{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EK4QNLNQ6V3SFLU2T44GPQ5P6D","short_pith_number":"pith:EK4QNLNQ","canonical_record":{"source":{"id":"2412.03513","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-04T17:56:49Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"f3f59b97bd6ed04d37f8c6016ec462ac05aa75ee323fedba2b81f1e1f2c1cbb1","abstract_canon_sha256":"b22e00391178495497bb92248aac98d12798e759ee2bb135cfd42c6373640866"},"schema_version":"1.0"},"canonical_sha256":"22b906adb0f57722ae9a9f3867c3aff0d804d43ccf51c364b855eaacfc840b82","source":{"kind":"arxiv","id":"2412.03513","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03513","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03513v2","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03513","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"EK4QNLNQ6V3S","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_16","alias_value":"EK4QNLNQ6V3SFLU2","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_8","alias_value":"EK4QNLNQ","created_at":"2026-07-05T09:45:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EK4QNLNQ6V3SFLU2T44GPQ5P6D","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03513","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-04T17:56:49Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"f3f59b97bd6ed04d37f8c6016ec462ac05aa75ee323fedba2b81f1e1f2c1cbb1","abstract_canon_sha256":"b22e00391178495497bb92248aac98d12798e759ee2bb135cfd42c6373640866"},"schema_version":"1.0"},"canonical_sha256":"22b906adb0f57722ae9a9f3867c3aff0d804d43ccf51c364b855eaacfc840b82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:59.903676Z","signature_b64":"3WakUTC5X4CS0VbbiYC81IurEN3+2/Uy4cgStyfZDQHIXlMj0ImTcj1u7kqSztQHkoCZC17V4OqGthYpYcZ7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22b906adb0f57722ae9a9f3867c3aff0d804d43ccf51c364b855eaacfc840b82","last_reissued_at":"2026-07-05T09:45:59.903160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:59.903160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03513","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:45:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XBpGrb+RHVqNAlw6+xKGIprMgU2IFEJxDBY9FUm5VUXk6gT4bNF38RnXOctVBpkM88h3pUNJ9jCkGdcrOPo7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:45:22.823038Z"},"content_sha256":"c91df8bc0b108f94e0117ba994561cf5003bd4788bff725168b5d9e7b8029987","schema_version":"1.0","event_id":"sha256:c91df8bc0b108f94e0117ba994561cf5003bd4788bff725168b5d9e7b8029987"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EK4QNLNQ6V3SFLU2T44GPQ5P6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing CLIP Conceptual Embedding through Knowledge Distillation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Kuei-Chun Kao","submitted_at":"2024-12-04T17:56:49Z","abstract_excerpt":"Recently, CLIP has become an important model for aligning images and text in multi-modal contexts. However, researchers have identified limitations in the ability of CLIP's text and image encoders to extract detailed knowledge from pairs of captions and images. In response, this paper presents Knowledge-CLIP, an innovative approach designed to improve CLIP's performance by integrating a new knowledge distillation (KD) method based on Llama 2. Our approach focuses on three key objectives: Text Embedding Distillation, Concept Learning, and Contrastive Learning. First, Text Embedding Distillation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03513","kind":"arxiv","version":2},"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/2412.03513/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":"2026-07-05T09:45:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WtboegMEilQCYiQn+rpzoV/6aqVcxIDAK61rs1EQHU9cgfHORcnT+7393OEnsa/lMZaOYgo3J6NIOyC3ajxaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:45:22.823783Z"},"content_sha256":"25c04ba58fc0292e5b6718fcb6bb5db64f3c1159dba8e387d0f3533f13f84a2e","schema_version":"1.0","event_id":"sha256:25c04ba58fc0292e5b6718fcb6bb5db64f3c1159dba8e387d0f3533f13f84a2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EK4QNLNQ6V3SFLU2T44GPQ5P6D/bundle.json","state_url":"https://pith.science/