{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7E3AYBISZTEUL5CSNDZENKCAZ5","short_pith_number":"pith:7E3AYBIS","canonical_record":{"source":{"id":"2409.07604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-09-11T20:31:42Z","cross_cats_sorted":[],"title_canon_sha256":"ff0fbf7654b9e97a2a0c804c29fb40ba8544e4eeaff5524192090b4004e277b9","abstract_canon_sha256":"6df5fc04e0adabc2d297629c489cca6c04ebc086ddddf61f400de0530c0dd948"},"schema_version":"1.0"},"canonical_sha256":"f9360c0512ccc945f45268f246a840cf7d290406295e0e35b255c9af737ec4ba","source":{"kind":"arxiv","id":"2409.07604","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07604","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07604v1","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07604","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"7E3AYBISZTEU","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"7E3AYBISZTEUL5CS","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"7E3AYBIS","created_at":"2026-07-05T09:06:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7E3AYBISZTEUL5CSNDZENKCAZ5","target":"record","payload":{"canonical_record":{"source":{"id":"2409.07604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-09-11T20:31:42Z","cross_cats_sorted":[],"title_canon_sha256":"ff0fbf7654b9e97a2a0c804c29fb40ba8544e4eeaff5524192090b4004e277b9","abstract_canon_sha256":"6df5fc04e0adabc2d297629c489cca6c04ebc086ddddf61f400de0530c0dd948"},"schema_version":"1.0"},"canonical_sha256":"f9360c0512ccc945f45268f246a840cf7d290406295e0e35b255c9af737ec4ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:12.454496Z","signature_b64":"ObRI5UAW4erfimne+BSajuI0vJa732JJ95rA6KycBblfqptIbwu5sy6SnQPdzpyoA5G8FjrbxdRCD9hM/gGJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9360c0512ccc945f45268f246a840cf7d290406295e0e35b255c9af737ec4ba","last_reissued_at":"2026-07-05T09:06:12.453986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:12.453986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.07604","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":"2026-07-05T09:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W71e0zjQPybqE1dv7dzmCOXvChSLjBKprlmyxKzCnwC7umKk+3UCrl+Kb3fG7p/yys7OQ6SYcspwP1g35lUwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:41:58.057736Z"},"content_sha256":"6c49ffdff379bc20cc2bde0f1fc45052bf00fc7fb1a27690f371562aa0b8125c","schema_version":"1.0","event_id":"sha256:6c49ffdff379bc20cc2bde0f1fc45052bf00fc7fb1a27690f371562aa0b8125c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7E3AYBISZTEUL5CSNDZENKCAZ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Prompts in LLM-Based Recommenders: Performance Across Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Makbule Gulcin Ozsoy","submitted_at":"2024-09-11T20:31:42Z","abstract_excerpt":"Large language models (LLMs) are increasingly used in natural language processing tasks. Recommender systems traditionally use methods such as collaborative filtering and matrix factorization, as well as advanced techniques like deep learning and reinforcement learning. Although language models have been applied in recommendation, the recent trend have focused on leveraging the generative capabilities of LLMs for more personalized suggestions. While current research focuses on English due to its resource richness, this work explores the impact of non-English prompts on recommendation performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07604","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/2409.07604/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":"2026-07-05T09:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2PI6VRIPoqQw+jmist8cE7v7/9cmUWlpHRQMLuvK0sfL5uey21quiDY5YnPPsBFyJeYF76Lb/MCLTU48DvCSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:41:58.058203Z"},"content_sha256":"4bbe9f8b8c97a98a7e97d2763737a01536ed7ddaf5b39c0dfe47669301c57582","schema_version":"1.0","event_id":"sha256:4bbe9f8b8c97a98a7e97d2763737a01536ed7ddaf5b39c0dfe47669301c57582"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7E3AYBISZTEUL5CSNDZENKCAZ5/bundle.json","state_url":"https://pith.science/pith/7E3AYBISZTEUL5CSNDZENKCAZ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7E3AYBISZTEUL5CSNDZENKCAZ5/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":"2026-08-04T09:41:58Z","links":{"resolver":"https://pith.science/pith/7E3AYBISZTEUL5CSNDZENKCAZ5","bundle":"https://pith.science/pith/7E3AYBISZTEUL5CSNDZENKCAZ5/bundle.json","state":"https://pith.science/pith/7E3AYBISZTEUL5CSNDZENKCAZ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7E3AYBISZTEUL5CSNDZENKCAZ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7E3AYBISZTEUL5CSNDZENKCAZ5","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":"6df5fc04e0adabc2d297629c489cca6c04ebc086ddddf61f400de0530c0dd948","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-09-11T20:31:42Z","title_canon_sha256":"ff0fbf7654b9e97a2a0c804c29fb40ba8544e4eeaff5524192090b4004e277b9"},"schema_version":"1.0","source":{"id":"2409.07604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07604","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07604v1","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07604","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"7E3AYBISZTEU","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"7E3AYBISZTEUL5CS","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"7E3AYBIS","created_at":"2026-07-05T09:06:12Z"}],"graph_snapshots":[{"event_id":"sha256:4bbe9f8b8c97a98a7e97d2763737a01536ed7ddaf5b39c0dfe47669301c57582","target":"graph","created_at":"2026-07-05T09:06:12Z","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/2409.07604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used in natural language processing tasks. Recommender systems traditionally use methods such as collaborative filtering and matrix factorization, as well as advanced techniques like deep learning and reinforcement learning. Although language models have been applied in recommendation, the recent trend have focused on leveraging the generative capabilities of LLMs for more personalized suggestions. While current research focuses on English due to its resource richness, this work explores the impact of non-English prompts on recommendation performan","authors_text":"Makbule Gulcin Ozsoy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-09-11T20:31:42Z","title":"Multilingual Prompts in LLM-Based Recommenders: Performance Across Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07604","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":"sha256:6c49ffdff379bc20cc2bde0f1fc45052bf00fc7fb1a27690f371562aa0b8125c","target":"record","created_at":"2026-07-05T09:06:12Z","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":"6df5fc04e0adabc2d297629c489cca6c04ebc086ddddf61f400de0530c0dd948","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-09-11T20:31:42Z","title_canon_sha256":"ff0fbf7654b9e97a2a0c804c29fb40ba8544e4eeaff5524192090b4004e277b9"},"schema_version":"1.0","source":{"id":"2409.07604","kind":"arxiv","version":1}},"canonical_sha256":"f9360c0512ccc945f45268f246a840cf7d290406295e0e35b255c9af737ec4ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9360c0512ccc945f45268f246a840cf7d290406295e0e35b255c9af737ec4ba","first_computed_at":"2026-07-05T09:06:12.453986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:12.453986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ObRI5UAW4erfimne+BSajuI0vJa732JJ95rA6KycBblfqptIbwu5sy6SnQPdzpyoA5G8FjrbxdRCD9hM/gGJDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:12.454496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c49ffdff379bc20cc2bde0f1fc45052bf00fc7fb1a27690f371562aa0b8125c","sha256:4bbe9f8b8c97a98a7e97d2763737a01536ed7ddaf5b39c0dfe47669301c57582"],"state_sha256":"c54c5756c91e523f0beb42625d64e7d77a8159450870d52ef839dc7c984c74a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gNyUAbb4s9+9PZNHDttr286vwW4o1xR7Nabq01IuX0KrgEkB2rYkvtxTHEgxZ5K2hUja8GVw12S+SSoLCsgQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:41:58.061627Z","bundle_sha256":"0b030c9cab53b6a9df5fbb363a1f0439d50782218e519a6c78353c0c4545bdaa"}}