{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XX2HUSAAD5BPTH2SVPZTNRGKNV","short_pith_number":"pith:XX2HUSAA","canonical_record":{"source":{"id":"2507.10019","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2025-07-14T07:56:29Z","cross_cats_sorted":["cs.DB","stat.ML"],"title_canon_sha256":"22780eb85efd5939c591a44be090e02111be78017ca0c8d737bc29b54e2f2413","abstract_canon_sha256":"1d3b106c1b67fc598bf4863a5178b15adc07b022131650a5d9450e4139be7af0"},"schema_version":"1.0"},"canonical_sha256":"bdf47a48001f42f99f52abf336c4ca6d727293d862e55298811605b229de05f4","source":{"kind":"arxiv","id":"2507.10019","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10019","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10019v3","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10019","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"XX2HUSAAD5BP","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"XX2HUSAAD5BPTH2S","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"XX2HUSAA","created_at":"2026-07-05T11:40:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XX2HUSAAD5BPTH2SVPZTNRGKNV","target":"record","payload":{"canonical_record":{"source":{"id":"2507.10019","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2025-07-14T07:56:29Z","cross_cats_sorted":["cs.DB","stat.ML"],"title_canon_sha256":"22780eb85efd5939c591a44be090e02111be78017ca0c8d737bc29b54e2f2413","abstract_canon_sha256":"1d3b106c1b67fc598bf4863a5178b15adc07b022131650a5d9450e4139be7af0"},"schema_version":"1.0"},"canonical_sha256":"bdf47a48001f42f99f52abf336c4ca6d727293d862e55298811605b229de05f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:01.121282Z","signature_b64":"uacfqOOCV+Uu1UoTpTn77DAareT8eNwgfzWdM0qfa3Q1I8WOrq+czcc3GVdwZqZgdyx/pIxJANWa1htUDH38Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdf47a48001f42f99f52abf336c4ca6d727293d862e55298811605b229de05f4","last_reissued_at":"2026-07-05T11:40:01.120774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:01.120774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.10019","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":"2026-07-05T11:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rRQvmPhgKKyToe2CcPOAYhi0KLGcRm9dvieU8NdbbKptakynuQ1jUfZ9ntSPqK93jn1F74B85ezc6fMAH09cDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:27:29.018795Z"},"content_sha256":"292192b62411b8271689f9201ffb64ec281a70844600994496562d6611a00874","schema_version":"1.0","event_id":"sha256:292192b62411b8271689f9201ffb64ec281a70844600994496562d6611a00874"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XX2HUSAAD5BPTH2SVPZTNRGKNV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sampling-Based Estimation of Jaccard Containment and Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","stat.ML"],"primary_cat":"stat.CO","authors_text":"Pranav Joshi","submitted_at":"2025-07-14T07:56:29Z","abstract_excerpt":"This paper addresses the problem of estimating the containment and similarity between two sets using only random samples from each set, without relying on sketches of full sets. The study introduces a binomial model for predicting the overlap between samples, demonstrating that it is both accurate and practical when sample sizes are small compared to the original sets. The paper compares this model to previous approaches and shows that it provides better estimates under the considered conditions. It also analyzes the statistical properties of the estimator, including error bounds and sample si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10019","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/2507.10019/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":"2026-07-05T11:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nmFeLTjCw9g12yLGrrGMM+dwPfP1wUs6PRE/Eocal3UKEcGfj9uDXJTuFse3aiKqi7zEUrZiflBGa2NOjVViCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:27:29.019308Z"},"content_sha256":"dadc4e9420e14af0fe0d2790d0eee13c79b8674b9a4bd95d921abfb1900c2c8c","schema_version":"1.0","event_id":"sha256:dadc4e9420e14af0fe0d2790d0eee13c79b8674b9a4bd95d921abfb1900c2c8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XX2HUSAAD5BPTH2SVPZTNRGKNV/bundle.json","state_url":"https://pith.science/pith/XX2HUSAAD5BPTH2SVPZTNRGKNV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XX2HUSAAD5BPTH2SVPZTNRGKNV/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":"2026-08-16T22:27:29Z","links":{"resolver":"https://pith.science/pith/XX2HUSAAD5BPTH2SVPZTNRGKNV","bundle":"https://pith.science/pith/XX2HUSAAD5BPTH2SVPZTNRGKNV/bundle.json","state":"https://pith.science/pith/XX2HUSAAD5BPTH2SVPZTNRGKNV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XX2HUSAAD5BPTH2SVPZTNRGKNV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XX2HUSAAD5BPTH2SVPZTNRGKNV","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":"1d3b106c1b67fc598bf4863a5178b15adc07b022131650a5d9450e4139be7af0","cross_cats_sorted":["cs.DB","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2025-07-14T07:56:29Z","title_canon_sha256":"22780eb85efd5939c591a44be090e02111be78017ca0c8d737bc29b54e2f2413"},"schema_version":"1.0","source":{"id":"2507.10019","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10019","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10019v3","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10019","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"XX2HUSAAD5BP","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"XX2HUSAAD5BPTH2S","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"XX2HUSAA","created_at":"2026-07-05T11:40:01Z"}],"graph_snapshots":[{"event_id":"sha256:dadc4e9420e14af0fe0d2790d0eee13c79b8674b9a4bd95d921abfb1900c2c8c","target":"graph","created_at":"2026-07-05T11:40:01Z","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/2507.10019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the problem of estimating the containment and similarity between two sets using only random samples from each set, without relying on sketches of full sets. The study introduces a binomial model for predicting the overlap between samples, demonstrating that it is both accurate and practical when sample sizes are small compared to the original sets. The paper compares this model to previous approaches and shows that it provides better estimates under the considered conditions. It also analyzes the statistical properties of the estimator, including error bounds and sample si","authors_text":"Pranav Joshi","cross_cats":["cs.DB","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2025-07-14T07:56:29Z","title":"Sampling-Based Estimation of Jaccard Containment and Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10019","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":"sha256:292192b62411b8271689f9201ffb64ec281a70844600994496562d6611a00874","target":"record","created_at":"2026-07-05T11:40:01Z","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":"1d3b106c1b67fc598bf4863a5178b15adc07b022131650a5d9450e4139be7af0","cross_cats_sorted":["cs.DB","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2025-07-14T07:56:29Z","title_canon_sha256":"22780eb85efd5939c591a44be090e02111be78017ca0c8d737bc29b54e2f2413"},"schema_version":"1.0","source":{"id":"2507.10019","kind":"arxiv","version":3}},"canonical_sha256":"bdf47a48001f42f99f52abf336c4ca6d727293d862e55298811605b229de05f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdf47a48001f42f99f52abf336c4ca6d727293d862e55298811605b229de05f4","first_computed_at":"2026-07-05T11:40:01.120774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:01.120774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uacfqOOCV+Uu1UoTpTn77DAareT8eNwgfzWdM0qfa3Q1I8WOrq+czcc3GVdwZqZgdyx/pIxJANWa1htUDH38Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:01.121282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10019","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:292192b62411b8271689f9201ffb64ec281a70844600994496562d6611a00874","sha256:dadc4e9420e14af0fe0d2790d0eee13c79b8674b9a4bd95d921abfb1900c2c8c"],"state_sha256":"db47560d653f150795bdb11d865c694d65c9ab686e1f2f3e0de70ce480362d2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PgiRSCI2dlDEC4lzicGfNycQ2EsLiUGnSBzkO5p9BR8OcxyE7DYhpLqGm4wLyIZ0UchwpkzAviMIu8pClhR0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:27:29.024351Z","bundle_sha256":"5f9a14d932dfa8449d8efd38421cabceaa493220e27cf73faf2ad862224ea468"}}