{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZGKGLTFHUUHRDQYU75DHC7VVG2","short_pith_number":"pith:ZGKGLTFH","canonical_record":{"source":{"id":"2505.01449","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T02:06:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34fb08d15a7c4aa7a21fb6af32ca985b3e1af39bae5348ae20e645cf29f76f0d","abstract_canon_sha256":"9b6eaf4f6a08b299015c66660167dab5a5b9e0550a3dc8cc29f218bdfcee3974"},"schema_version":"1.0"},"canonical_sha256":"c99465cca7a50f11c314ff46717eb536b1eb79dc36598c024add8c6392e155c2","source":{"kind":"arxiv","id":"2505.01449","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01449","created_at":"2026-07-05T11:16:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01449v1","created_at":"2026-07-05T11:16:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01449","created_at":"2026-07-05T11:16:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZGKGLTFHUUHR","created_at":"2026-07-05T11:16:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZGKGLTFHUUHRDQYU","created_at":"2026-07-05T11:16:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZGKGLTFH","created_at":"2026-07-05T11:16:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZGKGLTFHUUHRDQYU75DHC7VVG2","target":"record","payload":{"canonical_record":{"source":{"id":"2505.01449","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T02:06:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34fb08d15a7c4aa7a21fb6af32ca985b3e1af39bae5348ae20e645cf29f76f0d","abstract_canon_sha256":"9b6eaf4f6a08b299015c66660167dab5a5b9e0550a3dc8cc29f218bdfcee3974"},"schema_version":"1.0"},"canonical_sha256":"c99465cca7a50f11c314ff46717eb536b1eb79dc36598c024add8c6392e155c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:07.893615Z","signature_b64":"sH91Hrla6x6wMYIxxjmI7B8NHvQOYHc3OOeBnlYF/SNLa/cn+eFzK9AiQpzKxw4gxwfFsdWvCcFd5Ot9+PFtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c99465cca7a50f11c314ff46717eb536b1eb79dc36598c024add8c6392e155c2","last_reissued_at":"2026-07-05T11:16:07.893098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:07.893098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.01449","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":"2026-07-05T11:16:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sCASntDK8EUSaanU7v8LXbf0Q9sJsVkAtzEpTwqmImF1fYd2e33iKr4pjsYp+yS4x+IivJCzG5x2eOub90HHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:42:24.712068Z"},"content_sha256":"cc66133d786b4325718f36db5352e11d0d230473f3a29f53b784f003d3f98630","schema_version":"1.0","event_id":"sha256:cc66133d786b4325718f36db5352e11d0d230473f3a29f53b784f003d3f98630"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZGKGLTFHUUHRDQYU75DHC7VVG2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"COSMOS: Predictable and Cost-Effective Adaptation of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aws Albarghouthi, Frederic Sala, Jiayu Wang","submitted_at":"2025-04-30T02:06:26Z","abstract_excerpt":"Large language models (LLMs) achieve remarkable performance across numerous tasks by using a diverse array of adaptation strategies. However, optimally selecting a model and adaptation strategy under resource constraints is challenging and often requires extensive experimentation. We investigate whether it is possible to accurately predict both performance and cost without expensive trials. We formalize the strategy selection problem for LLMs and introduce COSMOS, a unified prediction framework that efficiently estimates adaptation outcomes at minimal cost. We instantiate and study the capabil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01449","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/2505.01449/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":"2026-07-05T11:16:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zvoFvGDk8Tk7Qgm3XZvn2nnA2JTOKYlj9BiISVRz0KqpXc1DWMpKu9veLzuilRtbvrh9uKrA83C8fZIR/4dBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:42:24.712577Z"},"content_sha256":"d68530027af05adf82976bcaca8281c944256a3ffc29f2c91d4647ff728f6159","schema_version":"1.0","event_id":"sha256:d68530027af05adf82976bcaca8281c944256a3ffc29f2c91d4647ff728f6159"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZGKGLTFHUUHRDQYU75DHC7VVG2/bundle.json","state