{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O4KNSMQVRCXJHZUJBV6VJ2ZE3H","short_pith_number":"pith:O4KNSMQV","canonical_record":{"source":{"id":"2412.11663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T11:11:23Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"efafde4d02f117e8ef31c98200c275ee8e9b685bab7e340ce6092a51a57d17e2","abstract_canon_sha256":"5bc15185c8b7647fbf0b2c1f0574398a7d41db19585fb6bbdfd89732ca717978"},"schema_version":"1.0"},"canonical_sha256":"7714d9321588ae93e6890d7d54eb24d9f25d9a67e648eb62cf590718ae3bebea","source":{"kind":"arxiv","id":"2412.11663","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11663","created_at":"2026-07-05T09:49:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11663v1","created_at":"2026-07-05T09:49:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11663","created_at":"2026-07-05T09:49:49Z"},{"alias_kind":"pith_short_12","alias_value":"O4KNSMQVRCXJ","created_at":"2026-07-05T09:49:49Z"},{"alias_kind":"pith_short_16","alias_value":"O4KNSMQVRCXJHZUJ","created_at":"2026-07-05T09:49:49Z"},{"alias_kind":"pith_short_8","alias_value":"O4KNSMQV","created_at":"2026-07-05T09:49:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O4KNSMQVRCXJHZUJBV6VJ2ZE3H","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T11:11:23Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"efafde4d02f117e8ef31c98200c275ee8e9b685bab7e340ce6092a51a57d17e2","abstract_canon_sha256":"5bc15185c8b7647fbf0b2c1f0574398a7d41db19585fb6bbdfd89732ca717978"},"schema_version":"1.0"},"canonical_sha256":"7714d9321588ae93e6890d7d54eb24d9f25d9a67e648eb62cf590718ae3bebea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:49.502681Z","signature_b64":"XqdZApkvbI3oPca/zH5S0ypRwOyHQbCr+pLg5Ru12hciUpPHF69EhuDZy8s8W6tyhvbqMxI5Fy0BQVVVp7zRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7714d9321588ae93e6890d7d54eb24d9f25d9a67e648eb62cf590718ae3bebea","last_reissued_at":"2026-07-05T09:49:49.502208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:49.502208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11663","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":"2026-07-05T09:49:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"edVDs0ahBg/kkYwi/576VF5VGyBFqOE9pGFMZvCapqakGubUKFArZzOTsem6s6oQssJN4oc/iW8AkwIaDu17AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:22:49.868410Z"},"content_sha256":"91f21f4ab196f4f0b53813bc82dd361daa2d57d18f1ae3b152cb4686256e5fcf","schema_version":"1.0","event_id":"sha256:91f21f4ab196f4f0b53813bc82dd361daa2d57d18f1ae3b152cb4686256e5fcf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O4KNSMQVRCXJHZUJBV6VJ2ZE3H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LMM-Regularized CLIP Embeddings for Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Maria Tzelepi, Vasileios Mezaris","submitted_at":"2024-12-16T11:11:23Z","abstract_excerpt":"In this paper we deal with image classification tasks using the powerful CLIP vision-language model. Our goal is to advance the classification performance using the CLIP's image encoder, by proposing a novel Large Multimodal Model (LMM) based regularization method. The proposed method uses an LMM to extract semantic descriptions for the images of the dataset. Then, it uses the CLIP's text encoder, frozen, in order to obtain the corresponding text embeddings and compute the mean semantic class descriptions. Subsequently, we adapt the CLIP's image encoder by adding a classification head, and we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11663","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/2412.11663/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":"2026-07-05T09:49:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3lo+UMq6OVlTMPQQVtdXsAJUSTUX7seEg3P1gKwoAujL+j8Ef7Pk7OkK1SQF5pUCKwFyWL27sdY3E4xlUTnBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:22:49.868943Z"},"content_sha256":"a0ad668e7416e9f48eb2568efe3e45d0922b99e0e6d7ae429d0374703880c20f","schema_version":"1.0","event_id":"sha256:a0ad668e7416e9f48eb2568efe3e45d0922b99e0e6d7ae429d0374703880c20f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O4KNSMQVRCXJHZUJBV6VJ2ZE3H/bundle.json","state_url":"https://pith.science/pith/O4KNSMQVRCXJHZUJBV