{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G2LZ6VBD5AB7253NR5PD57LD2Z","short_pith_number":"pith:G2LZ6VBD","canonical_record":{"source":{"id":"2506.22881","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T13:36:44Z","cross_cats_sorted":[],"title_canon_sha256":"40a8f7860e70a8e241e20ba8e6f08a778df1c4e9498dccadc4b3b825077c838e","abstract_canon_sha256":"c5df4ed14fd84f8b9434508767e9f1329d50b1cbeac4fb3a239c4be8485eef16"},"schema_version":"1.0"},"canonical_sha256":"36979f5423e803fd776d8f5e3efd63d67961845a7b7a0ced67fa568b3e581770","source":{"kind":"arxiv","id":"2506.22881","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22881","created_at":"2026-06-02T02:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22881v3","created_at":"2026-06-02T02:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22881","created_at":"2026-06-02T02:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"G2LZ6VBD5AB7","created_at":"2026-06-02T02:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"G2LZ6VBD5AB7253N","created_at":"2026-06-02T02:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"G2LZ6VBD","created_at":"2026-06-02T02:04:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G2LZ6VBD5AB7253NR5PD57LD2Z","target":"record","payload":{"canonical_record":{"source":{"id":"2506.22881","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T13:36:44Z","cross_cats_sorted":[],"title_canon_sha256":"40a8f7860e70a8e241e20ba8e6f08a778df1c4e9498dccadc4b3b825077c838e","abstract_canon_sha256":"c5df4ed14fd84f8b9434508767e9f1329d50b1cbeac4fb3a239c4be8485eef16"},"schema_version":"1.0"},"canonical_sha256":"36979f5423e803fd776d8f5e3efd63d67961845a7b7a0ced67fa568b3e581770","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:06.865272Z","signature_b64":"ld6Qxq0wm3ije8f3T6Vo5H4Xt2iyYXqK+qXy7T5LucPgi9Z9oKMGMIlsZkqBpl9cpDSt9VSalGB76ZlI3FotBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36979f5423e803fd776d8f5e3efd63d67961845a7b7a0ced67fa568b3e581770","last_reissued_at":"2026-06-02T02:04:06.864760Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:06.864760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.22881","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uMeXUjRsBp6ZFUOLljk3QLS42Xl0vXQl+o2PTs1XhBK73vG91g09TkFRn9ySq6zF3cMTEW6ZnadQ4doBWYx9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T16:55:30.769873Z"},"content_sha256":"7844511debe3fb058bb580750bbf8819ca88844de6eabecfd55d9d5df2dd9d52","schema_version":"1.0","event_id":"sha256:7844511debe3fb058bb580750bbf8819ca88844de6eabecfd55d9d5df2dd9d52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G2LZ6VBD5AB7253NR5PD57LD2Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP-like Model as a Foundational Density Ratio Estimator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fumiya Uchiyama, Hirokatsu Kataoka, Masahiro Suzuki, Rintaro Yanagi, Shohei Taniguchi, Shota Takashiro, Yusuke Iwasawa, Yutaka Matsuo","submitted_at":"2025-06-28T13:36:44Z","abstract_excerpt":"Density ratio estimation is a core concept in statistical machine learning because it provides a unified mechanism for tasks such as importance weighting, divergence estimation, and likelihood-free inference, but its potential in vision and language models has not been fully explored. Modern vision-language encoders such as CLIP and SigLIP are trained with contrastive objectives that implicitly optimize log density ratios between joint and marginal image-text distributions, which implicitly learn similarity scores proportional to log density ratios. However, prior work has largely focused on t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22881","kind":"arxiv","version":3},"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/2506.22881/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":"2026-06-02T02:04:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LBdNEqW3FTaikLypRivqMfmRTIizUYGmtygqf+pi081VshLVDws1uXUUpttjkZGg+NtLJSMoixb9MnMblxbaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T16:55:30.770252Z"},"content_sha256":"6c12ae828ea55d0412ea32bfb04c701f4f59e580fedab4c8ffe2ffd537bb7826","schema_version":"1.0","event_id":"sha256:6c12ae828ea55d0412ea32bfb04c701f4f59e580fedab4c8ffe2ffd537bb7826"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G2LZ6VBD5AB7253NR5PD57LD2Z/bundle.json","state_url":"https://pith.science/pith/G2LZ6VBD5AB7253NR5PD57