{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EFJL65OYUG4CMF7DATZEC7U3PM","short_pith_number":"pith:EFJL65OY","canonical_record":{"source":{"id":"2408.09441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-18T11:23:21Z","cross_cats_sorted":[],"title_canon_sha256":"101477fabbbcaa9ad28c0f7cbf1655f4a2169d8a3a5dbfb8691b297f73b4671c","abstract_canon_sha256":"bb4f863129c4443bab1e8ddaa3c840c64040d332652d09bdceb08512d439321b"},"schema_version":"1.0"},"canonical_sha256":"2152bf75d8a1b82617e304f2417e9b7b24a83f6503803b48b781f59c4dd20117","source":{"kind":"arxiv","id":"2408.09441","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09441","created_at":"2026-07-05T09:49:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09441v2","created_at":"2026-07-05T09:49:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09441","created_at":"2026-07-05T09:49:44Z"},{"alias_kind":"pith_short_12","alias_value":"EFJL65OYUG4C","created_at":"2026-07-05T09:49:44Z"},{"alias_kind":"pith_short_16","alias_value":"EFJL65OYUG4CMF7D","created_at":"2026-07-05T09:49:44Z"},{"alias_kind":"pith_short_8","alias_value":"EFJL65OY","created_at":"2026-07-05T09:49:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EFJL65OYUG4CMF7DATZEC7U3PM","target":"record","payload":{"canonical_record":{"source":{"id":"2408.09441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-18T11:23:21Z","cross_cats_sorted":[],"title_canon_sha256":"101477fabbbcaa9ad28c0f7cbf1655f4a2169d8a3a5dbfb8691b297f73b4671c","abstract_canon_sha256":"bb4f863129c4443bab1e8ddaa3c840c64040d332652d09bdceb08512d439321b"},"schema_version":"1.0"},"canonical_sha256":"2152bf75d8a1b82617e304f2417e9b7b24a83f6503803b48b781f59c4dd20117","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:44.465680Z","signature_b64":"+ymw0UWuBLWKVDJG5faxP5thCQ3W1yNWdad5vIYFqNhWWRNK/vgAQxd2KdHzPotq9UqaMTPyAW7JzU3Y85HsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2152bf75d8a1b82617e304f2417e9b7b24a83f6503803b48b781f59c4dd20117","last_reissued_at":"2026-07-05T09:49:44.465206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:44.465206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.09441","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":"2026-07-05T09:49:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIC+lBR1sZhR9TDYfJepil7dPx/aRZiDE6yYw4zbE4UR/xUMSgCJCme3xTf9j6ooUNbFFlMG84wGA21TgQhgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:31:40.184899Z"},"content_sha256":"aaf2132bf16e31d332e5e2ee175aa95ce0bf8e5b179ce09d5fc48a54abe854a1","schema_version":"1.0","event_id":"sha256:aaf2132bf16e31d332e5e2ee175aa95ce0bf8e5b179ce09d5fc48a54abe854a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EFJL65OYUG4CMF7DATZEC7U3PM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiqiang Jiang, Jiankang Deng, Kaicheng Yang, Tiancheng Gu, Weidong Cai, Xiang An, Xiangzi Dai, Ziyong Feng","submitted_at":"2024-08-18T11:23:21Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. However, the effectiveness of CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption of computational resources. Although knowledge distillation has been widely applied in single modality models, how to efficiently expand knowledge distillation to vision-language foundation models with extensive data remains relatively unexplored. In this paper, we introduce CLIP-CID, a novel distillation mechanism that effectively transfers knowledge from a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09441","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/2408.09441/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":"2026-07-05T09:49:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fdrBu6Dr+cuxI23Rbwz9hec3xga8Sa15U/LiM+KmAsMDthJoJKO8G3C9huCp4SOFd8HwQIrcHRNe4LTOEWEpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:31:40.185550Z"},"content_sha256":"238086a349e3162dadf59ed07c91b99c86f1fd7e9fb7f698cef8f55b64b1b454","schema_version":"1.0","event_id":"sha256:238086a349e3162dadf59ed07c91b99c86f1fd7e9fb7f698cef8f55b64b1b454"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EFJL65OYUG4CMF7DATZEC7U3PM/bundle.json","state_url":"https://pith.science/pith/