{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3RV3KM22XZRYNYMQWRFT752L3W","short_pith_number":"pith:3RV3KM22","canonical_record":{"source":{"id":"2305.07017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:56:09Z","cross_cats_sorted":[],"title_canon_sha256":"8c6a42be81e7252d8529d4e78059d58be818f6c1200c534c3ec1e2d9c495cfc3","abstract_canon_sha256":"df52e1d21854576f0de79c6d67da51c5ce86e01dc94088db928c8194d68830fe"},"schema_version":"1.0"},"canonical_sha256":"dc6bb5335abe6386e190b44b3ff74bdda73966805e13371e1dae4bf63462fab0","source":{"kind":"arxiv","id":"2305.07017","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07017","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07017v2","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07017","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_12","alias_value":"3RV3KM22XZRY","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_16","alias_value":"3RV3KM22XZRYNYMQ","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_8","alias_value":"3RV3KM22","created_at":"2026-07-05T07:06:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3RV3KM22XZRYNYMQWRFT752L3W","target":"record","payload":{"canonical_record":{"source":{"id":"2305.07017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:56:09Z","cross_cats_sorted":[],"title_canon_sha256":"8c6a42be81e7252d8529d4e78059d58be818f6c1200c534c3ec1e2d9c495cfc3","abstract_canon_sha256":"df52e1d21854576f0de79c6d67da51c5ce86e01dc94088db928c8194d68830fe"},"schema_version":"1.0"},"canonical_sha256":"dc6bb5335abe6386e190b44b3ff74bdda73966805e13371e1dae4bf63462fab0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:26.778117Z","signature_b64":"/CspnMYfpVpfiI0wZCLBbtSJChXBK0YUbC9Ue5Nn1ASzkCOWJbgsssUe4GIDuQ3PnL5g7i3vAwdsYcGjlLXqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc6bb5335abe6386e190b44b3ff74bdda73966805e13371e1dae4bf63462fab0","last_reissued_at":"2026-07-05T07:06:26.777646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:26.777646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.07017","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":"2026-07-05T07:06:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VYFujpf83taTCKfbGsiAZuFBNjwpESvHPIjW5nlHqwMcZmKCStsvRLm177pamnLrMADj0dpNlAQR+lAbkPyPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:02:37.572452Z"},"content_sha256":"891929486280ee155f3b7f8d6f4a0388af320092923cbaa766db2cf2bcb2f171","schema_version":"1.0","event_id":"sha256:891929486280ee155f3b7f8d6f4a0388af320092923cbaa766db2cf2bcb2f171"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3RV3KM22XZRYNYMQWRFT752L3W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Inverse Scaling Law for CLIP Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Xianhang Li, Zeyu Wang","submitted_at":"2023-05-11T17:56:09Z","abstract_excerpt":"CLIP, one of the pioneering foundation models that connect images and text, has enabled many recent breakthroughs in computer vision. However, its associated training cost is prohibitively high, imposing a significant barrier to its widespread exploration. In this paper, we present a surprising finding that there exists an inverse scaling law for CLIP training, whereby the larger the image/text encoders used, the shorter the sequence length of image/text tokens that can be applied in training. Moreover, we showcase that the strategy for reducing image/text token length plays a crucial role in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07017","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/2305.07017/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":"2026-07-05T07:06:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z96cVBmU2R53FN9y3+Cga2xcMpwWHaMHVqh5SY25BJmQBXnnVWiyJeMrrLgFj/KR5rDQAxMLBsKXiJxpd2VSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:02:37.572959Z"},"content_sha256":"90a24984aef5e4b588c48ee8857861ecfa797daa26b0ffb5e1e19437c2870972","schema_version":"1.0","event_id":"sha256:90a24984aef5e4b588c48ee8857861ecfa797daa26b0ffb5e1e19437c2870972"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RV3KM22XZRYNYMQWRFT752L3W/bundle.json","state_url":"https://pith.science