{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:X3NYBCI3OHDVUR3BNTLBB6JXYD","short_pith_number":"pith:X3NYBCI3","canonical_record":{"source":{"id":"2508.20691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T11:50:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"66b2b83e4cf1cd76f98c1ee5216f7a54db7dc54a10bcb29d9041f0d189f53718","abstract_canon_sha256":"f4a806c3c880071c8531bb9beb60a5fc8e73ff45e0a788277722328cb71a6164"},"schema_version":"1.0"},"canonical_sha256":"bedb80891b71c75a47616cd610f937c0f1335910615ccc43d294d434f0baba8f","source":{"kind":"arxiv","id":"2508.20691","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20691","created_at":"2026-07-05T12:00:58Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20691v1","created_at":"2026-07-05T12:00:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20691","created_at":"2026-07-05T12:00:58Z"},{"alias_kind":"pith_short_12","alias_value":"X3NYBCI3OHDV","created_at":"2026-07-05T12:00:58Z"},{"alias_kind":"pith_short_16","alias_value":"X3NYBCI3OHDVUR3B","created_at":"2026-07-05T12:00:58Z"},{"alias_kind":"pith_short_8","alias_value":"X3NYBCI3","created_at":"2026-07-05T12:00:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:X3NYBCI3OHDVUR3BNTLBB6JXYD","target":"record","payload":{"canonical_record":{"source":{"id":"2508.20691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T11:50:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"66b2b83e4cf1cd76f98c1ee5216f7a54db7dc54a10bcb29d9041f0d189f53718","abstract_canon_sha256":"f4a806c3c880071c8531bb9beb60a5fc8e73ff45e0a788277722328cb71a6164"},"schema_version":"1.0"},"canonical_sha256":"bedb80891b71c75a47616cd610f937c0f1335910615ccc43d294d434f0baba8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:58.074568Z","signature_b64":"KKZIKhzKE0cdfBb3nVJvBMByNS/JWy9x81KzEos6dRSlKgK4h5+yn2EUN2m7pbDGpqi56dEG8yPGBW3lRciiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bedb80891b71c75a47616cd610f937c0f1335910615ccc43d294d434f0baba8f","last_reissued_at":"2026-07-05T12:00:58.074065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:58.074065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.20691","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":"2026-07-05T12:00:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CCjmpd7SqhVkZSnsdceLdLe/HG0ZpH77dA2hSoIdmH90rtwWp9iIokKTRC/eKtn0SQ1AKLOZzl1frrkKnjQfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:43:10.333552Z"},"content_sha256":"dead5285bec5e675f6028063eb48789d19ec38859add4d76019fd297de1f2663","schema_version":"1.0","event_id":"sha256:dead5285bec5e675f6028063eb48789d19ec38859add4d76019fd297de1f2663"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:X3NYBCI3OHDVUR3BNTLBB6JXYD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Toshev, Cem Koc, Fartash Faghri, Hadi Pouransari, Oncel Tuzel, Pavan Kumar Anasosalu Vasu, Vaishaal Shankar","submitted_at":"2025-08-28T11:50:22Z","abstract_excerpt":"Foundation image-text models such as CLIP with zero-shot capabilities enable a wide array of applications. MobileCLIP is a recent family of image-text models at 3-15ms latency and 50-150M parameters with state-of-the-art zero-shot accuracy. The main ingredients in MobileCLIP were its low-latency and light architectures and a novel multi-modal reinforced training that made knowledge distillation from multiple caption-generators and CLIP teachers efficient, scalable, and reproducible. In this paper, we improve the multi-modal reinforced training of MobileCLIP through: 1) better CLIP teacher ense"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20691","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/2508.20691/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":"2026-07-05T12:00:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PMKQ2MB+aCfkzBmi/13Frwr72oYLA/HPElE3C90HK+mSFo+sajAu+gmJsdYoko+FxYskdXDUo+lzYAEc/4AuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:43:10.334050Z"},"content_sha256":"5e1cd64e4dba549ff6ed4b0c2031de9988b632a7b1ab361de97047fa2f92d79d","schema_version":"1.0","event_id":"sha256:5e1cd64e4dba549ff6ed4b0c2031de9988b632a7b1ab361de97047fa2f92d79d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X3NYBCI3OHDVUR3BNTLBB6JXYD/bundle.json","state_url":"https://pith.science/pith/X3NYBCI3OHDVUR3BNTLBB6JXYD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X3NYBCI3OHDVUR3BNTLBB6JXYD/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":"2026-08-23T12:43:10Z","links":{"resolver":"https://pith.science/pith/X3NYBCI3OHDVUR3BNTLBB6JXYD","bundle":"https://pith.science/pith/X3NYBCI3OHDVUR3BNTLBB6JXYD/bundle.json","state":"https://pith.science/pith/X3NYBCI3OHDVUR3BNTLBB6JXYD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X3NYBCI3OHDVUR3BNTLBB6JXYD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X3NYBCI3OHDVUR3BNTLBB6JXYD","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":"f4a806c3c880071c8531bb9beb60a5fc8e73ff45e0a788277722328cb71a6164","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T11:50:22Z","title_canon_sha256":"66b2b83e4cf1cd76f98c1ee5216f7a54db7dc54a10bcb29d9041f0d189f53718"},"schema_version":"1.0","source":{"id":"2508.20691","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20691","created_at":"2026-07-05T12:00:58Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20691v1","created_at":"2026-07-05T12:00:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20691","created_at":"2026-07-05T12:00:58Z"},{"alias_kind":"pith_short_12","alias_value":"X3NYBCI3OHDV","created_at":"2026-07-05T12:00:58Z"},{"alias_kind":"pith_short_16","alias_value":"X3NYBCI3OHDVUR3B","created_at":"2026-07-05T12:00:58Z"},{"alias_kind":"pith_short_8","alias_value":"X3NYBCI3","created_at":"2026-07-05T12:00:58Z"}],"graph_snapshots":[{"event_id":"sha256:5e1cd64e4dba549ff6ed4b0c2031de9988b632a7b1ab361de97047fa2f92d79d","target":"graph","created_at":"2026-07-05T12:00:58Z","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/2508.20691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation image-text models such as CLIP with zero-shot capabilities enable a wide array of applications. MobileCLIP is a recent family of image-text models at 3-15ms latency and 50-150M parameters with state-of-the-art zero-shot accuracy. The main ingredients in MobileCLIP were its low-latency and light architectures and a novel multi-modal reinforced training that made knowledge distillation from multiple caption-generators and CLIP teachers efficient, scalable, and reproducible. In this paper, we improve the multi-modal reinforced training of MobileCLIP through: 1) better CLIP teacher ense","authors_text":"Alexander Toshev, Cem Koc, Fartash Faghri, Hadi Pouransari, Oncel Tuzel, Pavan Kumar Anasosalu Vasu, Vaishaal Shankar","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T11:50:22Z","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20691","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:dead5285bec5e675f6028063eb48789d19ec38859add4d76019fd297de1f2663","target":"record","created_at":"2026-07-05T12:00:58Z","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":"f4a806c3c880071c8531bb9beb60a5fc8e73ff45e0a788277722328cb71a6164","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T11:50:22Z","title_canon_sha256":"66b2b83e4cf1cd76f98c1ee5216f7a54db7dc54a10bcb29d9041f0d189f53718"},"schema_version":"1.0","source":{"id":"2508.20691","kind":"arxiv","version":1}},"canonical_sha256":"bedb80891b71c75a47616cd610f937c0f1335910615ccc43d294d434f0baba8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bedb80891b71c75a47616cd610f937c0f1335910615ccc43d294d434f0baba8f","first_computed_at":"2026-07-05T12:00:58.074065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:58.074065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KKZIKhzKE0cdfBb3nVJvBMByNS/JWy9x81KzEos6dRSlKgK4h5+yn2EUN2m7pbDGpqi56dEG8yPGBW3lRciiAg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:58.074568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20691","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dead5285bec5e675f6028063eb48789d19ec38859add4d76019fd297de1f2663","sha256:5e1cd64e4dba549ff6ed4b0c2031de9988b632a7b1ab361de97047fa2f92d79d"],"state_sha256":"dd3544e0757d7ed9a8d48035ba44fdddce746d74d62f8061a167ab60aa77f801"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OSQ4SpE5E5uFBQ5VafDTCzakYYP9N/5woAzDnL9j1X8numrfBTNTlaX8irMspm0J1eeqwAX4ZgLWEjLm0gXPDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T12:43:10.342339Z","bundle_sha256":"5883913bccd7f083c4e9f6a2565e08745c4d123340411c13bb5c476bd3d67681"}}