{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:B67A3BEFAKNRDIFFKNAKOW7BOJ","short_pith_number":"pith:B67A3BEF","canonical_record":{"source":{"id":"2307.14063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-26T09:31:06Z","cross_cats_sorted":[],"title_canon_sha256":"4d9ebdd0ad1532ea0daa7c901fd298eabef4fa439b370d6b1af1bf51b419a5df","abstract_canon_sha256":"2c2310f3e6de2debc88fb121b15c74c8fd2543229fb184bfefe9a5d1c2046c6d"},"schema_version":"1.0"},"canonical_sha256":"0fbe0d8485029b11a0a55340a75be1725805ae39c73c076e1ab858370726927b","source":{"kind":"arxiv","id":"2307.14063","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14063","created_at":"2026-07-05T06:34:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14063v1","created_at":"2026-07-05T06:34:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14063","created_at":"2026-07-05T06:34:57Z"},{"alias_kind":"pith_short_12","alias_value":"B67A3BEFAKNR","created_at":"2026-07-05T06:34:57Z"},{"alias_kind":"pith_short_16","alias_value":"B67A3BEFAKNRDIFF","created_at":"2026-07-05T06:34:57Z"},{"alias_kind":"pith_short_8","alias_value":"B67A3BEF","created_at":"2026-07-05T06:34:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:B67A3BEFAKNRDIFFKNAKOW7BOJ","target":"record","payload":{"canonical_record":{"source":{"id":"2307.14063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-26T09:31:06Z","cross_cats_sorted":[],"title_canon_sha256":"4d9ebdd0ad1532ea0daa7c901fd298eabef4fa439b370d6b1af1bf51b419a5df","abstract_canon_sha256":"2c2310f3e6de2debc88fb121b15c74c8fd2543229fb184bfefe9a5d1c2046c6d"},"schema_version":"1.0"},"canonical_sha256":"0fbe0d8485029b11a0a55340a75be1725805ae39c73c076e1ab858370726927b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:57.093638Z","signature_b64":"BA1/IN1cuLmNpFTPmMtfBruDaDk1DOfT0yU1564GUVCG5zA4H3/XKxULHSQtZUGLMtf2kqlwHxI36C325RipCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fbe0d8485029b11a0a55340a75be1725805ae39c73c076e1ab858370726927b","last_reissued_at":"2026-07-05T06:34:57.093233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:57.093233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.14063","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":"2026-07-05T06:34:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NQCEeh4FYckUZxB1CAYscht5Dg7umgRkU1S9LhUFS+Kxwc2EjuK0gQHj+vFQLqTAjXLFjmEJ5BlJikiebgzbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:51:30.628892Z"},"content_sha256":"061d2b6808e9d581428d093d265cfd62464b6ad9166979474faa9a04d6d3658d","schema_version":"1.0","event_id":"sha256:061d2b6808e9d581428d093d265cfd62464b6ad9166979474faa9a04d6d3658d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:B67A3BEFAKNRDIFFKNAKOW7BOJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ECO: Ensembling Context Optimization for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alberto Baldrati, Alberto Del Bimbo, Federico Becattini, Francesco Todino, Lorenzo Agnolucci, Marco Bertini","submitted_at":"2023-07-26T09:31:06Z","abstract_excerpt":"Image recognition has recently witnessed a paradigm shift, where vision-language models are now used to perform few-shot classification based on textual prompts. Among these, the CLIP model has shown remarkable capabilities for zero-shot transfer by matching an image and a custom textual prompt in its latent space. This has paved the way for several works that focus on engineering or learning textual contexts for maximizing CLIP's classification capabilities. In this paper, we follow this trend by learning an ensemble of prompts for image classification. We show that learning diverse and possi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14063","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/2307.14063/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":"2026-07-05T06:34:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lDgZNKbQDirSfrhemij/L+6E9A30g9UTPtFZDKUgfZ00sDeei1ssfMrrdxjFVvyNXo2qi3KMPY8WMVpg9cJkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:51:30.629261Z"},"content_sha256":"1fd60024eb378da354e93c93e179ffd6d5b53199dcdd52b4045a89ad0c230f2c","schema_version":"1.0","event_id":"sha256:1fd60024eb378da354e93c93e179ffd6d5b53199dcdd52b4045a89ad0c230f2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B67A3BEFAKNRDIFFKNAKOW7BOJ/bundle.json","state_url":"https://pith.