{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A5WFQBEK24IA4NVN7TKOTVDGOS","short_pith_number":"pith:A5WFQBEK","canonical_record":{"source":{"id":"2408.11189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T20:47:27Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"33f2e1f6ec27553a184f972ba67fce4991dab5ed1e617e8e03a18d03d9b0908d","abstract_canon_sha256":"2eaef6ea6a4ec87041d161a68e1642d100245cef0e8e1691fd083d7936fd2d28"},"schema_version":"1.0"},"canonical_sha256":"076c58048ad7100e36adfcd4e9d466749c3222818a034c92df3cf50f1c9f78cf","source":{"kind":"arxiv","id":"2408.11189","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11189","created_at":"2026-07-05T11:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11189v2","created_at":"2026-07-05T11:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11189","created_at":"2026-07-05T11:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"A5WFQBEK24IA","created_at":"2026-07-05T11:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"A5WFQBEK24IA4NVN","created_at":"2026-07-05T11:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"A5WFQBEK","created_at":"2026-07-05T11:29:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A5WFQBEK24IA4NVN7TKOTVDGOS","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T20:47:27Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"33f2e1f6ec27553a184f972ba67fce4991dab5ed1e617e8e03a18d03d9b0908d","abstract_canon_sha256":"2eaef6ea6a4ec87041d161a68e1642d100245cef0e8e1691fd083d7936fd2d28"},"schema_version":"1.0"},"canonical_sha256":"076c58048ad7100e36adfcd4e9d466749c3222818a034c92df3cf50f1c9f78cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:01.079127Z","signature_b64":"kfrUEZCLlpUBykE8YVfPv2DBLD3yhb/sxQkUnEXORtihhCcLGwQGUJClSgj95KbzzIFU8s0HvJPeP/xGEBgHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"076c58048ad7100e36adfcd4e9d466749c3222818a034c92df3cf50f1c9f78cf","last_reissued_at":"2026-07-05T11:29:01.078583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:01.078583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11189","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBpa5ofefGIX+I6WDIwwA5QLw18EXCGUuRqOigusStCDc+2wMiP2t1wi0+DW4QK3FRAMt1HIQhnM+BEal/NhBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:51:00.637420Z"},"content_sha256":"1bf0ba06c10c48eabc13c7bb9240ad216b9ea959aff8f5cef1cac1dcc9e081ff","schema_version":"1.0","event_id":"sha256:1bf0ba06c10c48eabc13c7bb9240ad216b9ea959aff8f5cef1cac1dcc9e081ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A5WFQBEK24IA4NVN7TKOTVDGOS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emotional RAG LLMs: Reading Comprehension for the Open Internet","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adar Avsian, Benjamin Reichman, Kartik Talamadupula, Larry Heck, Toshish Jawale","submitted_at":"2024-08-20T20:47:27Z","abstract_excerpt":"Queries to large language models (LLMs) can be divided into two parts: the instruction/question and the accompanying context. The context for retrieval-augmented generation (RAG) systems in most benchmarks comes from Wikipedia-like texts written in a neutral and factual tone. However, real-world RAG applications often retrieve internet-based text with diverse tones and linguistic styles, posing challenges for downstream tasks. This paper introduces (a) a dataset that transforms RAG-retrieved passages into emotionally inflected and sarcastic text, (b) an emotion translation model for adapting t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11189","kind":"arxiv","version":2},"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/2408.11189/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":"2026-07-05T11:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EKvd8Drwk5qOHvtQtdhXh9AEkimw22JPhEkdbHLyCchEPPwl69Ic8TGWZ27x2eIVRNdIRMQ6W4ISjYFMUoi/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:51:00.637950Z"},"content_sha256":"ea98030971c1d7bf01a376801e70e99a309c226c154231c64b8e4ff1d42b7023","schema_version":"1.0","event_id":"sha256:ea98030971c1d7bf01a376801e70e99a309c226c154231c64b8e4ff1d42b7023"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5WFQBEK24IA4NVN7TKOTVDGOS/bundle.json","state_url":"https://pith.science/pith/A5WFQBEK24IA4NVN7TKOTVDGOS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