{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RGAYVBZMU43WY7QQIQM2DOACBZ","short_pith_number":"pith:RGAYVBZM","canonical_record":{"source":{"id":"2206.09680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-20T09:42:50Z","cross_cats_sorted":[],"title_canon_sha256":"67fcd42939fa0f135d9dcd604901966c5460f898afa30c2f532b7dec5c70754a","abstract_canon_sha256":"585cca08088ef62da4952263172913de083e5aa76c83dba0e0932eddfdb9370b"},"schema_version":"1.0"},"canonical_sha256":"89818a872ca7376c7e104419a1b8020e5c4262564459aec4100a98498f4e1a36","source":{"kind":"arxiv","id":"2206.09680","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.09680","created_at":"2026-07-05T04:33:09Z"},{"alias_kind":"arxiv_version","alias_value":"2206.09680v1","created_at":"2026-07-05T04:33:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09680","created_at":"2026-07-05T04:33:09Z"},{"alias_kind":"pith_short_12","alias_value":"RGAYVBZMU43W","created_at":"2026-07-05T04:33:09Z"},{"alias_kind":"pith_short_16","alias_value":"RGAYVBZMU43WY7QQ","created_at":"2026-07-05T04:33:09Z"},{"alias_kind":"pith_short_8","alias_value":"RGAYVBZM","created_at":"2026-07-05T04:33:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RGAYVBZMU43WY7QQIQM2DOACBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2206.09680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-20T09:42:50Z","cross_cats_sorted":[],"title_canon_sha256":"67fcd42939fa0f135d9dcd604901966c5460f898afa30c2f532b7dec5c70754a","abstract_canon_sha256":"585cca08088ef62da4952263172913de083e5aa76c83dba0e0932eddfdb9370b"},"schema_version":"1.0"},"canonical_sha256":"89818a872ca7376c7e104419a1b8020e5c4262564459aec4100a98498f4e1a36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:09.804420Z","signature_b64":"zECHR+U9iRZ49XeeMe5AQXQ05p/HpB3Xy+PkUbJLwZJSgC2hWW6qq2salABU/mUyCo6fXK3pAyjmQiINqGdQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89818a872ca7376c7e104419a1b8020e5c4262564459aec4100a98498f4e1a36","last_reissued_at":"2026-07-05T04:33:09.803963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:09.803963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.09680","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":"2026-07-05T04:33:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rYCOh+T4pt4IbHr29l+okqwk3Da11eGumFMzWR8rq0p5kqlZDv4rNWeIkSNvky46lwCZN8Xj1CccVJRU6swmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:39:00.763680Z"},"content_sha256":"a84eec0ba4c1d61141e8c59852f8f8f76f4229749419147416a7104e86bc1d20","schema_version":"1.0","event_id":"sha256:a84eec0ba4c1d61141e8c59852f8f8f76f4229749419147416a7104e86bc1d20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RGAYVBZMU43WY7QQIQM2DOACBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Misspelling Semantics In Thai","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Matthew Purver, Pakawat Nakwijit","submitted_at":"2022-06-20T09:42:50Z","abstract_excerpt":"User-generated content is full of misspellings. Rather than being just random noise, we hypothesise that many misspellings contain hidden semantics that can be leveraged for language understanding tasks. This paper presents a fine-grained annotated corpus of misspelling in Thai, together with an analysis of misspelling intention and its possible semantics to get a better understanding of the misspelling patterns observed in the corpus. In addition, we introduce two approaches to incorporate the semantics of misspelling: Misspelling Average Embedding (MAE) and Misspelling Semantic Tokens (MST)."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09680","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/2206.09680/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":"2026-07-05T04:33:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PQZxKvGoQNLpG0phmy+S/R2OOaOMqQk7J7tM3ts/gs0+dJ2BEQBL7/zcD3vu/XoEfA6fedKXWoM70XA2tAZjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:39:00.764477Z"},"content_sha256":"29d2c50cd6094efe8ea2c51bf99ebfdd9b731cefa4aed3c177f14e428799792d","schema_version":"1.0","event_id":"sha256:29d2c50cd6094efe8ea2c51bf99ebfdd9b731cefa4aed3c177f14e428799792d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RGAYVBZMU43WY7QQIQM2DOACBZ/bundle.json","state_url":"https://pith.science