{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RVAFUAP2MYDD7ALTVCCVZWBCET","short_pith_number":"pith:RVAFUAP2","canonical_record":{"source":{"id":"2605.18869","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T14:56:27Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"01e8b28d2d91bf5b5c8a10932e13bbce9ef6ab464dc1abbd7989e12e5360eafe","abstract_canon_sha256":"0a46f660d350fa82886f219539da4a97ac89912cab28a92f028db35f795caff3"},"schema_version":"1.0"},"canonical_sha256":"8d405a01fa66063f8173a8855cd82224d8276146714e09b8af77d277b29c2624","source":{"kind":"arxiv","id":"2605.18869","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18869","created_at":"2026-05-20T00:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18869v1","created_at":"2026-05-20T00:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18869","created_at":"2026-05-20T00:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"RVAFUAP2MYDD","created_at":"2026-05-20T00:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"RVAFUAP2MYDD7ALT","created_at":"2026-05-20T00:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"RVAFUAP2","created_at":"2026-05-20T00:06:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RVAFUAP2MYDD7ALTVCCVZWBCET","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18869","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T14:56:27Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"01e8b28d2d91bf5b5c8a10932e13bbce9ef6ab464dc1abbd7989e12e5360eafe","abstract_canon_sha256":"0a46f660d350fa82886f219539da4a97ac89912cab28a92f028db35f795caff3"},"schema_version":"1.0"},"canonical_sha256":"8d405a01fa66063f8173a8855cd82224d8276146714e09b8af77d277b29c2624","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:29.535736Z","signature_b64":"Ug8vylahoqGC8PCQl1AZ5Wc4kEyeyT2d/s6zr31gU7L5zThuEoAtHaeh2UD+Fxlq2UBSG/sAZoknxsheIePECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d405a01fa66063f8173a8855cd82224d8276146714e09b8af77d277b29c2624","last_reissued_at":"2026-05-20T00:06:29.534895Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:29.534895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18869","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":"2026-05-20T00:06:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XoeeGwURYOWmR0aR4wnPM53nZiu6Em1i+9919vttEDFBeQU/fmiczqPTuq42chKhwk/coxQMyABEgzXqry7wAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:50:46.998875Z"},"content_sha256":"526292f1a314d737a9dd998b8f5dcb03ea8a189bf97d80dac362e73561813bfa","schema_version":"1.0","event_id":"sha256:526292f1a314d737a9dd998b8f5dcb03ea8a189bf97d80dac362e73561813bfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RVAFUAP2MYDD7ALTVCCVZWBCET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jan B\\\"ussing, Matthias Feurer, Moritz Schlager, Timo Hei{\\ss}, Tom Zehle","submitted_at":"2026-05-15T14:56:27Z","abstract_excerpt":"Large language models (LLMs) achieve strong performance across a wide range of tasks but are highly sensitive to prompt design, motivating the need for automatic prompt optimization. Existing methods predominantly focus on performance alone, ignoring competing objectives such as inference cost or latency. At the same time, existing work on multi-objective prompt optimization relies on off-the-shelf NSGA-II, ignoring optimization efficiency. As a remedy, we introduce MO-CAPO, a novel multi-objective prompt optimization algorithm that jointly optimizes performance and inference cost while levera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18869","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/2605.18869/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":"2026-05-20T00:06:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gwGE1iT04BmPLd+ZdLJlBAubWhQxV6yKZ5oIMaD42WBEB5ThEI1N7Zo/s5/W9xc+k3nSiHYY2rj7xZ9WzPeSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:50:46.999246Z"},"content_sha256":"f5989fadd1e4079156fe38eddec0ccc73f6ea8c6f4c5a7eddf0b67d7d612f66a","schema_version":"1.0","event_id":"sha256:f5989fadd1e4079156fe38eddec0ccc73f6ea8c6f4c5a7eddf0b67d7d612f66a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVAFUAP2MYDD7ALTVCCVZWBCET/bundle.json","state_url":"https://pith.science/pith/RVAFUAP2MYDD7ALTVCCVZWBCET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVAFUAP2MYDD7ALTVCCVZWBCET/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":"2026-06-03T02:50:47Z","links":{"resolver":"https://pith.science/pith/RVAFUAP2MYDD7ALTVCCVZWBCET","bundle":"https://pith.science/pith/RVAFUAP2MYDD7ALTVCCVZWBCET/bundle.json","state":"https://pith.science/pith/RVAFUAP2MYDD7ALTVCCVZWBCET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVAFUAP2MYDD7ALTVCCVZWBCET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RVAFUAP2MYDD7ALTVCCVZWBCET","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":"0a46f660d350fa82886f219539da4a97ac89912cab28a92f028db35f795caff3","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T14:56:27Z","title_canon_sha256":"01e8b28d2d91bf5b5c8a10932e13bbce9ef6ab464dc1abbd7989e12e5360eafe"},"schema_version":"1.0","source":{"id":"2605.18869","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18869","created_at":"2026-05-20T00:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18869v1","created_at":"2026-05-20T00:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18869","created_at":"2026-05-20T00:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"RVAFUAP2MYDD","created_at":"2026-05-20T00:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"RVAFUAP2MYDD7ALT","created_at":"2026-05-20T00:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"RVAFUAP2","created_at":"2026-05-20T00:06:29Z"}],"graph_snapshots":[{"event_id":"sha256:f5989fadd1e4079156fe38eddec0ccc73f6ea8c6f4c5a7eddf0b67d7d612f66a","target":"graph","created_at":"2026-05-20T00:06:29Z","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/2605.18869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) achieve strong performance across a wide range of tasks but are highly sensitive to prompt design, motivating the need for automatic prompt optimization. Existing methods predominantly focus on performance alone, ignoring competing objectives such as inference cost or latency. At the same time, existing work on multi-objective prompt optimization relies on off-the-shelf NSGA-II, ignoring optimization efficiency. As a remedy, we introduce MO-CAPO, a novel multi-objective prompt optimization algorithm that jointly optimizes performance and inference cost while levera","authors_text":"Jan B\\\"ussing, Matthias Feurer, Moritz Schlager, Timo Hei{\\ss}, Tom Zehle","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T14:56:27Z","title":"MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18869","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":"sha256:526292f1a314d737a9dd998b8f5dcb03ea8a189bf97d80dac362e73561813bfa","target":"record","created_at":"2026-05-20T00:06:29Z","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":"0a46f660d350fa82886f219539da4a97ac89912cab28a92f028db35f795caff3","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T14:56:27Z","title_canon_sha256":"01e8b28d2d91bf5b5c8a10932e13bbce9ef6ab464dc1abbd7989e12e5360eafe"},"schema_version":"1.0","source":{"id":"2605.18869","kind":"arxiv","version":1}},"canonical_sha256":"8d405a01fa66063f8173a8855cd82224d8276146714e09b8af77d277b29c2624","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d405a01fa66063f8173a8855cd82224d8276146714e09b8af77d277b29c2624","first_computed_at":"2026-05-20T00:06:29.534895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:29.534895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ug8vylahoqGC8PCQl1AZ5Wc4kEyeyT2d/s6zr31gU7L5zThuEoAtHaeh2UD+Fxlq2UBSG/sAZoknxsheIePECA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:29.535736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18869","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:526292f1a314d737a9dd998b8f5dcb03ea8a189bf97d80dac362e73561813bfa","sha256:f5989fadd1e4079156fe38eddec0ccc73f6ea8c6f4c5a7eddf0b67d7d612f66a"],"state_sha256":"ba8067020a6a990d4f335fa36bc76739ef188cd916a0cf1c1a380ed9533a995b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+V6L6442aSuCVK1Id9gVN/0q15RI3yvyhBfMlBrx52ErK9FCYhFxlH1XNx7q9ijqHaWOBLi3+ePdKTIyY41dAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T02:50:47.001227Z","bundle_sha256":"67da0da2671adbc585c0c61f00ae420590120ef4ebcdc91051252a20e9bedd04"}}