{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ELXIDZC2K6XXKBOCMZF2N4WBIP","short_pith_number":"pith:ELXIDZC2","canonical_record":{"source":{"id":"2412.05388","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T19:29:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fb9c1a1f992131973dda42db3dc75b11ac16d77a07e55cf4c1f9703a6c047c0f","abstract_canon_sha256":"dd727e39bce19cc32d0911c0ba584ca922c12119d3cd96666376add9e58a41c2"},"schema_version":"1.0"},"canonical_sha256":"22ee81e45a57af7505c2664ba6f2c143ec15f98f0241d81f0671a98c1f57bb07","source":{"kind":"arxiv","id":"2412.05388","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05388","created_at":"2026-07-05T09:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05388v1","created_at":"2026-07-05T09:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05388","created_at":"2026-07-05T09:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"ELXIDZC2K6XX","created_at":"2026-07-05T09:46:02Z"},{"alias_kind":"pith_short_16","alias_value":"ELXIDZC2K6XXKBOC","created_at":"2026-07-05T09:46:02Z"},{"alias_kind":"pith_short_8","alias_value":"ELXIDZC2","created_at":"2026-07-05T09:46:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ELXIDZC2K6XXKBOCMZF2N4WBIP","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05388","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T19:29:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fb9c1a1f992131973dda42db3dc75b11ac16d77a07e55cf4c1f9703a6c047c0f","abstract_canon_sha256":"dd727e39bce19cc32d0911c0ba584ca922c12119d3cd96666376add9e58a41c2"},"schema_version":"1.0"},"canonical_sha256":"22ee81e45a57af7505c2664ba6f2c143ec15f98f0241d81f0671a98c1f57bb07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:02.412351Z","signature_b64":"8GOVjoU2RsuiWU/TWyWwzDlMaFJMDjj0I46KpS7UsiB8UjrRdsczaVoL4BiJEfnQMMuaCEeZoe3EBOl9Oja7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22ee81e45a57af7505c2664ba6f2c143ec15f98f0241d81f0671a98c1f57bb07","last_reissued_at":"2026-07-05T09:46:02.411856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:02.411856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05388","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":"2026-07-05T09:46:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TmFuqzZg03fhMJU/+h6y3/U2PYOrl+OX7WxoaN02Gtab3yqgA6c0D7gSec8S1CaNWnB/4JFsQZXeiP8QNFmjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:46:58.128853Z"},"content_sha256":"1666d823031fbfb679040f56b5f1b3a047124384055f3eac51921a8f1315e01e","schema_version":"1.0","event_id":"sha256:1666d823031fbfb679040f56b5f1b3a047124384055f3eac51921a8f1315e01e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ELXIDZC2K6XXKBOCMZF2N4WBIP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CALICO: Conversational Agent Localization via Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andy Rosenbaum, Christopher DiPersio, Clement Chung, Ershad Banijamali, Fabian Triefenbach, Gokmen Oz, Karolina Owczarzak, Lu Zeng, Pan Wei, Pegah Kharazmi, Wael Hamza","submitted_at":"2024-12-06T19:29:16Z","abstract_excerpt":"We present CALICO, a method to fine-tune Large Language Models (LLMs) to localize conversational agent training data from one language to another. For slots (named entities), CALICO supports three operations: verbatim copy, literal translation, and localization, i.e. generating slot values more appropriate in the target language, such as city and airport names located in countries where the language is spoken. Furthermore, we design an iterative filtering mechanism to discard noisy generated samples, which we show boosts the performance of the downstream conversational agent. To prove the effe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05388","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/2412.05388/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":"2026-07-05T09:46:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GD1wWexS+LKIRV6vN8MJp8zVOXDpPtAlLNTv8jWG8ndTFiXF7W8D0cUk5hcXkCtxoztNsS4BlHBuEKDaFmy/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:46:58.129227Z"},"content_sha256":"df53c33b362c30ae0f96adaa511d266e02fa2f339f593b5b4d4861d7bd550b76","schema_version":"1.0","event_id":"sha256:df53c33b362c30ae0f96adaa511d266e02fa2f339f593b5b4d4861d7bd550b76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ELXIDZC2K6XXKBOCMZF2N4WBIP/bundle.json","state_url":"https://pith.science