/pith/3RV3KM22XZRYNYMQWRFT752L3W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RV3KM22XZRYNYMQWRFT752L3W/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":"2026-08-06T04:02:37Z","links":{"resolver":"https://pith.science/pith/3RV3KM22XZRYNYMQWRFT752L3W","bundle":"https://pith.science/pith/3RV3KM22XZRYNYMQWRFT752L3W/bundle.json","state":"https://pith.science/pith/3RV3KM22XZRYNYMQWRFT752L3W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RV3KM22XZRYNYMQWRFT752L3W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3RV3KM22XZRYNYMQWRFT752L3W","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":"df52e1d21854576f0de79c6d67da51c5ce86e01dc94088db928c8194d68830fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:56:09Z","title_canon_sha256":"8c6a42be81e7252d8529d4e78059d58be818f6c1200c534c3ec1e2d9c495cfc3"},"schema_version":"1.0","source":{"id":"2305.07017","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07017","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07017v2","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07017","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_12","alias_value":"3RV3KM22XZRY","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_16","alias_value":"3RV3KM22XZRYNYMQ","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_8","alias_value":"3RV3KM22","created_at":"2026-07-05T07:06:26Z"}],"graph_snapshots":[{"event_id":"sha256:90a24984aef5e4b588c48ee8857861ecfa797daa26b0ffb5e1e19437c2870972","target":"graph","created_at":"2026-07-05T07:06:26Z","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/2305.07017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CLIP, one of the pioneering foundation models that connect images and text, has enabled many recent breakthroughs in computer vision. However, its associated training cost is prohibitively high, imposing a significant barrier to its widespread exploration. In this paper, we present a surprising finding that there exists an inverse scaling law for CLIP training, whereby the larger the image/text encoders used, the shorter the sequence length of image/text tokens that can be applied in training. Moreover, we showcase that the strategy for reducing image/text token length plays a crucial role in ","authors_text":"Cihang Xie, Xianhang Li, Zeyu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:56:09Z","title":"An Inverse Scaling Law for CLIP Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07017","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":"sha256:891929486280ee155f3b7f8d6f4a0388af320092923cbaa766db2cf2bcb2f171","target":"record","created_at":"2026-07-05T07:06:26Z","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":"df52e1d21854576f0de79c6d67da51c5ce86e01dc94088db928c8194d68830fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:56:09Z","title_canon_sha256":"8c6a42be81e7252d8529d4e78059d58be818f6c1200c534c3ec1e2d9c495cfc3"},"schema_version":"1.0","source":{"id":"2305.07017","kind":"arxiv","version":2}},"canonical_sha256":"dc6bb5335abe6386e190b44b3ff74bdda73966805e13371e1dae4bf63462fab0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc6bb5335abe6386e190b44b3ff74bdda73966805e13371e1dae4bf63462fab0","first_computed_at":"2026-07-05T07:06:26.777646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:26.777646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/CspnMYfpVpfiI0wZCLBbtSJChXBK0YUbC9Ue5Nn1ASzkCOWJbgsssUe4GIDuQ3PnL5g7i3vAwdsYcGjlLXqBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:26.778117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07017","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:891929486280ee155f3b7f8d6f4a0388af320092923cbaa766db2cf2bcb2f171","sha256:90a24984aef5e4b588c48ee8857861ecfa797daa26b0ffb5e1e19437c2870972"],"state_sha256":"eaade15937130d4b1b37c09bc8f5cc5b10b5490b73bb7c8150a9fd9a9c6a1ab2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7XpwSjnEuAeBpKnyh2HNrinY457iHH9qDLDuTY247+r34ZZIyXG0kcJ3tXSq0uNWxZiwT81t93JlgmWu4HD+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:02:37.576641Z","bundle_sha256":"d853a191211dd9e931aa9f6bb71f8a09b254e02ad718838ca237d3c698bb92a4"}}