{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BD2KMSCIKLPO4Q7GDOGHQ7CDPG","short_pith_number":"pith:BD2KMSCI","canonical_record":{"source":{"id":"2608.10109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T18:23:54Z","cross_cats_sorted":[],"title_canon_sha256":"da952138d3403e832066908de05bdcb06fc62cbfedfdeb6bcfff69240ac53a07","abstract_canon_sha256":"d1b60b1d990a2a5948cc486cee0d8d163d6d9e839f839211887ca85ad9227cc3"},"schema_version":"1.0"},"canonical_sha256":"08f4a6484852deee43e61b8c787c4379b404b4fbad94e39c08d3cce81a03ad31","source":{"kind":"arxiv","id":"2608.10109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10109","created_at":"2026-08-12T00:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10109v1","created_at":"2026-08-12T00:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10109","created_at":"2026-08-12T00:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"BD2KMSCIKLPO","created_at":"2026-08-12T00:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"BD2KMSCIKLPO4Q7G","created_at":"2026-08-12T00:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"BD2KMSCI","created_at":"2026-08-12T00:22:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BD2KMSCIKLPO4Q7GDOGHQ7CDPG","target":"record","payload":{"canonical_record":{"source":{"id":"2608.10109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T18:23:54Z","cross_cats_sorted":[],"title_canon_sha256":"da952138d3403e832066908de05bdcb06fc62cbfedfdeb6bcfff69240ac53a07","abstract_canon_sha256":"d1b60b1d990a2a5948cc486cee0d8d163d6d9e839f839211887ca85ad9227cc3"},"schema_version":"1.0"},"canonical_sha256":"08f4a6484852deee43e61b8c787c4379b404b4fbad94e39c08d3cce81a03ad31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T00:22:50.363774Z","signature_b64":"o0g+9esfBoGVTbMGvIshPjosgpADV7y+bqc4cKzs9P6+fdf1fAQIgIp4DMHe1dNxgJrGjpS8sDz74Gfmbq+MCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08f4a6484852deee43e61b8c787c4379b404b4fbad94e39c08d3cce81a03ad31","last_reissued_at":"2026-08-12T00:22:50.361728Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T00:22:50.361728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.10109","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":"2026-08-12T00:22:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3mAttkBx+x2XZCWvmqNSKs8jlqs3nDz4tzbWO6lr4Q1SiPt3auYSnbuETMwNCpibZFAEnG1ECheFlQrqrxNQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:49:56.982989Z"},"content_sha256":"351e7c7b65ad6af1c63589b40bec97918bc544273bcf573e1415397d582ad1ec","schema_version":"1.0","event_id":"sha256:351e7c7b65ad6af1c63589b40bec97918bc544273bcf573e1415397d582ad1ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BD2KMSCIKLPO4Q7GDOGHQ7CDPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PERCEPT: A Corpus for POS Tagging and Analysis of Persian-English Code-Mixing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amirarsalan Shahbazi, Behnam Bahrak, Ghazal Kalhor, Zahra Jafari","submitted_at":"2026-08-10T18:23:54Z","abstract_excerpt":"Social media has become a major venue for multilingual communication, where users frequently mix multiple languages within a single utterance. Although code-mixed corpora have been developed for several language pairs, Persian-English code-mixing remains relatively underexplored. Existing Persian resources lack Universal Dependencies (UD) part-of-speech (POS) annotations for code-mixed words, limiting both linguistic analyses and the development of syntax-aware NLP models. To address this gap, we introduce PERCEPT, the first publicly available large-scale Persian-English code-mixed corpus anno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10109","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/2608.10109/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":"2026-08-12T00:22:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IeSYgbh4bOto4FeXlgbCh8t8tw+Wn1CGoR7JUpjj7dRwnI/laAQGqmJtaxvbVYtdOP4AnfOPsWZfccyuauOFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:49:56.983494Z"},"content_sha256":"44f296ce305c56cd50bf3b2916bfc505be2263914dbf24cb43982f7ec523b715","schema_version":"1.0","event_id":"sha256:44f296ce305c56cd50bf3b2916bfc505be2263914dbf24cb43982f7ec523b715"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BD2KMSCIKLPO4Q7GDOGHQ7CDPG/bundle.json","