{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RS4QCIRVRRGII5IWBMAIUJGAF4","short_pith_number":"pith:RS4QCIRV","canonical_record":{"source":{"id":"2304.10572","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-04-20T18:03:21Z","cross_cats_sorted":[],"title_canon_sha256":"439ab69cceb2743f86d0ba8e24a646846db918ad6450e170fa10cbf607eea2ed","abstract_canon_sha256":"966e0f3a624458060337f5caa7e1f8335e39098ccff10e2e43087d4b43d48a04"},"schema_version":"1.0"},"canonical_sha256":"8cb90122358c4c8475160b008a24c02f35c67c59fef7e3657101ec9f4894792d","source":{"kind":"arxiv","id":"2304.10572","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.10572","created_at":"2026-07-05T06:03:00Z"},{"alias_kind":"arxiv_version","alias_value":"2304.10572v1","created_at":"2026-07-05T06:03:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10572","created_at":"2026-07-05T06:03:00Z"},{"alias_kind":"pith_short_12","alias_value":"RS4QCIRVRRGI","created_at":"2026-07-05T06:03:00Z"},{"alias_kind":"pith_short_16","alias_value":"RS4QCIRVRRGII5IW","created_at":"2026-07-05T06:03:00Z"},{"alias_kind":"pith_short_8","alias_value":"RS4QCIRV","created_at":"2026-07-05T06:03:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RS4QCIRVRRGII5IWBMAIUJGAF4","target":"record","payload":{"canonical_record":{"source":{"id":"2304.10572","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-04-20T18:03:21Z","cross_cats_sorted":[],"title_canon_sha256":"439ab69cceb2743f86d0ba8e24a646846db918ad6450e170fa10cbf607eea2ed","abstract_canon_sha256":"966e0f3a624458060337f5caa7e1f8335e39098ccff10e2e43087d4b43d48a04"},"schema_version":"1.0"},"canonical_sha256":"8cb90122358c4c8475160b008a24c02f35c67c59fef7e3657101ec9f4894792d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:00.189580Z","signature_b64":"HvEn14VxEiOqb1dws8TJ6VxcL3C6prDb4zSB3MnlFknL5nKAKRVAFI7yNaZ05s4uOhNC3QT8Elm6skCvSlhaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cb90122358c4c8475160b008a24c02f35c67c59fef7e3657101ec9f4894792d","last_reissued_at":"2026-07-05T06:03:00.189138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:00.189138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.10572","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":"2026-07-05T06:03:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U5gE5iRgIJbVslMNJF6fbrAKFhyHwTwxm0w5RKlEAhvzyufeprpqWCik1hjTTYefDVryVylVkeZthUT7WjOWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:24:20.207465Z"},"content_sha256":"449dff1ff6251859c2846a074b283564c217a5c0edfc2e05bd85e02af54fde79","schema_version":"1.0","event_id":"sha256:449dff1ff6251859c2846a074b283564c217a5c0edfc2e05bd85e02af54fde79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RS4QCIRVRRGII5IWBMAIUJGAF4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KOIOS: Top-k Semantic Overlap Set Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Fatemeh Nargesian, Jianhao Zhang, Nikolaus Augsten, Pranay Mundra","submitted_at":"2023-04-20T18:03:21Z","abstract_excerpt":"We study the top-k set similarity search problem using semantic overlap. While vanilla overlap requires exact matches between set elements, semantic overlap allows elements that are syntactically different but semantically related to increase the overlap. The semantic overlap is the maximum matching score of a bipartite graph, where an edge weight between two set elements is defined by a user-defined similarity function, e.g., cosine similarity between embeddings. Common techniques like token indexes fail for semantic search since similar elements may be unrelated at the character level. Furth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10572","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/2304.10572/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":"2026-07-05T06:03:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0OnG1R0T0q6erIbpILU/a+6SsWYVQK8ZQJngKYIGe3YC62n4Cf6cuZkooFswg8hcZ5utXUiQFx5U/y9FRPfIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:24:20.208108Z"},"content_sha256":"bac893c0a9fc5a84aff32841f895bef288afe2f8732babd7189a158079369cab","schema_version":"1.0","event_id":"sha256:bac893c0a9fc5a84aff32841f895bef288afe2f8732babd7189a158079369cab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RS4QCIRVRRGII5IWBMAIUJGAF4/bundle.json","state_url":"https://pith.science