science/pith/B67A3BEFAKNRDIFFKNAKOW7BOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B67A3BEFAKNRDIFFKNAKOW7BOJ/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":"2026-07-07T13:51:30Z","links":{"resolver":"https://pith.science/pith/B67A3BEFAKNRDIFFKNAKOW7BOJ","bundle":"https://pith.science/pith/B67A3BEFAKNRDIFFKNAKOW7BOJ/bundle.json","state":"https://pith.science/pith/B67A3BEFAKNRDIFFKNAKOW7BOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B67A3BEFAKNRDIFFKNAKOW7BOJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B67A3BEFAKNRDIFFKNAKOW7BOJ","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":"2c2310f3e6de2debc88fb121b15c74c8fd2543229fb184bfefe9a5d1c2046c6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-26T09:31:06Z","title_canon_sha256":"4d9ebdd0ad1532ea0daa7c901fd298eabef4fa439b370d6b1af1bf51b419a5df"},"schema_version":"1.0","source":{"id":"2307.14063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14063","created_at":"2026-07-05T06:34:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14063v1","created_at":"2026-07-05T06:34:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14063","created_at":"2026-07-05T06:34:57Z"},{"alias_kind":"pith_short_12","alias_value":"B67A3BEFAKNR","created_at":"2026-07-05T06:34:57Z"},{"alias_kind":"pith_short_16","alias_value":"B67A3BEFAKNRDIFF","created_at":"2026-07-05T06:34:57Z"},{"alias_kind":"pith_short_8","alias_value":"B67A3BEF","created_at":"2026-07-05T06:34:57Z"}],"graph_snapshots":[{"event_id":"sha256:1fd60024eb378da354e93c93e179ffd6d5b53199dcdd52b4045a89ad0c230f2c","target":"graph","created_at":"2026-07-05T06:34:57Z","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/2307.14063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image recognition has recently witnessed a paradigm shift, where vision-language models are now used to perform few-shot classification based on textual prompts. Among these, the CLIP model has shown remarkable capabilities for zero-shot transfer by matching an image and a custom textual prompt in its latent space. This has paved the way for several works that focus on engineering or learning textual contexts for maximizing CLIP's classification capabilities. In this paper, we follow this trend by learning an ensemble of prompts for image classification. We show that learning diverse and possi","authors_text":"Alberto Baldrati, Alberto Del Bimbo, Federico Becattini, Francesco Todino, Lorenzo Agnolucci, Marco Bertini","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-26T09:31:06Z","title":"ECO: Ensembling Context Optimization for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14063","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":"sha256:061d2b6808e9d581428d093d265cfd62464b6ad9166979474faa9a04d6d3658d","target":"record","created_at":"2026-07-05T06:34:57Z","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":"2c2310f3e6de2debc88fb121b15c74c8fd2543229fb184bfefe9a5d1c2046c6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-26T09:31:06Z","title_canon_sha256":"4d9ebdd0ad1532ea0daa7c901fd298eabef4fa439b370d6b1af1bf51b419a5df"},"schema_version":"1.0","source":{"id":"2307.14063","kind":"arxiv","version":1}},"canonical_sha256":"0fbe0d8485029b11a0a55340a75be1725805ae39c73c076e1ab858370726927b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fbe0d8485029b11a0a55340a75be1725805ae39c73c076e1ab858370726927b","first_computed_at":"2026-07-05T06:34:57.093233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:57.093233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BA1/IN1cuLmNpFTPmMtfBruDaDk1DOfT0yU1564GUVCG5zA4H3/XKxULHSQtZUGLMtf2kqlwHxI36C325RipCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:57.093638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.14063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:061d2b6808e9d581428d093d265cfd62464b6ad9166979474faa9a04d6d3658d","sha256:1fd60024eb378da354e93c93e179ffd6d5b53199dcdd52b4045a89ad0c230f2c"],"state_sha256":"ed0a2150d8d2d348d5eb197097b2e06bb159e053d51bba7fa0d3982d88f7a6e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NgMz+Ipcg53iUVyn/7Nt/E+KeKgf6B4jOfD12bhoLOc9s7RBk7dm84US9lKwCydqoHt60B/TEveQnP8Sgj7qAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:51:30.631257Z","bundle_sha256":"3a002a8b64190b0d7298b46f20faaa4f745682a3f3d478075b2e07f54a4c261d"}}