5WFQBEK24IA4NVN7TKOTVDGOS/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":"2026-08-12T16:51:00Z","links":{"resolver":"https://pith.science/pith/A5WFQBEK24IA4NVN7TKOTVDGOS","bundle":"https://pith.science/pith/A5WFQBEK24IA4NVN7TKOTVDGOS/bundle.json","state":"https://pith.science/pith/A5WFQBEK24IA4NVN7TKOTVDGOS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5WFQBEK24IA4NVN7TKOTVDGOS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A5WFQBEK24IA4NVN7TKOTVDGOS","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":"2eaef6ea6a4ec87041d161a68e1642d100245cef0e8e1691fd083d7936fd2d28","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T20:47:27Z","title_canon_sha256":"33f2e1f6ec27553a184f972ba67fce4991dab5ed1e617e8e03a18d03d9b0908d"},"schema_version":"1.0","source":{"id":"2408.11189","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11189","created_at":"2026-07-05T11:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11189v2","created_at":"2026-07-05T11:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11189","created_at":"2026-07-05T11:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"A5WFQBEK24IA","created_at":"2026-07-05T11:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"A5WFQBEK24IA4NVN","created_at":"2026-07-05T11:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"A5WFQBEK","created_at":"2026-07-05T11:29:01Z"}],"graph_snapshots":[{"event_id":"sha256:ea98030971c1d7bf01a376801e70e99a309c226c154231c64b8e4ff1d42b7023","target":"graph","created_at":"2026-07-05T11:29:01Z","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/2408.11189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Queries to large language models (LLMs) can be divided into two parts: the instruction/question and the accompanying context. The context for retrieval-augmented generation (RAG) systems in most benchmarks comes from Wikipedia-like texts written in a neutral and factual tone. However, real-world RAG applications often retrieve internet-based text with diverse tones and linguistic styles, posing challenges for downstream tasks. This paper introduces (a) a dataset that transforms RAG-retrieved passages into emotionally inflected and sarcastic text, (b) an emotion translation model for adapting t","authors_text":"Adar Avsian, Benjamin Reichman, Kartik Talamadupula, Larry Heck, Toshish Jawale","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T20:47:27Z","title":"Emotional RAG LLMs: Reading Comprehension for the Open Internet"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11189","kind":"arxiv","version":2},"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":"sha256:1bf0ba06c10c48eabc13c7bb9240ad216b9ea959aff8f5cef1cac1dcc9e081ff","target":"record","created_at":"2026-07-05T11:29:01Z","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":"2eaef6ea6a4ec87041d161a68e1642d100245cef0e8e1691fd083d7936fd2d28","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T20:47:27Z","title_canon_sha256":"33f2e1f6ec27553a184f972ba67fce4991dab5ed1e617e8e03a18d03d9b0908d"},"schema_version":"1.0","source":{"id":"2408.11189","kind":"arxiv","version":2}},"canonical_sha256":"076c58048ad7100e36adfcd4e9d466749c3222818a034c92df3cf50f1c9f78cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"076c58048ad7100e36adfcd4e9d466749c3222818a034c92df3cf50f1c9f78cf","first_computed_at":"2026-07-05T11:29:01.078583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:01.078583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kfrUEZCLlpUBykE8YVfPv2DBLD3yhb/sxQkUnEXORtihhCcLGwQGUJClSgj95KbzzIFU8s0HvJPeP/xGEBgHBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:01.079127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11189","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bf0ba06c10c48eabc13c7bb9240ad216b9ea959aff8f5cef1cac1dcc9e081ff","sha256:ea98030971c1d7bf01a376801e70e99a309c226c154231c64b8e4ff1d42b7023"],"state_sha256":"aaf1e01637d8edd2d7c795946dae64081e5f98c9ea273f68fe9e6145e4353795"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W0RYorPV9LVvQtbPJZDn7pSkLDs9SWfSrGPfZ7gV49HZmx4yFELXJsnTyuUC1CRPUdljxVg6LKQGRsariURNBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T16:51:00.643647Z","bundle_sha256":"5c8348eea85e4c53ce093491d1eab9a22db869d6368cc040837b4f87222d145d"}}