/pith/RS4QCIRVRRGII5IWBMAIUJGAF4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RS4QCIRVRRGII5IWBMAIUJGAF4/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":"2026-07-09T05:24:20Z","links":{"resolver":"https://pith.science/pith/RS4QCIRVRRGII5IWBMAIUJGAF4","bundle":"https://pith.science/pith/RS4QCIRVRRGII5IWBMAIUJGAF4/bundle.json","state":"https://pith.science/pith/RS4QCIRVRRGII5IWBMAIUJGAF4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RS4QCIRVRRGII5IWBMAIUJGAF4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RS4QCIRVRRGII5IWBMAIUJGAF4","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":"966e0f3a624458060337f5caa7e1f8335e39098ccff10e2e43087d4b43d48a04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-04-20T18:03:21Z","title_canon_sha256":"439ab69cceb2743f86d0ba8e24a646846db918ad6450e170fa10cbf607eea2ed"},"schema_version":"1.0","source":{"id":"2304.10572","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.10572","created_at":"2026-07-05T06:03:00Z"},{"alias_kind":"arxiv_version","alias_value":"2304.10572v1","created_at":"2026-07-05T06:03:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10572","created_at":"2026-07-05T06:03:00Z"},{"alias_kind":"pith_short_12","alias_value":"RS4QCIRVRRGI","created_at":"2026-07-05T06:03:00Z"},{"alias_kind":"pith_short_16","alias_value":"RS4QCIRVRRGII5IW","created_at":"2026-07-05T06:03:00Z"},{"alias_kind":"pith_short_8","alias_value":"RS4QCIRV","created_at":"2026-07-05T06:03:00Z"}],"graph_snapshots":[{"event_id":"sha256:bac893c0a9fc5a84aff32841f895bef288afe2f8732babd7189a158079369cab","target":"graph","created_at":"2026-07-05T06:03:00Z","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/2304.10572/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the top-k set similarity search problem using semantic overlap. While vanilla overlap requires exact matches between set elements, semantic overlap allows elements that are syntactically different but semantically related to increase the overlap. The semantic overlap is the maximum matching score of a bipartite graph, where an edge weight between two set elements is defined by a user-defined similarity function, e.g., cosine similarity between embeddings. Common techniques like token indexes fail for semantic search since similar elements may be unrelated at the character level. Furth","authors_text":"Fatemeh Nargesian, Jianhao Zhang, Nikolaus Augsten, Pranay Mundra","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-04-20T18:03:21Z","title":"KOIOS: Top-k Semantic Overlap Set Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10572","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":"sha256:449dff1ff6251859c2846a074b283564c217a5c0edfc2e05bd85e02af54fde79","target":"record","created_at":"2026-07-05T06:03:00Z","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":"966e0f3a624458060337f5caa7e1f8335e39098ccff10e2e43087d4b43d48a04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-04-20T18:03:21Z","title_canon_sha256":"439ab69cceb2743f86d0ba8e24a646846db918ad6450e170fa10cbf607eea2ed"},"schema_version":"1.0","source":{"id":"2304.10572","kind":"arxiv","version":1}},"canonical_sha256":"8cb90122358c4c8475160b008a24c02f35c67c59fef7e3657101ec9f4894792d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cb90122358c4c8475160b008a24c02f35c67c59fef7e3657101ec9f4894792d","first_computed_at":"2026-07-05T06:03:00.189138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:00.189138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HvEn14VxEiOqb1dws8TJ6VxcL3C6prDb4zSB3MnlFknL5nKAKRVAFI7yNaZ05s4uOhNC3QT8Elm6skCvSlhaBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:00.189580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.10572","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:449dff1ff6251859c2846a074b283564c217a5c0edfc2e05bd85e02af54fde79","sha256:bac893c0a9fc5a84aff32841f895bef288afe2f8732babd7189a158079369cab"],"state_sha256":"b42e14b0032b2ccd6130dc643593b816b613a221e54e69bc9ce356ec5c611dd0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7moRtJgWtC1ojakcMG9lOIy2lKuxUla5qcDAhj7DSbFCdzQcuEkafdXFs3jTfntyx9LIP9VeQ03/Z4dYsF2JBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:24:20.212043Z","bundle_sha256":"b403a25daaf63f568894b170f08fcb5f87500b8fb4f10160d31edd0c05012f3f"}}