{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YGKQTCQV4GZXS7UTUFV4Y4F46V","short_pith_number":"pith:YGKQTCQV","canonical_record":{"source":{"id":"2211.07514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T16:45:30Z","cross_cats_sorted":[],"title_canon_sha256":"3d9d9652eda6f64d8d1e57d84723e46b1e00f17904fdcfabd48e65794eb65537","abstract_canon_sha256":"d6079ad754bc8fae643b756de0c2e02ead6984e2231862f7bbad9d87911d361b"},"schema_version":"1.0"},"canonical_sha256":"c195098a15e1b3797e93a16bcc70bcf55b41be0d3e21c2026a5fb7ecaa48007f","source":{"kind":"arxiv","id":"2211.07514","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.07514","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"arxiv_version","alias_value":"2211.07514v1","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07514","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"pith_short_12","alias_value":"YGKQTCQV4GZX","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"pith_short_16","alias_value":"YGKQTCQV4GZXS7UT","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"pith_short_8","alias_value":"YGKQTCQV","created_at":"2026-07-05T05:15:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YGKQTCQV4GZXS7UTUFV4Y4F46V","target":"record","payload":{"canonical_record":{"source":{"id":"2211.07514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T16:45:30Z","cross_cats_sorted":[],"title_canon_sha256":"3d9d9652eda6f64d8d1e57d84723e46b1e00f17904fdcfabd48e65794eb65537","abstract_canon_sha256":"d6079ad754bc8fae643b756de0c2e02ead6984e2231862f7bbad9d87911d361b"},"schema_version":"1.0"},"canonical_sha256":"c195098a15e1b3797e93a16bcc70bcf55b41be0d3e21c2026a5fb7ecaa48007f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:54.437276Z","signature_b64":"wWEO3s0mkfDXKtSszWKYN6Txl06KDBXZJZaLzWKcROQpZlHyKqk7G8W83cxFyv4bNTo+QoP48XuwhmppmPtwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c195098a15e1b3797e93a16bcc70bcf55b41be0d3e21c2026a5fb7ecaa48007f","last_reissued_at":"2026-07-05T05:15:54.436860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:54.436860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.07514","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":"2026-07-05T05:15:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VgwrUYuUzP559N6PnOd0xaAdJUnb77vKEJ2VjXu2r1U9SjvbNc36yP/Av4EDnzwTQcGxbPanvSQ1UhOLtd07Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:14:52.866773Z"},"content_sha256":"bcf6823fd5117144461a3723187b30ebde5540b22062c22d0e00e92194c380d3","schema_version":"1.0","event_id":"sha256:bcf6823fd5117144461a3723187b30ebde5540b22062c22d0e00e92194c380d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YGKQTCQV4GZXS7UTUFV4Y4F46V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CST5: Data Augmentation for Code-Switched Semantic Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anmol Agarwal, Jigar Gupta, Pankaj Joshi, Rahul Goel, Rengarajan Aravamudhan, Shyam Upadhyay","submitted_at":"2022-11-14T16:45:30Z","abstract_excerpt":"Extending semantic parsers to code-switched input has been a challenging problem, primarily due to a lack of supervised training data. In this work, we introduce CST5, a new data augmentation technique that finetunes a T5 model using a small seed set ($\\approx$100 utterances) to generate code-switched utterances from English utterances. We show that CST5 generates high quality code-switched data, both intrinsically (per human evaluation) and extrinsically by comparing baseline models which are trained without data augmentation to models which are trained with augmented data. Empirically we obs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07514","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/2211.07514/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":"2026-07-05T05:15:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W2M8tIVixh0qI4nqaWaSCW+nuH+y+/Jfe2WGrTOsLyRO8/tmpYkMbWzgBrCI1Q99mQnOj9qJO4KGhFvbrAyUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:14:52.867151Z"},"content_sha256":"782d6dfeeef86b4ce1eab3500b07948aa9d9fac8525bdb377d27637eab4ced99","schema_version":"1.0","event_id":"sha256:782d6dfeeef86b4ce1eab3500b07948aa9d9fac8525bdb377d27637eab4ced99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YGKQTCQV4GZXS7UTUFV4Y4F46V/bundle.json","state_url":"https://pith