{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W4HAVUBBRME47B3Z6CMYH6D5R5","short_pith_number":"pith:W4HAVUBB","canonical_record":{"source":{"id":"2404.17507","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T16:19:55Z","cross_cats_sorted":[],"title_canon_sha256":"96d640899ea25ce7bdebe2351fed24272c925ecd75c1cd040eee235c24e3eccb","abstract_canon_sha256":"578e61440e03d0fec326e3ec0b54feec79db115270c73f1f39e0264ed3ea3eb7"},"schema_version":"1.0"},"canonical_sha256":"b70e0ad0218b09cf8779f09983f87d8f6622e7db1ca9958c09ba26582b2b91fe","source":{"kind":"arxiv","id":"2404.17507","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17507","created_at":"2026-07-05T08:44:37Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17507v2","created_at":"2026-07-05T08:44:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17507","created_at":"2026-07-05T08:44:37Z"},{"alias_kind":"pith_short_12","alias_value":"W4HAVUBBRME4","created_at":"2026-07-05T08:44:37Z"},{"alias_kind":"pith_short_16","alias_value":"W4HAVUBBRME47B3Z","created_at":"2026-07-05T08:44:37Z"},{"alias_kind":"pith_short_8","alias_value":"W4HAVUBB","created_at":"2026-07-05T08:44:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W4HAVUBBRME47B3Z6CMYH6D5R5","target":"record","payload":{"canonical_record":{"source":{"id":"2404.17507","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T16:19:55Z","cross_cats_sorted":[],"title_canon_sha256":"96d640899ea25ce7bdebe2351fed24272c925ecd75c1cd040eee235c24e3eccb","abstract_canon_sha256":"578e61440e03d0fec326e3ec0b54feec79db115270c73f1f39e0264ed3ea3eb7"},"schema_version":"1.0"},"canonical_sha256":"b70e0ad0218b09cf8779f09983f87d8f6622e7db1ca9958c09ba26582b2b91fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:37.851359Z","signature_b64":"8USTjTnD4yjOaXF1XzckrLkyt0jlPoQd1TfhHGDfeb7PqhqacIQyvxenJMAlVgG4pzyi6mYcKVt3NVSP70h5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b70e0ad0218b09cf8779f09983f87d8f6622e7db1ca9958c09ba26582b2b91fe","last_reissued_at":"2026-07-05T08:44:37.850891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:37.850891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.17507","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":"2026-07-05T08:44:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a6V5mdeTp/pxCPb5dM4cBAcvdglX54De4tr2FqjqvuSxQQAr3hVvoxn6EZYGeiDEyfrNm5nyMYhj951GXHp3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:51:14.163097Z"},"content_sha256":"033008a46e4a2586549642547b88efa2bf7c9f97a8467c5d26e0b812ab64c0d1","schema_version":"1.0","event_id":"sha256:033008a46e4a2586549642547b88efa2bf7c9f97a8467c5d26e0b812ab64c0d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W4HAVUBBRME47B3Z6CMYH6D5R5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongyoon Han, Sangdoo Yun, Sanghyuk Chun, Taekyung Kim, Wonjae Kim","submitted_at":"2024-04-26T16:19:55Z","abstract_excerpt":"In an era where the volume of data drives the effectiveness of self-supervised learning, the specificity and clarity of data semantics play a crucial role in model training. Addressing this, we introduce HYPerbolic Entailment filtering (HYPE), a novel methodology designed to meticulously extract modality-wise meaningful and well-aligned data from extensive, noisy image-text pair datasets. Our approach leverages hyperbolic embeddings and the concept of entailment cones to evaluate and filter out samples with meaningless or underspecified semantics, focusing on enhancing the specificity of each "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17507","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/2404.17507/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":"2026-07-05T08:44:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jd4xiqX0EfDPnuScJ4k76hTckC6otix/5g7X5WLtOU5lwFFm9Iu1oqNyoBsafMxYTzxgg2A+cpdm9/FuOETwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:51:14.163613Z"},"content_sha256":"08871b5a7facc3d3c4472c277a3bf2bed82e27c763f4dc4fa303dcadfb783adb","schema_version":"1.0","event_id":"sha256:08871b5a7facc3d3c4472c277a3bf2bed82e27c763f4dc4fa303dcadfb783adb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W4HAVUBBRME47B3Z6CMYH6D5R5/bundle.json","state_url":"https://pith.science/pith/W4HAVUBBRME47B