZ","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":"37728abdf680d5c870430a660d609f4d33dabfbb33f1373795099913769e06c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T04:02:54Z","title_canon_sha256":"d556421a4839b49c337031ce3cf2a3f18407d3339fa936e47ffb64d6f6a46275"},"schema_version":"1.0","source":{"id":"2305.13658","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13658","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13658v2","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13658","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"7BMFS2J6RH7B","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"7BMFS2J6RH7B4GLE","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"7BMFS2J6","created_at":"2026-07-05T07:04:16Z"}],"graph_snapshots":[{"event_id":"sha256:47feaea84780e4160cdb84c49fb0914fe07c976fb565e38ebd900545d84eb42c","target":"graph","created_at":"2026-07-05T07:04:16Z","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/2305.13658/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation techniques are widely used in low-resource automatic morphological inflection to overcome data sparsity. However, the full implications of these techniques remain poorly understood. In this study, we aim to shed light on the theoretical aspects of the prominent data augmentation strategy StemCorrupt (Silfverberg et al., 2017; Anastasopoulos and Neubig, 2019), a method that generates synthetic examples by randomly substituting stem characters in gold standard training examples. To begin, we conduct an information-theoretic analysis, arguing that StemCorrupt improves compositio","authors_text":"Farhan Samir, Miikka Silfverberg","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T04:02:54Z","title":"Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13658","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":"sha256:879259226a965b5924e099ba0b470d3cd443c904cfc86ef8709963a561ffb07a","target":"record","created_at":"2026-07-05T07:04:16Z","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":"37728abdf680d5c870430a660d609f4d33dabfbb33f1373795099913769e06c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T04:02:54Z","title_canon_sha256":"d556421a4839b49c337031ce3cf2a3f18407d3339fa936e47ffb64d6f6a46275"},"schema_version":"1.0","source":{"id":"2305.13658","kind":"arxiv","version":2}},"canonical_sha256":"f85859693e89fe1e1964cc355a5a76be441ef9559a5a57000aa7ee2df502999e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f85859693e89fe1e1964cc355a5a76be441ef9559a5a57000aa7ee2df502999e","first_computed_at":"2026-07-05T07:04:16.027431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:16.027431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8TEB0avKM9aotzISM2JIDuMlDtY3AbyVZXRTXnMM2mARpht0SmFfQTS4HpURxA+W4X8Me2UH1nMjALMLgwoFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:16.027893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13658","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:879259226a965b5924e099ba0b470d3cd443c904cfc86ef8709963a561ffb07a","sha256:47feaea84780e4160cdb84c49fb0914fe07c976fb565e38ebd900545d84eb42c"],"state_sha256":"3ae3506376ade8656dd0465d7458a1327c0c52e6d67b8c58718beccb99c192de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9LZ5c7jnhCkoVckvHm8/xLdl0yJH76ZzrwQ0ZO9WqKsCb30HFr11CYmoaBzCzHXKG5cEteYozUQ665lVcxAlBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:40:19.665576Z","bundle_sha256":"69763556310f5b1fa00b4a6c299065d42405ccb546da901047f21f8c307b9ea9"}}