/pith/RGAYVBZMU43WY7QQIQM2DOACBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RGAYVBZMU43WY7QQIQM2DOACBZ/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":"2026-08-17T20:39:00Z","links":{"resolver":"https://pith.science/pith/RGAYVBZMU43WY7QQIQM2DOACBZ","bundle":"https://pith.science/pith/RGAYVBZMU43WY7QQIQM2DOACBZ/bundle.json","state":"https://pith.science/pith/RGAYVBZMU43WY7QQIQM2DOACBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RGAYVBZMU43WY7QQIQM2DOACBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RGAYVBZMU43WY7QQIQM2DOACBZ","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":"585cca08088ef62da4952263172913de083e5aa76c83dba0e0932eddfdb9370b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-20T09:42:50Z","title_canon_sha256":"67fcd42939fa0f135d9dcd604901966c5460f898afa30c2f532b7dec5c70754a"},"schema_version":"1.0","source":{"id":"2206.09680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.09680","created_at":"2026-07-05T04:33:09Z"},{"alias_kind":"arxiv_version","alias_value":"2206.09680v1","created_at":"2026-07-05T04:33:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09680","created_at":"2026-07-05T04:33:09Z"},{"alias_kind":"pith_short_12","alias_value":"RGAYVBZMU43W","created_at":"2026-07-05T04:33:09Z"},{"alias_kind":"pith_short_16","alias_value":"RGAYVBZMU43WY7QQ","created_at":"2026-07-05T04:33:09Z"},{"alias_kind":"pith_short_8","alias_value":"RGAYVBZM","created_at":"2026-07-05T04:33:09Z"}],"graph_snapshots":[{"event_id":"sha256:29d2c50cd6094efe8ea2c51bf99ebfdd9b731cefa4aed3c177f14e428799792d","target":"graph","created_at":"2026-07-05T04:33:09Z","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/2206.09680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"User-generated content is full of misspellings. Rather than being just random noise, we hypothesise that many misspellings contain hidden semantics that can be leveraged for language understanding tasks. This paper presents a fine-grained annotated corpus of misspelling in Thai, together with an analysis of misspelling intention and its possible semantics to get a better understanding of the misspelling patterns observed in the corpus. In addition, we introduce two approaches to incorporate the semantics of misspelling: Misspelling Average Embedding (MAE) and Misspelling Semantic Tokens (MST).","authors_text":"Matthew Purver, Pakawat Nakwijit","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-20T09:42:50Z","title":"Misspelling Semantics In Thai"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09680","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:a84eec0ba4c1d61141e8c59852f8f8f76f4229749419147416a7104e86bc1d20","target":"record","created_at":"2026-07-05T04:33:09Z","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":"585cca08088ef62da4952263172913de083e5aa76c83dba0e0932eddfdb9370b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-20T09:42:50Z","title_canon_sha256":"67fcd42939fa0f135d9dcd604901966c5460f898afa30c2f532b7dec5c70754a"},"schema_version":"1.0","source":{"id":"2206.09680","kind":"arxiv","version":1}},"canonical_sha256":"89818a872ca7376c7e104419a1b8020e5c4262564459aec4100a98498f4e1a36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89818a872ca7376c7e104419a1b8020e5c4262564459aec4100a98498f4e1a36","first_computed_at":"2026-07-05T04:33:09.803963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:09.803963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zECHR+U9iRZ49XeeMe5AQXQ05p/HpB3Xy+PkUbJLwZJSgC2hWW6qq2salABU/mUyCo6fXK3pAyjmQiINqGdQDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:09.804420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.09680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a84eec0ba4c1d61141e8c59852f8f8f76f4229749419147416a7104e86bc1d20","sha256:29d2c50cd6094efe8ea2c51bf99ebfdd9b731cefa4aed3c177f14e428799792d"],"state_sha256":"04c487c23ca0f5c9761ffd451b16eb94cde320dafdbd869d7ae3e3830c55afa1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iUsfY2CSqzarVgkYlFm8oStxDpBZda6wrtQ6FgYSmC3RCAsnmFUPhY9n7mwSD5yf+sb5YxZ7wU6W4S5thD1uAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:39:00.830217Z","bundle_sha256":"72128cfb4cf5219dba4777a61cecaae9bfe87770efba6ebaaaffb4d0e4301f74"}}