{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JUXDGH2G3MAHCZW3IHJYUL3LDS","short_pith_number":"pith:JUXDGH2G","canonical_record":{"source":{"id":"2311.17049","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:55:42Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"33c76664002c96b6c1072073e8d44ea907c645def518448c5635ed8a0d52832a","abstract_canon_sha256":"2624bbf32d8b8687d09f57e65c20d7bb53bc3d848205f8d3666423ec2687ad69"},"schema_version":"1.0"},"canonical_sha256":"4d2e331f46db007166db41d38a2f6b1c89e01b9bd1c139c2a83a9cb687fc7cb8","source":{"kind":"arxiv","id":"2311.17049","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17049","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17049v2","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17049","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"pith_short_12","alias_value":"JUXDGH2G3MAH","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"pith_short_16","alias_value":"JUXDGH2G3MAHCZW3","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"pith_short_8","alias_value":"JUXDGH2G","created_at":"2026-07-05T08:02:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JUXDGH2G3MAHCZW3IHJYUL3LDS","target":"record","payload":{"canonical_record":{"source":{"id":"2311.17049","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:55:42Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"33c76664002c96b6c1072073e8d44ea907c645def518448c5635ed8a0d52832a","abstract_canon_sha256":"2624bbf32d8b8687d09f57e65c20d7bb53bc3d848205f8d3666423ec2687ad69"},"schema_version":"1.0"},"canonical_sha256":"4d2e331f46db007166db41d38a2f6b1c89e01b9bd1c139c2a83a9cb687fc7cb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:48.625548Z","signature_b64":"2HnpAbiTexYDvSLd4qjWa2qUl/98x9HhhZXXVJ2yhtgKnz1U+xi0wqbLIflabLUcVwQKxADXofX+KhpKWywdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d2e331f46db007166db41d38a2f6b1c89e01b9bd1c139c2a83a9cb687fc7cb8","last_reissued_at":"2026-07-05T08:02:48.624793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:48.624793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.17049","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":"2026-07-05T08:02:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FGNlp18sDLhyNlvAwwaw88EyrHetDyx4bRqxmCWEt815Wk84L0et63GDufeeNX2jm476ScC+JZjHW89x81qhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:16:40.072203Z"},"content_sha256":"512a6f5bc3f09c8efa537b4af344ad773c5326c0375c9f93da84c34a54fce2a0","schema_version":"1.0","event_id":"sha256:512a6f5bc3f09c8efa537b4af344ad773c5326c0375c9f93da84c34a54fce2a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JUXDGH2G3MAHCZW3IHJYUL3LDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fartash Faghri, Hadi Pouransari, Oncel Tuzel, Pavan Kumar Anasosalu Vasu, Raviteja Vemulapalli","submitted_at":"2023-11-28T18:55:42Z","abstract_excerpt":"Contrastive pretraining of image-text foundation models, such as CLIP, demonstrated excellent zero-shot performance and improved robustness on a wide range of downstream tasks. However, these models utilize large transformer-based encoders with significant memory and latency overhead which pose challenges for deployment on mobile devices. In this work, we introduce MobileCLIP -- a new family of efficient image-text models optimized for runtime performance along with a novel and efficient training approach, namely multi-modal reinforced training. The proposed training approach leverages knowled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17049","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/2311.17049/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":"2026-07-05T08:02:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P33pQwI5gF6AE1sTuSrW6/fctCJVDQH8Eay/ozzawM7IfeFabVqgtSXa0nzzp0cCGAn+U69YtIiKZBC2gjEDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:16:40.072751Z"},"content_sha256":"7611b7ad1cf809fa6926313c71c0b6b62964ffa3cce1e7973a15f2827b1b1e57","schema_version":"1.0","event_id":"sha256:7611b7ad1cf809fa6926313c71c0b6b62964ffa3cce1e7973a15f2827b1b1e57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JUXDGH2G3MAHCZW3IHJYUL3LDS/bundle.json","state_url":"https://pith.science/pith/JUXDGH2G3MAHCZW3IHJYUL3LDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JUXDGH2G3MAHCZW3IHJYUL3LDS/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":"2026-08-07T00:16:40Z","links":{"resolver":"https://pith.science/pith/JUXDGH2G3MAHCZW3IHJYUL3LDS","bundle":"https://pith.science/pith/JUXDGH2G3MAHCZW3IHJYUL3LDS/bundle.json","state":"https://pith.science/pith/JUXDGH2G3MAHCZW3IHJYUL3LDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JUXDGH2G3MAHCZW3IHJYUL3LDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JUXDGH2G3MAHCZW3IHJYUL3LDS","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":"2624bbf32d8b8687d09f57e65c20d7bb53bc3d848205f8d3666423ec2687ad69","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:55:42Z","title_canon_sha256":"33c76664002c96b6c1072073e8d44ea907c645def518448c5635ed8a0d52832a"},"schema_version":"1.0","source":{"id":"2311.17049","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17049","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17049v2","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17049","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"pith_short_12","alias_value":"JUXDGH2G3MAH","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"pith_short_16","alias_value":"JUXDGH2G3MAHCZW3","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"pith_short_8","alias_value":"JUXDGH2G","created_at":"2026-07-05T08:02:48Z"}],"graph_snapshots":[{"event_id":"sha256:7611b7ad1cf809fa6926313c71c0b6b62964ffa3cce1e7973a15f2827b1b1e57","target":"graph","created_at":"2026-07-05T08:02:48Z","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/2311.17049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive pretraining of image-text foundation models, such as CLIP, demonstrated excellent zero-shot performance and improved robustness on a wide range of downstream tasks. However, these models utilize large transformer-based encoders with significant memory and latency overhead which pose challenges for deployment on mobile devices. In this work, we introduce MobileCLIP -- a new family of efficient image-text models optimized for runtime performance along with a novel and efficient training approach, namely multi-modal reinforced training. The proposed training approach leverages knowled","authors_text":"Fartash Faghri, Hadi Pouransari, Oncel Tuzel, Pavan Kumar Anasosalu Vasu, Raviteja Vemulapalli","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:55:42Z","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17049","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":"sha256:512a6f5bc3f09c8efa537b4af344ad773c5326c0375c9f93da84c34a54fce2a0","target":"record","created_at":"2026-07-05T08:02:48Z","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":"2624bbf32d8b8687d09f57e65c20d7bb53bc3d848205f8d3666423ec2687ad69","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:55:42Z","title_canon_sha256":"33c76664002c96b6c1072073e8d44ea907c645def518448c5635ed8a0d52832a"},"schema_version":"1.0","source":{"id":"2311.17049","kind":"arxiv","version":2}},"canonical_sha256":"4d2e331f46db007166db41d38a2f6b1c89e01b9bd1c139c2a83a9cb687fc7cb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d2e331f46db007166db41d38a2f6b1c89e01b9bd1c139c2a83a9cb687fc7cb8","first_computed_at":"2026-07-05T08:02:48.624793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:48.624793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2HnpAbiTexYDvSLd4qjWa2qUl/98x9HhhZXXVJ2yhtgKnz1U+xi0wqbLIflabLUcVwQKxADXofX+KhpKWywdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:48.625548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17049","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:512a6f5bc3f09c8efa537b4af344ad773c5326c0375c9f93da84c34a54fce2a0","sha256:7611b7ad1cf809fa6926313c71c0b6b62964ffa3cce1e7973a15f2827b1b1e57"],"state_sha256":"e6b7999e80b767569301b16b35df3b82c381c7caf22bc58aaed9510d91c02437"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wGW9t8/t7t6fAe8cSmziBBv7B2WMdwPQLSGQtuJh3s9leHDUa0/KwpCZCNx6NcQtBie2KizX8scyjzlUKS5tBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:16:40.146550Z","bundle_sha256":"3d47bdf29fbfe8ec2fd62da2c5e729b3cc6accb0fbc0a046a2e6913b40552993"}}