LD2Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G2LZ6VBD5AB7253NR5PD57LD2Z/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":"2026-06-30T16:55:30Z","links":{"resolver":"https://pith.science/pith/G2LZ6VBD5AB7253NR5PD57LD2Z","bundle":"https://pith.science/pith/G2LZ6VBD5AB7253NR5PD57LD2Z/bundle.json","state":"https://pith.science/pith/G2LZ6VBD5AB7253NR5PD57LD2Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G2LZ6VBD5AB7253NR5PD57LD2Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G2LZ6VBD5AB7253NR5PD57LD2Z","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":"c5df4ed14fd84f8b9434508767e9f1329d50b1cbeac4fb3a239c4be8485eef16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T13:36:44Z","title_canon_sha256":"40a8f7860e70a8e241e20ba8e6f08a778df1c4e9498dccadc4b3b825077c838e"},"schema_version":"1.0","source":{"id":"2506.22881","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22881","created_at":"2026-06-02T02:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22881v3","created_at":"2026-06-02T02:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22881","created_at":"2026-06-02T02:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"G2LZ6VBD5AB7","created_at":"2026-06-02T02:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"G2LZ6VBD5AB7253N","created_at":"2026-06-02T02:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"G2LZ6VBD","created_at":"2026-06-02T02:04:06Z"}],"graph_snapshots":[{"event_id":"sha256:6c12ae828ea55d0412ea32bfb04c701f4f59e580fedab4c8ffe2ffd537bb7826","target":"graph","created_at":"2026-06-02T02:04:06Z","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/2506.22881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Density ratio estimation is a core concept in statistical machine learning because it provides a unified mechanism for tasks such as importance weighting, divergence estimation, and likelihood-free inference, but its potential in vision and language models has not been fully explored. Modern vision-language encoders such as CLIP and SigLIP are trained with contrastive objectives that implicitly optimize log density ratios between joint and marginal image-text distributions, which implicitly learn similarity scores proportional to log density ratios. However, prior work has largely focused on t","authors_text":"Fumiya Uchiyama, Hirokatsu Kataoka, Masahiro Suzuki, Rintaro Yanagi, Shohei Taniguchi, Shota Takashiro, Yusuke Iwasawa, Yutaka Matsuo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T13:36:44Z","title":"CLIP-like Model as a Foundational Density Ratio Estimator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22881","kind":"arxiv","version":3},"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":"sha256:7844511debe3fb058bb580750bbf8819ca88844de6eabecfd55d9d5df2dd9d52","target":"record","created_at":"2026-06-02T02:04:06Z","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":"c5df4ed14fd84f8b9434508767e9f1329d50b1cbeac4fb3a239c4be8485eef16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T13:36:44Z","title_canon_sha256":"40a8f7860e70a8e241e20ba8e6f08a778df1c4e9498dccadc4b3b825077c838e"},"schema_version":"1.0","source":{"id":"2506.22881","kind":"arxiv","version":3}},"canonical_sha256":"36979f5423e803fd776d8f5e3efd63d67961845a7b7a0ced67fa568b3e581770","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36979f5423e803fd776d8f5e3efd63d67961845a7b7a0ced67fa568b3e581770","first_computed_at":"2026-06-02T02:04:06.864760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:06.864760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ld6Qxq0wm3ije8f3T6Vo5H4Xt2iyYXqK+qXy7T5LucPgi9Z9oKMGMIlsZkqBpl9cpDSt9VSalGB76ZlI3FotBw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:06.865272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22881","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7844511debe3fb058bb580750bbf8819ca88844de6eabecfd55d9d5df2dd9d52","sha256:6c12ae828ea55d0412ea32bfb04c701f4f59e580fedab4c8ffe2ffd537bb7826"],"state_sha256":"c75832f54adc19a0132faa0a71bbc013ec180e2b29ec46e12151b291b302b827"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uCHawcnm/31RJ/FV17owm1k8Ulb9LtBNAXctyuPWnJMZ048apgAm/MOBB4yHflbHDxP+8fdKEOxiO3fOUk8VAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T16:55:30.773079Z","bundle_sha256":"aa193de64bf7f91e864a0bfc04dc6ec0e74f0b66079db95cb8ed5e405c5d726d"}}