EFJL65OYUG4CMF7DATZEC7U3PM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EFJL65OYUG4CMF7DATZEC7U3PM/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":"2026-07-07T06:31:40Z","links":{"resolver":"https://pith.science/pith/EFJL65OYUG4CMF7DATZEC7U3PM","bundle":"https://pith.science/pith/EFJL65OYUG4CMF7DATZEC7U3PM/bundle.json","state":"https://pith.science/pith/EFJL65OYUG4CMF7DATZEC7U3PM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EFJL65OYUG4CMF7DATZEC7U3PM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EFJL65OYUG4CMF7DATZEC7U3PM","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":"bb4f863129c4443bab1e8ddaa3c840c64040d332652d09bdceb08512d439321b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-18T11:23:21Z","title_canon_sha256":"101477fabbbcaa9ad28c0f7cbf1655f4a2169d8a3a5dbfb8691b297f73b4671c"},"schema_version":"1.0","source":{"id":"2408.09441","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09441","created_at":"2026-07-05T09:49:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09441v2","created_at":"2026-07-05T09:49:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09441","created_at":"2026-07-05T09:49:44Z"},{"alias_kind":"pith_short_12","alias_value":"EFJL65OYUG4C","created_at":"2026-07-05T09:49:44Z"},{"alias_kind":"pith_short_16","alias_value":"EFJL65OYUG4CMF7D","created_at":"2026-07-05T09:49:44Z"},{"alias_kind":"pith_short_8","alias_value":"EFJL65OY","created_at":"2026-07-05T09:49:44Z"}],"graph_snapshots":[{"event_id":"sha256:238086a349e3162dadf59ed07c91b99c86f1fd7e9fb7f698cef8f55b64b1b454","target":"graph","created_at":"2026-07-05T09:49:44Z","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/2408.09441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. However, the effectiveness of CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption of computational resources. Although knowledge distillation has been widely applied in single modality models, how to efficiently expand knowledge distillation to vision-language foundation models with extensive data remains relatively unexplored. In this paper, we introduce CLIP-CID, a novel distillation mechanism that effectively transfers knowledge from a ","authors_text":"Haiqiang Jiang, Jiankang Deng, Kaicheng Yang, Tiancheng Gu, Weidong Cai, Xiang An, Xiangzi Dai, Ziyong Feng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-18T11:23:21Z","title":"CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09441","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:aaf2132bf16e31d332e5e2ee175aa95ce0bf8e5b179ce09d5fc48a54abe854a1","target":"record","created_at":"2026-07-05T09:49:44Z","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":"bb4f863129c4443bab1e8ddaa3c840c64040d332652d09bdceb08512d439321b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-18T11:23:21Z","title_canon_sha256":"101477fabbbcaa9ad28c0f7cbf1655f4a2169d8a3a5dbfb8691b297f73b4671c"},"schema_version":"1.0","source":{"id":"2408.09441","kind":"arxiv","version":2}},"canonical_sha256":"2152bf75d8a1b82617e304f2417e9b7b24a83f6503803b48b781f59c4dd20117","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2152bf75d8a1b82617e304f2417e9b7b24a83f6503803b48b781f59c4dd20117","first_computed_at":"2026-07-05T09:49:44.465206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:44.465206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ymw0UWuBLWKVDJG5faxP5thCQ3W1yNWdad5vIYFqNhWWRNK/vgAQxd2KdHzPotq9UqaMTPyAW7JzU3Y85HsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:44.465680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09441","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaf2132bf16e31d332e5e2ee175aa95ce0bf8e5b179ce09d5fc48a54abe854a1","sha256:238086a349e3162dadf59ed07c91b99c86f1fd7e9fb7f698cef8f55b64b1b454"],"state_sha256":"053a93d27aa2c6c23b41389e3f1d0144250f5d4f05de8f9ac2d57f6e1dccc264"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gy5dPsxu45O5KHeeFwSLHET44yqKdNInZ1RFPgKhhCipTvtRNclj2x2MbvsoprXM7vYcGSlD9Hp8Ky2ClQYKBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:31:40.188760Z","bundle_sha256":"bfb934f92439cb211770dd448825096ab5421534a0623072712405dc3d2ab42a"}}