{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:BMIO4RCQ2FEY5NXKOXJ7BOLWUI","short_pith_number":"pith:BMIO4RCQ","canonical_record":{"source":{"id":"2212.00784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T18:59:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"821924d414bc72566c40b6aca741e39683d7a5da242bf515c2e4c23f650fb20b","abstract_canon_sha256":"5134267df8caf2d81c480516523d8693230e36d3bd4a4b6deb7b1e244b0ac4ca"},"schema_version":"1.0"},"canonical_sha256":"0b10ee4450d1498eb6ea75d3f0b976a21e1a0c1427ef6d0a9b776e5fc3c0e564","source":{"kind":"arxiv","id":"2212.00784","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00784","created_at":"2026-07-05T05:21:38Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00784v1","created_at":"2026-07-05T05:21:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00784","created_at":"2026-07-05T05:21:38Z"},{"alias_kind":"pith_short_12","alias_value":"BMIO4RCQ2FEY","created_at":"2026-07-05T05:21:38Z"},{"alias_kind":"pith_short_16","alias_value":"BMIO4RCQ2FEY5NXK","created_at":"2026-07-05T05:21:38Z"},{"alias_kind":"pith_short_8","alias_value":"BMIO4RCQ","created_at":"2026-07-05T05:21:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:BMIO4RCQ2FEY5NXKOXJ7BOLWUI","target":"record","payload":{"canonical_record":{"source":{"id":"2212.00784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T18:59:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"821924d414bc72566c40b6aca741e39683d7a5da242bf515c2e4c23f650fb20b","abstract_canon_sha256":"5134267df8caf2d81c480516523d8693230e36d3bd4a4b6deb7b1e244b0ac4ca"},"schema_version":"1.0"},"canonical_sha256":"0b10ee4450d1498eb6ea75d3f0b976a21e1a0c1427ef6d0a9b776e5fc3c0e564","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:38.135891Z","signature_b64":"/KoFakmqJTbfolA3r/XXmChyCbcliurffimTlqMfiPkpp4DrSyXiw/dkpM9GiuUZ8NGQC7ypgKXlkPNXXOklAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b10ee4450d1498eb6ea75d3f0b976a21e1a0c1427ef6d0a9b776e5fc3c0e564","last_reissued_at":"2026-07-05T05:21:38.135480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:38.135480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.00784","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":"2026-07-05T05:21:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8RT+RB33tlb45LTRbI2tncP6/bvJxkx0lyHmovEk1B52voz/MTNlYBTl5ZTyqqwmQnRYSadsfySNwT65s2bVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:38:21.850253Z"},"content_sha256":"3337e4d435cf108f7ec783b1dc1b9fb9600f64152ed09316cfa4bb53a3a9eb39","schema_version":"1.0","event_id":"sha256:3337e4d435cf108f7ec783b1dc1b9fb9600f64152ed09316cfa4bb53a3a9eb39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:BMIO4RCQ2FEY5NXKOXJ7BOLWUI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Zero-Shot Models with Label Distribution Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jonathan Kahana, Niv Cohen, Yedid Hoshen","submitted_at":"2022-12-01T18:59:03Z","abstract_excerpt":"Labeling large image datasets with attributes such as facial age or object type is tedious and sometimes infeasible. Supervised machine learning methods provide a highly accurate solution, but require manual labels which are often unavailable. Zero-shot models (e.g., CLIP) do not require manual labels but are not as accurate as supervised ones, particularly when the attribute is numeric. We propose a new approach, CLIPPR (CLIP with Priors), which adapts zero-shot models for regression and classification on unlabelled datasets. Our method does not use any annotated images. Instead, we assume a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00784","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/2212.00784/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":"2026-07-05T05:21:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cveEqxnLJJ9Rrvz/FddkBn/v0U1Z+XojGJCI0H+RHcgBQxelJSwpWdEQWgSbJp6ZNMbly9VbHeDTwdY9xZYDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:38:21.850935Z"},"content_sha256":"f1a2fb5e4cd26229a181de275e211054d1654d215be150f609bc1c453328ed07","schema_version":"1.0","event_id":"sha256:f1a2fb5e4cd26229a181de275e211054d1654d215be150f609bc1c453328ed07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BMIO4RCQ2FEY5NXKOXJ7BOLWUI/bundle.json","state_url":"https://pith.science