.science/pith/YGKQTCQV4GZXS7UTUFV4Y4F46V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YGKQTCQV4GZXS7UTUFV4Y4F46V/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":"2026-08-17T23:14:52Z","links":{"resolver":"https://pith.science/pith/YGKQTCQV4GZXS7UTUFV4Y4F46V","bundle":"https://pith.science/pith/YGKQTCQV4GZXS7UTUFV4Y4F46V/bundle.json","state":"https://pith.science/pith/YGKQTCQV4GZXS7UTUFV4Y4F46V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YGKQTCQV4GZXS7UTUFV4Y4F46V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YGKQTCQV4GZXS7UTUFV4Y4F46V","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":"d6079ad754bc8fae643b756de0c2e02ead6984e2231862f7bbad9d87911d361b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T16:45:30Z","title_canon_sha256":"3d9d9652eda6f64d8d1e57d84723e46b1e00f17904fdcfabd48e65794eb65537"},"schema_version":"1.0","source":{"id":"2211.07514","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.07514","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"arxiv_version","alias_value":"2211.07514v1","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07514","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"pith_short_12","alias_value":"YGKQTCQV4GZX","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"pith_short_16","alias_value":"YGKQTCQV4GZXS7UT","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"pith_short_8","alias_value":"YGKQTCQV","created_at":"2026-07-05T05:15:54Z"}],"graph_snapshots":[{"event_id":"sha256:782d6dfeeef86b4ce1eab3500b07948aa9d9fac8525bdb377d27637eab4ced99","target":"graph","created_at":"2026-07-05T05:15:54Z","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/2211.07514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extending semantic parsers to code-switched input has been a challenging problem, primarily due to a lack of supervised training data. In this work, we introduce CST5, a new data augmentation technique that finetunes a T5 model using a small seed set ($\\approx$100 utterances) to generate code-switched utterances from English utterances. We show that CST5 generates high quality code-switched data, both intrinsically (per human evaluation) and extrinsically by comparing baseline models which are trained without data augmentation to models which are trained with augmented data. Empirically we obs","authors_text":"Anmol Agarwal, Jigar Gupta, Pankaj Joshi, Rahul Goel, Rengarajan Aravamudhan, Shyam Upadhyay","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T16:45:30Z","title":"CST5: Data Augmentation for Code-Switched Semantic Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07514","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:bcf6823fd5117144461a3723187b30ebde5540b22062c22d0e00e92194c380d3","target":"record","created_at":"2026-07-05T05:15:54Z","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":"d6079ad754bc8fae643b756de0c2e02ead6984e2231862f7bbad9d87911d361b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T16:45:30Z","title_canon_sha256":"3d9d9652eda6f64d8d1e57d84723e46b1e00f17904fdcfabd48e65794eb65537"},"schema_version":"1.0","source":{"id":"2211.07514","kind":"arxiv","version":1}},"canonical_sha256":"c195098a15e1b3797e93a16bcc70bcf55b41be0d3e21c2026a5fb7ecaa48007f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c195098a15e1b3797e93a16bcc70bcf55b41be0d3e21c2026a5fb7ecaa48007f","first_computed_at":"2026-07-05T05:15:54.436860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:54.436860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wWEO3s0mkfDXKtSszWKYN6Txl06KDBXZJZaLzWKcROQpZlHyKqk7G8W83cxFyv4bNTo+QoP48XuwhmppmPtwBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:54.437276Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.07514","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcf6823fd5117144461a3723187b30ebde5540b22062c22d0e00e92194c380d3","sha256:782d6dfeeef86b4ce1eab3500b07948aa9d9fac8525bdb377d27637eab4ced99"],"state_sha256":"067cd9a9759e4ea06690cd2c62cf2109315734f9507ac52890d59185c7e970b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4b8PO16TPRLyaEIawB1AanZ1LdK1kb0PxtfWbiB1h4E2TIrMy+9XGyoivQLTM2zl88MZeA/b5BJlaXJ9lESHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:14:52.869523Z","bundle_sha256":"c3ba15747ab3e17fa064114201a61505e404dc0a4cc05a27ad71e9e94e474aed"}}