3Z6CMYH6D5R5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W4HAVUBBRME47B3Z6CMYH6D5R5/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":"2026-08-06T17:51:14Z","links":{"resolver":"https://pith.science/pith/W4HAVUBBRME47B3Z6CMYH6D5R5","bundle":"https://pith.science/pith/W4HAVUBBRME47B3Z6CMYH6D5R5/bundle.json","state":"https://pith.science/pith/W4HAVUBBRME47B3Z6CMYH6D5R5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W4HAVUBBRME47B3Z6CMYH6D5R5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W4HAVUBBRME47B3Z6CMYH6D5R5","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":"578e61440e03d0fec326e3ec0b54feec79db115270c73f1f39e0264ed3ea3eb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T16:19:55Z","title_canon_sha256":"96d640899ea25ce7bdebe2351fed24272c925ecd75c1cd040eee235c24e3eccb"},"schema_version":"1.0","source":{"id":"2404.17507","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17507","created_at":"2026-07-05T08:44:37Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17507v2","created_at":"2026-07-05T08:44:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17507","created_at":"2026-07-05T08:44:37Z"},{"alias_kind":"pith_short_12","alias_value":"W4HAVUBBRME4","created_at":"2026-07-05T08:44:37Z"},{"alias_kind":"pith_short_16","alias_value":"W4HAVUBBRME47B3Z","created_at":"2026-07-05T08:44:37Z"},{"alias_kind":"pith_short_8","alias_value":"W4HAVUBB","created_at":"2026-07-05T08:44:37Z"}],"graph_snapshots":[{"event_id":"sha256:08871b5a7facc3d3c4472c277a3bf2bed82e27c763f4dc4fa303dcadfb783adb","target":"graph","created_at":"2026-07-05T08:44:37Z","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/2404.17507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In an era where the volume of data drives the effectiveness of self-supervised learning, the specificity and clarity of data semantics play a crucial role in model training. Addressing this, we introduce HYPerbolic Entailment filtering (HYPE), a novel methodology designed to meticulously extract modality-wise meaningful and well-aligned data from extensive, noisy image-text pair datasets. Our approach leverages hyperbolic embeddings and the concept of entailment cones to evaluate and filter out samples with meaningless or underspecified semantics, focusing on enhancing the specificity of each ","authors_text":"Dongyoon Han, Sangdoo Yun, Sanghyuk Chun, Taekyung Kim, Wonjae Kim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T16:19:55Z","title":"HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17507","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":"sha256:033008a46e4a2586549642547b88efa2bf7c9f97a8467c5d26e0b812ab64c0d1","target":"record","created_at":"2026-07-05T08:44:37Z","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":"578e61440e03d0fec326e3ec0b54feec79db115270c73f1f39e0264ed3ea3eb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T16:19:55Z","title_canon_sha256":"96d640899ea25ce7bdebe2351fed24272c925ecd75c1cd040eee235c24e3eccb"},"schema_version":"1.0","source":{"id":"2404.17507","kind":"arxiv","version":2}},"canonical_sha256":"b70e0ad0218b09cf8779f09983f87d8f6622e7db1ca9958c09ba26582b2b91fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b70e0ad0218b09cf8779f09983f87d8f6622e7db1ca9958c09ba26582b2b91fe","first_computed_at":"2026-07-05T08:44:37.850891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:37.850891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8USTjTnD4yjOaXF1XzckrLkyt0jlPoQd1TfhHGDfeb7PqhqacIQyvxenJMAlVgG4pzyi6mYcKVt3NVSP70h5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:37.851359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.17507","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:033008a46e4a2586549642547b88efa2bf7c9f97a8467c5d26e0b812ab64c0d1","sha256:08871b5a7facc3d3c4472c277a3bf2bed82e27c763f4dc4fa303dcadfb783adb"],"state_sha256":"427b03db9a5b340f1ec81be37934aad14e23cc4d52a9e1b96f964044efd46714"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"59dG5Dz3gJfnC8PYEqVnJek6uozOkERVYNAlYflLT+f+M//TeRkzPWQ+jgS4tvn+aH4zZCq6/oxEzJCgHIIiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:51:14.169557Z","bundle_sha256":"9a50fd2f6eb2fa247d5ac4cf602cc1ca14d55475bce1e99e89d304fad52e43ef"}}