{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5XXCWAPY3KFPA4734NAZP3X25U","short_pith_number":"pith:5XXCWAPY","canonical_record":{"source":{"id":"2310.14581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T05:40:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6bd7467a4dde20a897ef8d5e59c8e19ac057354e03e424b2943a7b1e529b70bd","abstract_canon_sha256":"9553139d0b03ead4acd9e565960323d6317bd29ff73412d5d13580148e4f5b9c"},"schema_version":"1.0"},"canonical_sha256":"edee2b01f8da8af073fbe34197eefaed1e69f5073456b9f4b4cda75e33392c0d","source":{"kind":"arxiv","id":"2310.14581","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14581","created_at":"2026-07-05T07:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14581v1","created_at":"2026-07-05T07:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14581","created_at":"2026-07-05T07:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"5XXCWAPY3KFP","created_at":"2026-07-05T07:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"5XXCWAPY3KFPA473","created_at":"2026-07-05T07:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"5XXCWAPY","created_at":"2026-07-05T07:03:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5XXCWAPY3KFPA4734NAZP3X25U","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T05:40:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6bd7467a4dde20a897ef8d5e59c8e19ac057354e03e424b2943a7b1e529b70bd","abstract_canon_sha256":"9553139d0b03ead4acd9e565960323d6317bd29ff73412d5d13580148e4f5b9c"},"schema_version":"1.0"},"canonical_sha256":"edee2b01f8da8af073fbe34197eefaed1e69f5073456b9f4b4cda75e33392c0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:46.754165Z","signature_b64":"PeLwC1NTDdxKHrKehFkHrq445cDFZ/THsh8pEnEr74FXPvnlDU3vXk/wB0ka5gBvnDFpjY3ZqA+SSaV+U2KbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edee2b01f8da8af073fbe34197eefaed1e69f5073456b9f4b4cda75e33392c0d","last_reissued_at":"2026-07-05T07:03:46.753696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:46.753696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14581","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":"2026-07-05T07:03:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UkVlUDadcDgdbh4D41ZQySE9XsFrk+3VzwowQcDXtf5MyVKpN+pNCJ+MK4pbZLhLo1p7L98tCnPnqiRa3ENPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:35:14.518166Z"},"content_sha256":"d5fa85dd40bbdd12b6a7e1555efb14954ffda29ec7639d654825f8ff7930f6e7","schema_version":"1.0","event_id":"sha256:d5fa85dd40bbdd12b6a7e1555efb14954ffda29ec7639d654825f8ff7930f6e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5XXCWAPY3KFPA4734NAZP3X25U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Image-Text Similarity and Caption Modification for the DataComp Challenge: Filtering Track and BYOD Track","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hirokatsu Kataoka, Masayoshi Kondo, Mikihiro Tanaka, Peifei Zhu, Shuhei Yokoo, Yuchi Ishikawa","submitted_at":"2023-10-23T05:40:43Z","abstract_excerpt":"Large web crawl datasets have already played an important role in learning multimodal features with high generalization capabilities. However, there are still very limited studies investigating the details or improvements of data design. Recently, a DataComp challenge has been designed to propose the best training data with the fixed models. This paper presents our solution to both filtering track and BYOD track of the DataComp challenge. Our solution adopts large multimodal models CLIP and BLIP-2 to filter and modify web crawl data, and utilize external datasets along with a bag of tricks to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14581","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/2310.14581/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":"2026-07-05T07:03:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JZa5dIx2+mT23bFyHjU8BigVq0tvvj8cRfESoaDKQRcuA5hII+4viMgqLNbpe14dPfBKuzLuQoKxbvF98ZhuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:35:14.518720Z"},"content_sha256":"2a7a14b1450ebde6d1bdccec1666155e895a23e68ff6d740764c935246d89854","schema_version":"1.0","event_id":"sha256:2a7a14b1450ebde6d1bdccec1666155e895a23e68ff6d740764c935246d89854"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XXCWAPY3KFPA4734NAZP3X25U/bundle.json","state_url":"https://pith.science/pith/5XXCWAPY3KFPA4734NAZP3X25