/pith/BMIO4RCQ2FEY5NXKOXJ7BOLWUI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BMIO4RCQ2FEY5NXKOXJ7BOLWUI/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":"2026-08-09T17:38:21Z","links":{"resolver":"https://pith.science/pith/BMIO4RCQ2FEY5NXKOXJ7BOLWUI","bundle":"https://pith.science/pith/BMIO4RCQ2FEY5NXKOXJ7BOLWUI/bundle.json","state":"https://pith.science/pith/BMIO4RCQ2FEY5NXKOXJ7BOLWUI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BMIO4RCQ2FEY5NXKOXJ7BOLWUI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BMIO4RCQ2FEY5NXKOXJ7BOLWUI","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":"5134267df8caf2d81c480516523d8693230e36d3bd4a4b6deb7b1e244b0ac4ca","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T18:59:03Z","title_canon_sha256":"821924d414bc72566c40b6aca741e39683d7a5da242bf515c2e4c23f650fb20b"},"schema_version":"1.0","source":{"id":"2212.00784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00784","created_at":"2026-07-05T05:21:38Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00784v1","created_at":"2026-07-05T05:21:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00784","created_at":"2026-07-05T05:21:38Z"},{"alias_kind":"pith_short_12","alias_value":"BMIO4RCQ2FEY","created_at":"2026-07-05T05:21:38Z"},{"alias_kind":"pith_short_16","alias_value":"BMIO4RCQ2FEY5NXK","created_at":"2026-07-05T05:21:38Z"},{"alias_kind":"pith_short_8","alias_value":"BMIO4RCQ","created_at":"2026-07-05T05:21:38Z"}],"graph_snapshots":[{"event_id":"sha256:f1a2fb5e4cd26229a181de275e211054d1654d215be150f609bc1c453328ed07","target":"graph","created_at":"2026-07-05T05:21:38Z","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/2212.00784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Labeling large image datasets with attributes such as facial age or object type is tedious and sometimes infeasible. Supervised machine learning methods provide a highly accurate solution, but require manual labels which are often unavailable. Zero-shot models (e.g., CLIP) do not require manual labels but are not as accurate as supervised ones, particularly when the attribute is numeric. We propose a new approach, CLIPPR (CLIP with Priors), which adapts zero-shot models for regression and classification on unlabelled datasets. Our method does not use any annotated images. Instead, we assume a ","authors_text":"Jonathan Kahana, Niv Cohen, Yedid Hoshen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T18:59:03Z","title":"Improving Zero-Shot Models with Label Distribution Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00784","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":"sha256:3337e4d435cf108f7ec783b1dc1b9fb9600f64152ed09316cfa4bb53a3a9eb39","target":"record","created_at":"2026-07-05T05:21:38Z","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":"5134267df8caf2d81c480516523d8693230e36d3bd4a4b6deb7b1e244b0ac4ca","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T18:59:03Z","title_canon_sha256":"821924d414bc72566c40b6aca741e39683d7a5da242bf515c2e4c23f650fb20b"},"schema_version":"1.0","source":{"id":"2212.00784","kind":"arxiv","version":1}},"canonical_sha256":"0b10ee4450d1498eb6ea75d3f0b976a21e1a0c1427ef6d0a9b776e5fc3c0e564","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b10ee4450d1498eb6ea75d3f0b976a21e1a0c1427ef6d0a9b776e5fc3c0e564","first_computed_at":"2026-07-05T05:21:38.135480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:38.135480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/KoFakmqJTbfolA3r/XXmChyCbcliurffimTlqMfiPkpp4DrSyXiw/dkpM9GiuUZ8NGQC7ypgKXlkPNXXOklAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:38.135891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.00784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3337e4d435cf108f7ec783b1dc1b9fb9600f64152ed09316cfa4bb53a3a9eb39","sha256:f1a2fb5e4cd26229a181de275e211054d1654d215be150f609bc1c453328ed07"],"state_sha256":"cb001d7551ab9389fe2911710524dec6ebe6b547ec7115487852529833a00849"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mi9faD+tcgHXOZ0DiXNFNN/D7LHkeSt2IaIr2hHNByizlvYMl5m6TO89WSvh1bVIqgTIn5Onaq45J/udB1u0DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:38:21.857052Z","bundle_sha256":"8958d692b3b292deb1ce0ef0d4c17fe376a3784b5dde8291355839f633f8e365"}}