{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EP75ETDP2H6WPBNMZFU5ZNVX2Y","short_pith_number":"pith:EP75ETDP","canonical_record":{"source":{"id":"2404.19228","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-30T03:15:04Z","cross_cats_sorted":[],"title_canon_sha256":"441e222d7b289921908749233c5e5383a0011bb6cd92d2793083f06b3054c3d2","abstract_canon_sha256":"451a2b042b91f0a5391007f97e6be688b91a016d75af558fea6ddfa92b721df5"},"schema_version":"1.0"},"canonical_sha256":"23ffd24c6fd1fd6785acc969dcb6b7d6175172769984bd5c021d7a8af565d3af","source":{"kind":"arxiv","id":"2404.19228","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.19228","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.19228v3","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19228","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"EP75ETDP2H6W","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_16","alias_value":"EP75ETDP2H6WPBNM","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_8","alias_value":"EP75ETDP","created_at":"2026-07-05T10:21:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EP75ETDP2H6WPBNMZFU5ZNVX2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2404.19228","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-30T03:15:04Z","cross_cats_sorted":[],"title_canon_sha256":"441e222d7b289921908749233c5e5383a0011bb6cd92d2793083f06b3054c3d2","abstract_canon_sha256":"451a2b042b91f0a5391007f97e6be688b91a016d75af558fea6ddfa92b721df5"},"schema_version":"1.0"},"canonical_sha256":"23ffd24c6fd1fd6785acc969dcb6b7d6175172769984bd5c021d7a8af565d3af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:59.318220Z","signature_b64":"hEmvXuElcI3F2oV4eDW/eGekGTRkb7L6ScyAQ5DOwmAwwVx/UXQ5rvDX6FYPeQCqXU/omolTAt18Jle7XKGmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23ffd24c6fd1fd6785acc969dcb6b7d6175172769984bd5c021d7a8af565d3af","last_reissued_at":"2026-07-05T10:21:59.317568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:59.317568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.19228","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":"2026-07-05T10:21:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FQk/kxpiohNUtKjUyJOojScLUdDdvpX26reQhex0NoEbN8s5VBM83LqXtF6rF/XglNuwIma+dGPWDrdVAYp9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:53:56.966697Z"},"content_sha256":"f68e376113b6d733bd1bc3dbdce95383d8c41bdbb8e07981a48394a516d9bc5c","schema_version":"1.0","event_id":"sha256:f68e376113b6d733bd1bc3dbdce95383d8c41bdbb8e07981a48394a516d9bc5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EP75ETDP2H6WPBNMZFU5ZNVX2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Naoki Murata, Taiji Suzuki, Toshimitsu Uesaka, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2024-04-30T03:15:04Z","abstract_excerpt":"In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity structure of a huge amount of instances in the real world. For richer classes of the similarity, we propose the use of weighted point sets, namely, sets of pairs of weight and vector, as representations of instances. In this work, we theoretically show the benefit of our proposed method through a new understanding of the contrastive loss of CLIP, which we call sym"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19228","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/2404.19228/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":"2026-07-05T10:21:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HxbocF4QewYW/9DOOHQBI5dkviCF1dV+tJGh1xxdL2gng7vmhWYGFUf0ciY2KjuwsdaZSTKifcYUtqfRLliXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:53:56.967350Z"},"content_sha256":"b111fdefed17b539de5e3f05d1608c2dd1403212c0d2ff65f4598b06266eb8fa","schema_version":"1.0","event_id":"sha256:b111fdefed17b539de5e3f05d1608c2dd1403212c0d2ff65f4598b06266eb8fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EP75ETDP2H6WPBNMZFU5ZNVX2Y/bundle.json","state_url":"https://pith.science/pith/EP75ETDP2H6WPBNMZFU5ZNVX2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EP75ETDP2H6WPBNMZFU5ZNVX2Y/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":"2026-07-07T03:53:56Z","links":{"resolver":"https://pith.science/pith/EP75ETDP2H6WPBNMZFU5ZNVX2Y","bundle":"https://pith.science/pith/EP75ETDP2H6WPBNMZFU5ZNVX2Y/bundle.json","state":"https://pith.science/pith/EP75ETDP2H6WPBNMZFU5ZNVX2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EP75ETDP2H6WPBNMZFU5ZNVX2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EP75ETDP2H6WPBNMZFU5ZNVX2Y","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":"451a2b042b91f0a5391007f97e6be688b91a016d75af558fea6ddfa92b721df5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-30T03:15:04Z","title_canon_sha256":"441e222d7b289921908749233c5e5383a0011bb6cd92d2793083f06b3054c3d2"},"schema_version":"1.0","source":{"id":"2404.19228","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.19228","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.19228v3","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19228","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"EP75ETDP2H6W","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_16","alias_value":"EP75ETDP2H6WPBNM","created_at":"2026-07-05T10:21:59Z"},{"alias_kind":"pith_short_8","alias_value":"EP75ETDP","created_at":"2026-07-05T10:21:59Z"}],"graph_snapshots":[{"event_id":"sha256:b111fdefed17b539de5e3f05d1608c2dd1403212c0d2ff65f4598b06266eb8fa","target":"graph","created_at":"2026-07-05T10:21:59Z","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/2404.19228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity structure of a huge amount of instances in the real world. For richer classes of the similarity, we propose the use of weighted point sets, namely, sets of pairs of weight and vector, as representations of instances. In this work, we theoretically show the benefit of our proposed method through a new understanding of the contrastive loss of CLIP, which we call sym","authors_text":"Chieh-Hsin Lai, Naoki Murata, Taiji Suzuki, Toshimitsu Uesaka, Yuhta Takida, Yuki Mitsufuji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-30T03:15:04Z","title":"Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19228","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:f68e376113b6d733bd1bc3dbdce95383d8c41bdbb8e07981a48394a516d9bc5c","target":"record","created_at":"2026-07-05T10:21:59Z","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":"451a2b042b91f0a5391007f97e6be688b91a016d75af558fea6ddfa92b721df5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-30T03:15:04Z","title_canon_sha256":"441e222d7b289921908749233c5e5383a0011bb6cd92d2793083f06b3054c3d2"},"schema_version":"1.0","source":{"id":"2404.19228","kind":"arxiv","version":3}},"canonical_sha256":"23ffd24c6fd1fd6785acc969dcb6b7d6175172769984bd5c021d7a8af565d3af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23ffd24c6fd1fd6785acc969dcb6b7d6175172769984bd5c021d7a8af565d3af","first_computed_at":"2026-07-05T10:21:59.317568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:59.317568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hEmvXuElcI3F2oV4eDW/eGekGTRkb7L6ScyAQ5DOwmAwwVx/UXQ5rvDX6FYPeQCqXU/omolTAt18Jle7XKGmAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:59.318220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.19228","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f68e376113b6d733bd1bc3dbdce95383d8c41bdbb8e07981a48394a516d9bc5c","sha256:b111fdefed17b539de5e3f05d1608c2dd1403212c0d2ff65f4598b06266eb8fa"],"state_sha256":"b5a8881dbbe7895dadd8b98c0cd63e78b489dd60937da011baa165b5b64d40fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VyTzdGoAyz7eC/YOlxSIk+e7KglZiKcuI22CN6yekG1NrxVQ7klFHRoxYI/ZomcA0JP9Slf4CXF4jIpIlZDNCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:53:56.970181Z","bundle_sha256":"a32b647bdd446075aba599483203a819a6a35060c712bc76dde4702bdc029d0b"}}