{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:AV2MLYARIGDGHLDRALJRKM7NZR","short_pith_number":"pith:AV2MLYAR","canonical_record":{"source":{"id":"1410.8149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-29T20:07:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"35d3151dd0f36ee89b258e6f6c11c4c20fde951ec4a422085013a19f4b73066f","abstract_canon_sha256":"bb344de9d0a745f5a97eec736fa8a9b72c1821cfb043d05d61c2d3163d2603e6"},"schema_version":"1.0"},"canonical_sha256":"0574c5e011418663ac7102d31533edcc416edad83d6d6d20837d788e42ff962b","source":{"kind":"arxiv","id":"1410.8149","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.8149","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"1410.8149v1","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.8149","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"AV2MLYARIGDG","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"AV2MLYARIGDGHLDR","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"AV2MLYAR","created_at":"2026-05-18T12:28:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:AV2MLYARIGDGHLDRALJRKM7NZR","target":"record","payload":{"canonical_record":{"source":{"id":"1410.8149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-29T20:07:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"35d3151dd0f36ee89b258e6f6c11c4c20fde951ec4a422085013a19f4b73066f","abstract_canon_sha256":"bb344de9d0a745f5a97eec736fa8a9b72c1821cfb043d05d61c2d3163d2603e6"},"schema_version":"1.0"},"canonical_sha256":"0574c5e011418663ac7102d31533edcc416edad83d6d6d20837d788e42ff962b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:29.810137Z","signature_b64":"qB+9a6kHF0hmsBYedKWq0+6AZVptE16BiJEsLsibEJv/5kOUjaFrmupsJKpkSyt9++FJam3Ulq0BRHXEKi05AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0574c5e011418663ac7102d31533edcc416edad83d6d6d20837d788e42ff962b","last_reissued_at":"2026-05-18T01:20:29.809553Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:29.809553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1410.8149","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":"2026-05-18T01:20:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C/Daar60MyFwcaZX4hROzPHdy1zoQ0BnkRb+U34Y138OTJSuymnu43Zvw8KiRKdW3aznXJJld9gfdxvxZ2G7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:35:18.583547Z"},"content_sha256":"d34131c435ba281126432fadc8f0fd60722ca7cdbd4e8a2eff36b2d02a10e574","schema_version":"1.0","event_id":"sha256:d34131c435ba281126432fadc8f0fd60722ca7cdbd4e8a2eff36b2d02a10e574"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:AV2MLYARIGDGHLDRALJRKM7NZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detecting Structural Irregularity in Electronic Dictionaries Using Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"David Doermann, David Zajic, Michael Bloodgood, Paul Rodrigues, Peng Ye","submitted_at":"2014-10-29T20:07:21Z","abstract_excerpt":"Dictionaries are often developed using tools that save to Extensible Markup Language (XML)-based standards. These standards often allow high-level repeating elements to represent lexical entries, and utilize descendants of these repeating elements to represent the structure within each lexical entry, in the form of an XML tree. In many cases, dictionaries are published that have errors and inconsistencies that are expensive to find manually. This paper discusses a method for dictionary writers to quickly audit structural regularity across entries in a dictionary by using statistical language m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.8149","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":""},"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":"2026-05-18T01:20:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8AubO/9X4Ggdbb1qhRcEgNZSoC/DGrNAFWYKHba4idYiYscbq/kjtoWkQYfPO4a5YyEaIyHBZA9Up1vu8EMLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:35:18.584200Z"},"content_sha256":"6a33b67dcf680f10bb156cc6443073acf8029d14763fa1b9d94071db898273e1","schema_version":"1.0","event_id":"sha256:6a33b67dcf680f10bb156cc6443073acf8029d14763fa1b9d94071db898273e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AV2MLYARIGDGHLDRALJRKM7NZR/bundle.json","state_url":"https://pith.science