/pith/ELXIDZC2K6XXKBOCMZF2N4WBIP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ELXIDZC2K6XXKBOCMZF2N4WBIP/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":"2026-07-06T17:46:58Z","links":{"resolver":"https://pith.science/pith/ELXIDZC2K6XXKBOCMZF2N4WBIP","bundle":"https://pith.science/pith/ELXIDZC2K6XXKBOCMZF2N4WBIP/bundle.json","state":"https://pith.science/pith/ELXIDZC2K6XXKBOCMZF2N4WBIP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ELXIDZC2K6XXKBOCMZF2N4WBIP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ELXIDZC2K6XXKBOCMZF2N4WBIP","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":"dd727e39bce19cc32d0911c0ba584ca922c12119d3cd96666376add9e58a41c2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T19:29:16Z","title_canon_sha256":"fb9c1a1f992131973dda42db3dc75b11ac16d77a07e55cf4c1f9703a6c047c0f"},"schema_version":"1.0","source":{"id":"2412.05388","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05388","created_at":"2026-07-05T09:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05388v1","created_at":"2026-07-05T09:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05388","created_at":"2026-07-05T09:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"ELXIDZC2K6XX","created_at":"2026-07-05T09:46:02Z"},{"alias_kind":"pith_short_16","alias_value":"ELXIDZC2K6XXKBOC","created_at":"2026-07-05T09:46:02Z"},{"alias_kind":"pith_short_8","alias_value":"ELXIDZC2","created_at":"2026-07-05T09:46:02Z"}],"graph_snapshots":[{"event_id":"sha256:df53c33b362c30ae0f96adaa511d266e02fa2f339f593b5b4d4861d7bd550b76","target":"graph","created_at":"2026-07-05T09:46:02Z","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/2412.05388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CALICO, a method to fine-tune Large Language Models (LLMs) to localize conversational agent training data from one language to another. For slots (named entities), CALICO supports three operations: verbatim copy, literal translation, and localization, i.e. generating slot values more appropriate in the target language, such as city and airport names located in countries where the language is spoken. Furthermore, we design an iterative filtering mechanism to discard noisy generated samples, which we show boosts the performance of the downstream conversational agent. To prove the effe","authors_text":"Andy Rosenbaum, Christopher DiPersio, Clement Chung, Ershad Banijamali, Fabian Triefenbach, Gokmen Oz, Karolina Owczarzak, Lu Zeng, Pan Wei, Pegah Kharazmi, Wael Hamza","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T19:29:16Z","title":"CALICO: Conversational Agent Localization via Synthetic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05388","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":"sha256:1666d823031fbfb679040f56b5f1b3a047124384055f3eac51921a8f1315e01e","target":"record","created_at":"2026-07-05T09:46:02Z","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":"dd727e39bce19cc32d0911c0ba584ca922c12119d3cd96666376add9e58a41c2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T19:29:16Z","title_canon_sha256":"fb9c1a1f992131973dda42db3dc75b11ac16d77a07e55cf4c1f9703a6c047c0f"},"schema_version":"1.0","source":{"id":"2412.05388","kind":"arxiv","version":1}},"canonical_sha256":"22ee81e45a57af7505c2664ba6f2c143ec15f98f0241d81f0671a98c1f57bb07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22ee81e45a57af7505c2664ba6f2c143ec15f98f0241d81f0671a98c1f57bb07","first_computed_at":"2026-07-05T09:46:02.411856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:02.411856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8GOVjoU2RsuiWU/TWyWwzDlMaFJMDjj0I46KpS7UsiB8UjrRdsczaVoL4BiJEfnQMMuaCEeZoe3EBOl9Oja7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:02.412351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05388","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1666d823031fbfb679040f56b5f1b3a047124384055f3eac51921a8f1315e01e","sha256:df53c33b362c30ae0f96adaa511d266e02fa2f339f593b5b4d4861d7bd550b76"],"state_sha256":"4e8531de819ee806946725321d15b2a1c3be35566f3d508f562a24fbb49f7961"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G4qidt6t/xPvq+E+2Ec+K0hbOH6E1vfC0Ag5hhMMVdkW6dKvY2g0WMyZiK3ijkBxSi7EGZvU+uOAA+RTTiUeBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:46:58.131127Z","bundle_sha256":"71c9f8e940ea77e7aaf951fb5ea9c79b4bdb3720ad754bababdfd2e8d1a70b7a"}}