state_url":"https://pith.science/pith/BD2KMSCIKLPO4Q7GDOGHQ7CDPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BD2KMSCIKLPO4Q7GDOGHQ7CDPG/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":"2026-08-18T20:49:56Z","links":{"resolver":"https://pith.science/pith/BD2KMSCIKLPO4Q7GDOGHQ7CDPG","bundle":"https://pith.science/pith/BD2KMSCIKLPO4Q7GDOGHQ7CDPG/bundle.json","state":"https://pith.science/pith/BD2KMSCIKLPO4Q7GDOGHQ7CDPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BD2KMSCIKLPO4Q7GDOGHQ7CDPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BD2KMSCIKLPO4Q7GDOGHQ7CDPG","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":"d1b60b1d990a2a5948cc486cee0d8d163d6d9e839f839211887ca85ad9227cc3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T18:23:54Z","title_canon_sha256":"da952138d3403e832066908de05bdcb06fc62cbfedfdeb6bcfff69240ac53a07"},"schema_version":"1.0","source":{"id":"2608.10109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10109","created_at":"2026-08-12T00:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10109v1","created_at":"2026-08-12T00:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10109","created_at":"2026-08-12T00:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"BD2KMSCIKLPO","created_at":"2026-08-12T00:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"BD2KMSCIKLPO4Q7G","created_at":"2026-08-12T00:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"BD2KMSCI","created_at":"2026-08-12T00:22:50Z"}],"graph_snapshots":[{"event_id":"sha256:44f296ce305c56cd50bf3b2916bfc505be2263914dbf24cb43982f7ec523b715","target":"graph","created_at":"2026-08-12T00:22:50Z","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/2608.10109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Social media has become a major venue for multilingual communication, where users frequently mix multiple languages within a single utterance. Although code-mixed corpora have been developed for several language pairs, Persian-English code-mixing remains relatively underexplored. Existing Persian resources lack Universal Dependencies (UD) part-of-speech (POS) annotations for code-mixed words, limiting both linguistic analyses and the development of syntax-aware NLP models. To address this gap, we introduce PERCEPT, the first publicly available large-scale Persian-English code-mixed corpus anno","authors_text":"Amirarsalan Shahbazi, Behnam Bahrak, Ghazal Kalhor, Zahra Jafari","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T18:23:54Z","title":"PERCEPT: A Corpus for POS Tagging and Analysis of Persian-English Code-Mixing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10109","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":"sha256:351e7c7b65ad6af1c63589b40bec97918bc544273bcf573e1415397d582ad1ec","target":"record","created_at":"2026-08-12T00:22:50Z","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":"d1b60b1d990a2a5948cc486cee0d8d163d6d9e839f839211887ca85ad9227cc3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T18:23:54Z","title_canon_sha256":"da952138d3403e832066908de05bdcb06fc62cbfedfdeb6bcfff69240ac53a07"},"schema_version":"1.0","source":{"id":"2608.10109","kind":"arxiv","version":1}},"canonical_sha256":"08f4a6484852deee43e61b8c787c4379b404b4fbad94e39c08d3cce81a03ad31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08f4a6484852deee43e61b8c787c4379b404b4fbad94e39c08d3cce81a03ad31","first_computed_at":"2026-08-12T00:22:50.361728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T00:22:50.361728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o0g+9esfBoGVTbMGvIshPjosgpADV7y+bqc4cKzs9P6+fdf1fAQIgIp4DMHe1dNxgJrGjpS8sDz74Gfmbq+MCQ==","signature_status":"signed_v1","signed_at":"2026-08-12T00:22:50.363774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:351e7c7b65ad6af1c63589b40bec97918bc544273bcf573e1415397d582ad1ec","sha256:44f296ce305c56cd50bf3b2916bfc505be2263914dbf24cb43982f7ec523b715"],"state_sha256":"1dc7ff3aa79797086a35cfa0122735e015ebe766b9d4f8898617b8a192eb4acc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQuuchn6CtXjiWhPN5T/d5XpFMQpsHxj+OJi5TmOpHGB3qkXyv/EDn3vQ4gcbVCNAtkkuDFbu3Yq1mqjK08hCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:49:56.988801Z","bundle_sha256":"aba0f952e9ac37ccb3f3f98875d7eb82db3d12bb5345119dd64e3d4d2175fffc"}}