6VJ2ZE3H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O4KNSMQVRCXJHZUJBV6VJ2ZE3H/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":"2026-08-18T08:22:49Z","links":{"resolver":"https://pith.science/pith/O4KNSMQVRCXJHZUJBV6VJ2ZE3H","bundle":"https://pith.science/pith/O4KNSMQVRCXJHZUJBV6VJ2ZE3H/bundle.json","state":"https://pith.science/pith/O4KNSMQVRCXJHZUJBV6VJ2ZE3H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O4KNSMQVRCXJHZUJBV6VJ2ZE3H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O4KNSMQVRCXJHZUJBV6VJ2ZE3H","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":"5bc15185c8b7647fbf0b2c1f0574398a7d41db19585fb6bbdfd89732ca717978","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T11:11:23Z","title_canon_sha256":"efafde4d02f117e8ef31c98200c275ee8e9b685bab7e340ce6092a51a57d17e2"},"schema_version":"1.0","source":{"id":"2412.11663","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11663","created_at":"2026-07-05T09:49:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11663v1","created_at":"2026-07-05T09:49:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11663","created_at":"2026-07-05T09:49:49Z"},{"alias_kind":"pith_short_12","alias_value":"O4KNSMQVRCXJ","created_at":"2026-07-05T09:49:49Z"},{"alias_kind":"pith_short_16","alias_value":"O4KNSMQVRCXJHZUJ","created_at":"2026-07-05T09:49:49Z"},{"alias_kind":"pith_short_8","alias_value":"O4KNSMQV","created_at":"2026-07-05T09:49:49Z"}],"graph_snapshots":[{"event_id":"sha256:a0ad668e7416e9f48eb2568efe3e45d0922b99e0e6d7ae429d0374703880c20f","target":"graph","created_at":"2026-07-05T09:49:49Z","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/2412.11663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we deal with image classification tasks using the powerful CLIP vision-language model. Our goal is to advance the classification performance using the CLIP's image encoder, by proposing a novel Large Multimodal Model (LMM) based regularization method. The proposed method uses an LMM to extract semantic descriptions for the images of the dataset. Then, it uses the CLIP's text encoder, frozen, in order to obtain the corresponding text embeddings and compute the mean semantic class descriptions. Subsequently, we adapt the CLIP's image encoder by adding a classification head, and we ","authors_text":"Maria Tzelepi, Vasileios Mezaris","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T11:11:23Z","title":"LMM-Regularized CLIP Embeddings for Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11663","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":"sha256:91f21f4ab196f4f0b53813bc82dd361daa2d57d18f1ae3b152cb4686256e5fcf","target":"record","created_at":"2026-07-05T09:49:49Z","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":"5bc15185c8b7647fbf0b2c1f0574398a7d41db19585fb6bbdfd89732ca717978","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T11:11:23Z","title_canon_sha256":"efafde4d02f117e8ef31c98200c275ee8e9b685bab7e340ce6092a51a57d17e2"},"schema_version":"1.0","source":{"id":"2412.11663","kind":"arxiv","version":1}},"canonical_sha256":"7714d9321588ae93e6890d7d54eb24d9f25d9a67e648eb62cf590718ae3bebea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7714d9321588ae93e6890d7d54eb24d9f25d9a67e648eb62cf590718ae3bebea","first_computed_at":"2026-07-05T09:49:49.502208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:49.502208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XqdZApkvbI3oPca/zH5S0ypRwOyHQbCr+pLg5Ru12hciUpPHF69EhuDZy8s8W6tyhvbqMxI5Fy0BQVVVp7zRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:49.502681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11663","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91f21f4ab196f4f0b53813bc82dd361daa2d57d18f1ae3b152cb4686256e5fcf","sha256:a0ad668e7416e9f48eb2568efe3e45d0922b99e0e6d7ae429d0374703880c20f"],"state_sha256":"8e6dd1de035f12849eeaf7db765899c743e48c5516db7e1d20ee23ce399eb214"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bc5KP+LqnUjvobuJoVxzESM6g2pzWI+fnd13bHGGtc1YQiCDBhrI6OKgMtwR8e6SXpVa1DqukxsMiAwMVuqxAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:22:49.873844Z","bundle_sha256":"ed2196179735deb04948c48a944135d2007cd5f89f42bddbba7ba06441a69462"}}