U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XXCWAPY3KFPA4734NAZP3X25U/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":"2026-08-10T19:35:14Z","links":{"resolver":"https://pith.science/pith/5XXCWAPY3KFPA4734NAZP3X25U","bundle":"https://pith.science/pith/5XXCWAPY3KFPA4734NAZP3X25U/bundle.json","state":"https://pith.science/pith/5XXCWAPY3KFPA4734NAZP3X25U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XXCWAPY3KFPA4734NAZP3X25U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5XXCWAPY3KFPA4734NAZP3X25U","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":"9553139d0b03ead4acd9e565960323d6317bd29ff73412d5d13580148e4f5b9c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T05:40:43Z","title_canon_sha256":"6bd7467a4dde20a897ef8d5e59c8e19ac057354e03e424b2943a7b1e529b70bd"},"schema_version":"1.0","source":{"id":"2310.14581","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14581","created_at":"2026-07-05T07:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14581v1","created_at":"2026-07-05T07:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14581","created_at":"2026-07-05T07:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"5XXCWAPY3KFP","created_at":"2026-07-05T07:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"5XXCWAPY3KFPA473","created_at":"2026-07-05T07:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"5XXCWAPY","created_at":"2026-07-05T07:03:46Z"}],"graph_snapshots":[{"event_id":"sha256:2a7a14b1450ebde6d1bdccec1666155e895a23e68ff6d740764c935246d89854","target":"graph","created_at":"2026-07-05T07:03:46Z","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/2310.14581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large web crawl datasets have already played an important role in learning multimodal features with high generalization capabilities. However, there are still very limited studies investigating the details or improvements of data design. Recently, a DataComp challenge has been designed to propose the best training data with the fixed models. This paper presents our solution to both filtering track and BYOD track of the DataComp challenge. Our solution adopts large multimodal models CLIP and BLIP-2 to filter and modify web crawl data, and utilize external datasets along with a bag of tricks to ","authors_text":"Hirokatsu Kataoka, Masayoshi Kondo, Mikihiro Tanaka, Peifei Zhu, Shuhei Yokoo, Yuchi Ishikawa","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T05:40:43Z","title":"Leveraging Image-Text Similarity and Caption Modification for the DataComp Challenge: Filtering Track and BYOD Track"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14581","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:d5fa85dd40bbdd12b6a7e1555efb14954ffda29ec7639d654825f8ff7930f6e7","target":"record","created_at":"2026-07-05T07:03:46Z","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":"9553139d0b03ead4acd9e565960323d6317bd29ff73412d5d13580148e4f5b9c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T05:40:43Z","title_canon_sha256":"6bd7467a4dde20a897ef8d5e59c8e19ac057354e03e424b2943a7b1e529b70bd"},"schema_version":"1.0","source":{"id":"2310.14581","kind":"arxiv","version":1}},"canonical_sha256":"edee2b01f8da8af073fbe34197eefaed1e69f5073456b9f4b4cda75e33392c0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edee2b01f8da8af073fbe34197eefaed1e69f5073456b9f4b4cda75e33392c0d","first_computed_at":"2026-07-05T07:03:46.753696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:46.753696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PeLwC1NTDdxKHrKehFkHrq445cDFZ/THsh8pEnEr74FXPvnlDU3vXk/wB0ka5gBvnDFpjY3ZqA+SSaV+U2KbDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:46.754165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14581","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5fa85dd40bbdd12b6a7e1555efb14954ffda29ec7639d654825f8ff7930f6e7","sha256:2a7a14b1450ebde6d1bdccec1666155e895a23e68ff6d740764c935246d89854"],"state_sha256":"25848f88d8843b270ed7675af1833e7fa56cee6a981bb13f77bc0fab18620faa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tk0ks1Y9L2g/IbzWluCp7jwZZ9qVqGJWGR/J4LMx3153o9Ck3QygCx8xNWlr1NkMK79cbVlfDn6vy2TQGmQnDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:35:14.522994Z","bundle_sha256":"d9726249ec0bf8cd772062be15e2886d6c668116aa9bca0caa0046e8b25728bb"}}