_url":"https://pith.science/pith/ZGKGLTFHUUHRDQYU75DHC7VVG2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZGKGLTFHUUHRDQYU75DHC7VVG2/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":"2026-08-19T04:42:24Z","links":{"resolver":"https://pith.science/pith/ZGKGLTFHUUHRDQYU75DHC7VVG2","bundle":"https://pith.science/pith/ZGKGLTFHUUHRDQYU75DHC7VVG2/bundle.json","state":"https://pith.science/pith/ZGKGLTFHUUHRDQYU75DHC7VVG2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZGKGLTFHUUHRDQYU75DHC7VVG2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZGKGLTFHUUHRDQYU75DHC7VVG2","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":"9b6eaf4f6a08b299015c66660167dab5a5b9e0550a3dc8cc29f218bdfcee3974","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T02:06:26Z","title_canon_sha256":"34fb08d15a7c4aa7a21fb6af32ca985b3e1af39bae5348ae20e645cf29f76f0d"},"schema_version":"1.0","source":{"id":"2505.01449","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01449","created_at":"2026-07-05T11:16:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01449v1","created_at":"2026-07-05T11:16:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01449","created_at":"2026-07-05T11:16:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZGKGLTFHUUHR","created_at":"2026-07-05T11:16:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZGKGLTFHUUHRDQYU","created_at":"2026-07-05T11:16:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZGKGLTFH","created_at":"2026-07-05T11:16:07Z"}],"graph_snapshots":[{"event_id":"sha256:d68530027af05adf82976bcaca8281c944256a3ffc29f2c91d4647ff728f6159","target":"graph","created_at":"2026-07-05T11:16:07Z","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/2505.01449/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) achieve remarkable performance across numerous tasks by using a diverse array of adaptation strategies. However, optimally selecting a model and adaptation strategy under resource constraints is challenging and often requires extensive experimentation. We investigate whether it is possible to accurately predict both performance and cost without expensive trials. We formalize the strategy selection problem for LLMs and introduce COSMOS, a unified prediction framework that efficiently estimates adaptation outcomes at minimal cost. We instantiate and study the capabil","authors_text":"Aws Albarghouthi, Frederic Sala, Jiayu Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T02:06:26Z","title":"COSMOS: Predictable and Cost-Effective Adaptation of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01449","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:cc66133d786b4325718f36db5352e11d0d230473f3a29f53b784f003d3f98630","target":"record","created_at":"2026-07-05T11:16:07Z","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":"9b6eaf4f6a08b299015c66660167dab5a5b9e0550a3dc8cc29f218bdfcee3974","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T02:06:26Z","title_canon_sha256":"34fb08d15a7c4aa7a21fb6af32ca985b3e1af39bae5348ae20e645cf29f76f0d"},"schema_version":"1.0","source":{"id":"2505.01449","kind":"arxiv","version":1}},"canonical_sha256":"c99465cca7a50f11c314ff46717eb536b1eb79dc36598c024add8c6392e155c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c99465cca7a50f11c314ff46717eb536b1eb79dc36598c024add8c6392e155c2","first_computed_at":"2026-07-05T11:16:07.893098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:07.893098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sH91Hrla6x6wMYIxxjmI7B8NHvQOYHc3OOeBnlYF/SNLa/cn+eFzK9AiQpzKxw4gxwfFsdWvCcFd5Ot9+PFtBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:07.893615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.01449","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc66133d786b4325718f36db5352e11d0d230473f3a29f53b784f003d3f98630","sha256:d68530027af05adf82976bcaca8281c944256a3ffc29f2c91d4647ff728f6159"],"state_sha256":"cc189acc1c308a902701dcb8ef70092a1358b91cdfa4bf422351964c6e14289b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2wH1HTD6+ryok+9oDBbOeof7OKtgj5fmmcFdgTFZvJ/ocyjj06tbhTJmsO8AmP4n0SrXB0pUPw2ax8wtt/gzCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:42:24.717852Z","bundle_sha256":"e4a0488ed4f1fd3c5ad7230b10fb9f57246e2f75bbb47f66f653fb06739a7bde"}}