pith/EK4QNLNQ6V3SFLU2T44GPQ5P6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EK4QNLNQ6V3SFLU2T44GPQ5P6D/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":"2026-08-14T18:45:22Z","links":{"resolver":"https://pith.science/pith/EK4QNLNQ6V3SFLU2T44GPQ5P6D","bundle":"https://pith.science/pith/EK4QNLNQ6V3SFLU2T44GPQ5P6D/bundle.json","state":"https://pith.science/pith/EK4QNLNQ6V3SFLU2T44GPQ5P6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EK4QNLNQ6V3SFLU2T44GPQ5P6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EK4QNLNQ6V3SFLU2T44GPQ5P6D","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":"b22e00391178495497bb92248aac98d12798e759ee2bb135cfd42c6373640866","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-04T17:56:49Z","title_canon_sha256":"f3f59b97bd6ed04d37f8c6016ec462ac05aa75ee323fedba2b81f1e1f2c1cbb1"},"schema_version":"1.0","source":{"id":"2412.03513","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03513","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03513v2","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03513","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"EK4QNLNQ6V3S","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_16","alias_value":"EK4QNLNQ6V3SFLU2","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_8","alias_value":"EK4QNLNQ","created_at":"2026-07-05T09:45:59Z"}],"graph_snapshots":[{"event_id":"sha256:25c04ba58fc0292e5b6718fcb6bb5db64f3c1159dba8e387d0f3533f13f84a2e","target":"graph","created_at":"2026-07-05T09:45:59Z","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/2412.03513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, CLIP has become an important model for aligning images and text in multi-modal contexts. However, researchers have identified limitations in the ability of CLIP's text and image encoders to extract detailed knowledge from pairs of captions and images. In response, this paper presents Knowledge-CLIP, an innovative approach designed to improve CLIP's performance by integrating a new knowledge distillation (KD) method based on Llama 2. Our approach focuses on three key objectives: Text Embedding Distillation, Concept Learning, and Contrastive Learning. First, Text Embedding Distillation","authors_text":"Kuei-Chun Kao","cross_cats":["cs.CL","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-04T17:56:49Z","title":"Enhancing CLIP Conceptual Embedding through Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03513","kind":"arxiv","version":2},"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:c91df8bc0b108f94e0117ba994561cf5003bd4788bff725168b5d9e7b8029987","target":"record","created_at":"2026-07-05T09:45:59Z","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":"b22e00391178495497bb92248aac98d12798e759ee2bb135cfd42c6373640866","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-04T17:56:49Z","title_canon_sha256":"f3f59b97bd6ed04d37f8c6016ec462ac05aa75ee323fedba2b81f1e1f2c1cbb1"},"schema_version":"1.0","source":{"id":"2412.03513","kind":"arxiv","version":2}},"canonical_sha256":"22b906adb0f57722ae9a9f3867c3aff0d804d43ccf51c364b855eaacfc840b82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22b906adb0f57722ae9a9f3867c3aff0d804d43ccf51c364b855eaacfc840b82","first_computed_at":"2026-07-05T09:45:59.903160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:59.903160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3WakUTC5X4CS0VbbiYC81IurEN3+2/Uy4cgStyfZDQHIXlMj0ImTcj1u7kqSztQHkoCZC17V4OqGthYpYcZ7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:59.903676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03513","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c91df8bc0b108f94e0117ba994561cf5003bd4788bff725168b5d9e7b8029987","sha256:25c04ba58fc0292e5b6718fcb6bb5db64f3c1159dba8e387d0f3533f13f84a2e"],"state_sha256":"014a4fa7d04b737ef4c6af392158767a895f0a0183cef9370953dfb93f00452d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XmMA1HRzncn1exiH1jRAsIxfDqPh0np7xh8eLv5ODXgpVtfdpNng1X43sQKUpIdIzvRr1OqIjCtIth1q33vSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:45:22.830025Z","bundle_sha256":"5b969c61589f77c58017de3692b2b034a2b856678d50c0f7468eb362153e3254"}}