{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SDUZFRXQUECJHW3VBJPA27FMUC","short_pith_number":"pith:SDUZFRXQ","canonical_record":{"source":{"id":"2410.06154","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T15:55:40Z","cross_cats_sorted":[],"title_canon_sha256":"7e7902be5e3bfb2ff90e328e07ec3a199fd3e3c04111d3a166c8bc1175e98dde","abstract_canon_sha256":"501552539082edc8fa5ca4f34c1c5264630ac30872106a0a71f1921f7d273fdd"},"schema_version":"1.0"},"canonical_sha256":"90e992c6f0a10493db750a5e0d7caca0bfc41db137a1b07078df3d5fec10a470","source":{"kind":"arxiv","id":"2410.06154","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06154","created_at":"2026-07-05T11:56:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06154v6","created_at":"2026-07-05T11:56:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06154","created_at":"2026-07-05T11:56:50Z"},{"alias_kind":"pith_short_12","alias_value":"SDUZFRXQUECJ","created_at":"2026-07-05T11:56:50Z"},{"alias_kind":"pith_short_16","alias_value":"SDUZFRXQUECJHW3V","created_at":"2026-07-05T11:56:50Z"},{"alias_kind":"pith_short_8","alias_value":"SDUZFRXQ","created_at":"2026-07-05T11:56:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SDUZFRXQUECJHW3VBJPA27FMUC","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06154","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T15:55:40Z","cross_cats_sorted":[],"title_canon_sha256":"7e7902be5e3bfb2ff90e328e07ec3a199fd3e3c04111d3a166c8bc1175e98dde","abstract_canon_sha256":"501552539082edc8fa5ca4f34c1c5264630ac30872106a0a71f1921f7d273fdd"},"schema_version":"1.0"},"canonical_sha256":"90e992c6f0a10493db750a5e0d7caca0bfc41db137a1b07078df3d5fec10a470","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:50.278327Z","signature_b64":"4aCrj94RcafXX1hRK633aN90YnngM+NydWwArgZs8LVhuCEgsZOk4ok87/3Ka+vIJX02fwcnfZz7KUxnqXGLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90e992c6f0a10493db750a5e0d7caca0bfc41db137a1b07078df3d5fec10a470","last_reissued_at":"2026-07-05T11:56:50.277840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:50.277840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06154","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:56:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGOGuHBFDi3lvQgWv3Eg65mnUyYQ2ByrSmFytoNqJNyEIcfcI4VAyFziAR4xJY1CkjBKsv+yv3PfNJjcHjWxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:52:29.303670Z"},"content_sha256":"d85e121d6c4920166a75127a005ef4d8b35de463c2cb82be033a149b94386753","schema_version":"1.0","event_id":"sha256:d85e121d6c4920166a75127a005ef4d8b35de463c2cb82be033a149b94386753"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SDUZFRXQUECJHW3VBJPA27FMUC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hiromi Wakaki, Horst Possegger, James Glass, Leonid Karlinsky, Mengjie Zhao, Michael Dorkenwald, M. Jehanzeb Mirza, Paul Gavrikov, Rogerio Feris, Saurav Jha, Shiqi Yang, Sivan Doveh, Wei Lin, Yuki Mitsufuji, Zhuoyuan Mao","submitted_at":"2024-10-08T15:55:40Z","abstract_excerpt":"In this work, we propose GLOV, which enables Large Language Models (LLMs) to act as implicit optimizers for Vision-Language Models (VLMs) to enhance downstream vision tasks. GLOV prompts an LLM with the downstream task description, querying it for suitable VLM prompts (e.g., for zero-shot classification with CLIP). These prompts are ranked according to their fitness for the downstream vision task. In each respective optimization step, the ranked prompts are fed as in-context examples (with their accuracies) to equip the LLM with the knowledge of the type of prompts preferred by the downstream "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06154","kind":"arxiv","version":6},"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/2410.06154/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":"2026-07-05T11:56:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"brZ0ESNxzZICjDYhZZ7NuDrqbtvRsJw/kPD3tre+no0cntC4wVEkLTVp5rnEM2lVHK3cHvE0pXacmUztwdt6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:52:29.304134Z"},"content_sha256":"4d2a6d66098d642ccc384cbccdda49a27a80bb378c8ff06f7eacb791911ef4b5","schema_version":"1.0","event_id":"sha256:4d2a6d66098d642ccc384cbccdda49a27a80bb378c8ff06f7eacb791911ef4b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SDUZFRXQUECJHW3VBJPA27FMUC/bundle.json","state_url":"https://pith.science/pith/SDUZFRXQUECJHW3VBJPA27FMUC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SDUZFRXQUECJHW3VBJPA27FMUC/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":"2026-08-14T00:52:29Z","links":{"resolver":"https://pith.science/pith/SDUZFRXQUECJHW3VBJPA27FMUC","bundle":"https://pith.science/pith/SDUZFRXQUECJHW3VBJPA27FMUC/bundle.json","state":"https://pith.science/pith/SDUZFRXQUECJHW3VBJPA27FMUC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SDUZFRXQUECJHW3VBJPA27FMUC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SDUZFRXQUECJHW3VBJPA27FMUC","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":"501552539082edc8fa5ca4f34c1c5264630ac30872106a0a71f1921f7d273fdd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T15:55:40Z","title_canon_sha256":"7e7902be5e3bfb2ff90e328e07ec3a199fd3e3c04111d3a166c8bc1175e98dde"},"schema_version":"1.0","source":{"id":"2410.06154","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06154","created_at":"2026-07-05T11:56:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06154v6","created_at":"2026-07-05T11:56:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06154","created_at":"2026-07-05T11:56:50Z"},{"alias_kind":"pith_short_12","alias_value":"SDUZFRXQUECJ","created_at":"2026-07-05T11:56:50Z"},{"alias_kind":"pith_short_16","alias_value":"SDUZFRXQUECJHW3V","created_at":"2026-07-05T11:56:50Z"},{"alias_kind":"pith_short_8","alias_value":"SDUZFRXQ","created_at":"2026-07-05T11:56:50Z"}],"graph_snapshots":[{"event_id":"sha256:4d2a6d66098d642ccc384cbccdda49a27a80bb378c8ff06f7eacb791911ef4b5","target":"graph","created_at":"2026-07-05T11:56:50Z","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/2410.06154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose GLOV, which enables Large Language Models (LLMs) to act as implicit optimizers for Vision-Language Models (VLMs) to enhance downstream vision tasks. GLOV prompts an LLM with the downstream task description, querying it for suitable VLM prompts (e.g., for zero-shot classification with CLIP). These prompts are ranked according to their fitness for the downstream vision task. In each respective optimization step, the ranked prompts are fed as in-context examples (with their accuracies) to equip the LLM with the knowledge of the type of prompts preferred by the downstream ","authors_text":"Hiromi Wakaki, Horst Possegger, James Glass, Leonid Karlinsky, Mengjie Zhao, Michael Dorkenwald, M. Jehanzeb Mirza, Paul Gavrikov, Rogerio Feris, Saurav Jha, Shiqi Yang, Sivan Doveh, Wei Lin, Yuki Mitsufuji, Zhuoyuan Mao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T15:55:40Z","title":"GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06154","kind":"arxiv","version":6},"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:d85e121d6c4920166a75127a005ef4d8b35de463c2cb82be033a149b94386753","target":"record","created_at":"2026-07-05T11:56:50Z","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":"501552539082edc8fa5ca4f34c1c5264630ac30872106a0a71f1921f7d273fdd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T15:55:40Z","title_canon_sha256":"7e7902be5e3bfb2ff90e328e07ec3a199fd3e3c04111d3a166c8bc1175e98dde"},"schema_version":"1.0","source":{"id":"2410.06154","kind":"arxiv","version":6}},"canonical_sha256":"90e992c6f0a10493db750a5e0d7caca0bfc41db137a1b07078df3d5fec10a470","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90e992c6f0a10493db750a5e0d7caca0bfc41db137a1b07078df3d5fec10a470","first_computed_at":"2026-07-05T11:56:50.277840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:50.277840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4aCrj94RcafXX1hRK633aN90YnngM+NydWwArgZs8LVhuCEgsZOk4ok87/3Ka+vIJX02fwcnfZz7KUxnqXGLBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:50.278327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06154","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d85e121d6c4920166a75127a005ef4d8b35de463c2cb82be033a149b94386753","sha256:4d2a6d66098d642ccc384cbccdda49a27a80bb378c8ff06f7eacb791911ef4b5"],"state_sha256":"a8ef76698716bef47590a2cd8c7450fa792191c141b7bd8a3ec15c6f9afb1a7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YZk61wHFZUpdDd9o+vQL/keKddGFhdhc/LYIbQSwqYZBiOjeuIUP+rhuw+miH4Sgpf2NMTvy7LnT6JsoNJlNBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T00:52:29.310564Z","bundle_sha256":"ce913d471d3650d60d8fe4c349f4ed354b1b8f0a7ca6f6ecdc6e4584386dd8ad"}}