/pith/AV2MLYARIGDGHLDRALJRKM7NZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AV2MLYARIGDGHLDRALJRKM7NZR/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":"2026-05-30T12:35:18Z","links":{"resolver":"https://pith.science/pith/AV2MLYARIGDGHLDRALJRKM7NZR","bundle":"https://pith.science/pith/AV2MLYARIGDGHLDRALJRKM7NZR/bundle.json","state":"https://pith.science/pith/AV2MLYARIGDGHLDRALJRKM7NZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AV2MLYARIGDGHLDRALJRKM7NZR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:AV2MLYARIGDGHLDRALJRKM7NZR","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":"bb344de9d0a745f5a97eec736fa8a9b72c1821cfb043d05d61c2d3163d2603e6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-29T20:07:21Z","title_canon_sha256":"35d3151dd0f36ee89b258e6f6c11c4c20fde951ec4a422085013a19f4b73066f"},"schema_version":"1.0","source":{"id":"1410.8149","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.8149","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"1410.8149v1","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.8149","created_at":"2026-05-18T01:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"AV2MLYARIGDG","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"AV2MLYARIGDGHLDR","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"AV2MLYAR","created_at":"2026-05-18T12:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:6a33b67dcf680f10bb156cc6443073acf8029d14763fa1b9d94071db898273e1","target":"graph","created_at":"2026-05-18T01:20:29Z","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"},"paper":{"abstract_excerpt":"Dictionaries are often developed using tools that save to Extensible Markup Language (XML)-based standards. These standards often allow high-level repeating elements to represent lexical entries, and utilize descendants of these repeating elements to represent the structure within each lexical entry, in the form of an XML tree. In many cases, dictionaries are published that have errors and inconsistencies that are expensive to find manually. This paper discusses a method for dictionary writers to quickly audit structural regularity across entries in a dictionary by using statistical language m","authors_text":"David Doermann, David Zajic, Michael Bloodgood, Paul Rodrigues, Peng Ye","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-29T20:07:21Z","title":"Detecting Structural Irregularity in Electronic Dictionaries Using Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.8149","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:d34131c435ba281126432fadc8f0fd60722ca7cdbd4e8a2eff36b2d02a10e574","target":"record","created_at":"2026-05-18T01:20:29Z","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":"bb344de9d0a745f5a97eec736fa8a9b72c1821cfb043d05d61c2d3163d2603e6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-29T20:07:21Z","title_canon_sha256":"35d3151dd0f36ee89b258e6f6c11c4c20fde951ec4a422085013a19f4b73066f"},"schema_version":"1.0","source":{"id":"1410.8149","kind":"arxiv","version":1}},"canonical_sha256":"0574c5e011418663ac7102d31533edcc416edad83d6d6d20837d788e42ff962b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0574c5e011418663ac7102d31533edcc416edad83d6d6d20837d788e42ff962b","first_computed_at":"2026-05-18T01:20:29.809553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:29.809553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qB+9a6kHF0hmsBYedKWq0+6AZVptE16BiJEsLsibEJv/5kOUjaFrmupsJKpkSyt9++FJam3Ulq0BRHXEKi05AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:29.810137Z","signed_message":"canonical_sha256_bytes"},"source_id":"1410.8149","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d34131c435ba281126432fadc8f0fd60722ca7cdbd4e8a2eff36b2d02a10e574","sha256:6a33b67dcf680f10bb156cc6443073acf8029d14763fa1b9d94071db898273e1"],"state_sha256":"e7c4ed728a8428d734dcdcca69ada699bcc14ed1e830aa96379d6b2cbd926862"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7zvwHSutlptFERrpX8Ukoix8ue6p6IBiyM97nuW94/FaTh872J3I85tGjO8HxDL34y9UrHC/UyItdALON1AJBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:35:18.587965Z","bundle_sha256":"d061cd2d84b55c224ca039d3b2a8565be98dfe0857aa88876ce885780eb29c16"}}