{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:L533QI6QT4RXGGLOFAESOS47U2","short_pith_number":"pith:L533QI6Q","canonical_record":{"source":{"id":"2606.24407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-23T10:44:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3874c5d5c5e242bf6ce25b12bde374cd802f69c5efd14873bca5b87a0fa312f0","abstract_canon_sha256":"181659c3dd5b516d97920dbb30f4a24576b31728c8b62ba885fcd9a9970c7a6c"},"schema_version":"1.0"},"canonical_sha256":"5f77b823d09f2373196e2809274b9fa694ef292999ff7b85ce02af01b614ad7e","source":{"kind":"arxiv","id":"2606.24407","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24407","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24407v1","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24407","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"L533QI6QT4RX","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"L533QI6QT4RXGGLO","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"L533QI6Q","created_at":"2026-06-24T01:15:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:L533QI6QT4RXGGLOFAESOS47U2","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-23T10:44:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3874c5d5c5e242bf6ce25b12bde374cd802f69c5efd14873bca5b87a0fa312f0","abstract_canon_sha256":"181659c3dd5b516d97920dbb30f4a24576b31728c8b62ba885fcd9a9970c7a6c"},"schema_version":"1.0"},"canonical_sha256":"5f77b823d09f2373196e2809274b9fa694ef292999ff7b85ce02af01b614ad7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:29.724351Z","signature_b64":"PZAvX1PZl3q+i2AAQ/jb1AIQ8Nf7F0ziXG0sEFbjvLnRB38Gr+2rbF/calaDq6ur8YwtIkHwTZxKIrcs21mMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f77b823d09f2373196e2809274b9fa694ef292999ff7b85ce02af01b614ad7e","last_reissued_at":"2026-06-24T01:15:29.723998Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:29.723998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24407","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":"2026-06-24T01:15:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CIWqBmTchzG0e3F4emES4g6UmZRxKTjidKSoQVJpmJg5un+FCa0RJCth/bTyBp+DFOBO/unwUPwxT2FNkyF6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T10:50:19.321734Z"},"content_sha256":"ffb9e79dad6c412600e0c6acfc28b12500b8b5f0f5884cda37164b6a791a0567","schema_version":"1.0","event_id":"sha256:ffb9e79dad6c412600e0c6acfc28b12500b8b5f0f5884cda37164b6a791a0567"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:L533QI6QT4RXGGLOFAESOS47U2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entity Resolution via Batched Oracle Queries","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Donatella Firmani, Giovanni Simonini, Lorenzo Balzotti, Luca Gagliardelli","submitted_at":"2026-06-23T10:44:35Z","abstract_excerpt":"We consider an oracle that processes a limited batch of records at a time and clusters those that refer to the same real-world entity. We study how to interrogate such an oracle to resolve entities in a dataset whose size is far larger than a single batch, and where no batch is guaranteed to contain all records of any given entity. We aim at a pay-as-you-go approach, to have full control over the costs (the number of oracle consults), while achieving the highest possible recall at every step. We formally cast this problem as batched entity resolution, prove that selecting optimal batches is NP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24407","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/2606.24407/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":"2026-06-24T01:15:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5fLm548SBrwzs1M59W8fGR1fA3LstvORD03p3AggIPed6jF7vC2Q7Nm7bGdhOBz+5ufs1MLt3iIBxXWVbz4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T10:50:19.322110Z"},"content_sha256":"24449ebb6c51f80bf1b38f598238f7f6a9090208e415854e4274bc4ce8c5acdc","schema_version":"1.0","event_id":"sha256:24449ebb6c51f80bf1b38f598238f7f6a9090208e415854e4274bc4ce8c5acdc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L533QI6QT4RXGGLOFAESOS47U2/bundle.json","state_url":"https://pith.science/pith/L533QI6QT4RXGGLOFAESOS47U2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L533QI6QT4RXGGLOFAESOS47U2/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":"2026-06-25T10:50:19Z","links":{"resolver":"https://pith.science/pith/L533QI6QT4RXGGLOFAESOS47U2","bundle":"https://pith.science/pith/L533QI6QT4RXGGLOFAESOS47U2/bundle.json","state":"https://pith.science/pith/L533QI6QT4RXGGLOFAESOS47U2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L533QI6QT4RXGGLOFAESOS47U2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:L533QI6QT4RXGGLOFAESOS47U2","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":"181659c3dd5b516d97920dbb30f4a24576b31728c8b62ba885fcd9a9970c7a6c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-23T10:44:35Z","title_canon_sha256":"3874c5d5c5e242bf6ce25b12bde374cd802f69c5efd14873bca5b87a0fa312f0"},"schema_version":"1.0","source":{"id":"2606.24407","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24407","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24407v1","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24407","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"L533QI6QT4RX","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"L533QI6QT4RXGGLO","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"L533QI6Q","created_at":"2026-06-24T01:15:29Z"}],"graph_snapshots":[{"event_id":"sha256:24449ebb6c51f80bf1b38f598238f7f6a9090208e415854e4274bc4ce8c5acdc","target":"graph","created_at":"2026-06-24T01:15:29Z","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/2606.24407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider an oracle that processes a limited batch of records at a time and clusters those that refer to the same real-world entity. We study how to interrogate such an oracle to resolve entities in a dataset whose size is far larger than a single batch, and where no batch is guaranteed to contain all records of any given entity. We aim at a pay-as-you-go approach, to have full control over the costs (the number of oracle consults), while achieving the highest possible recall at every step. We formally cast this problem as batched entity resolution, prove that selecting optimal batches is NP","authors_text":"Donatella Firmani, Giovanni Simonini, Lorenzo Balzotti, Luca Gagliardelli","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-23T10:44:35Z","title":"Entity Resolution via Batched Oracle Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24407","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:ffb9e79dad6c412600e0c6acfc28b12500b8b5f0f5884cda37164b6a791a0567","target":"record","created_at":"2026-06-24T01:15:29Z","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":"181659c3dd5b516d97920dbb30f4a24576b31728c8b62ba885fcd9a9970c7a6c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-23T10:44:35Z","title_canon_sha256":"3874c5d5c5e242bf6ce25b12bde374cd802f69c5efd14873bca5b87a0fa312f0"},"schema_version":"1.0","source":{"id":"2606.24407","kind":"arxiv","version":1}},"canonical_sha256":"5f77b823d09f2373196e2809274b9fa694ef292999ff7b85ce02af01b614ad7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f77b823d09f2373196e2809274b9fa694ef292999ff7b85ce02af01b614ad7e","first_computed_at":"2026-06-24T01:15:29.723998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:29.723998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PZAvX1PZl3q+i2AAQ/jb1AIQ8Nf7F0ziXG0sEFbjvLnRB38Gr+2rbF/calaDq6ur8YwtIkHwTZxKIrcs21mMCg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:29.724351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24407","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffb9e79dad6c412600e0c6acfc28b12500b8b5f0f5884cda37164b6a791a0567","sha256:24449ebb6c51f80bf1b38f598238f7f6a9090208e415854e4274bc4ce8c5acdc"],"state_sha256":"9fdeb8f3daf940ed18e8e5be1d4c922423a300026f3ea38d9361ccd0ffb1d726"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EZ50c/S9zGnh4oykXR9p1dhKJk1CA2GraVnQ2yt6gQJpi9d4YcUpDm0EX7GsgAxcNE0+YmECbwveOltp9uuLCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T10:50:19.324099Z","bundle_sha256":"6fe51617c6941876684e4fcc272441b451c54e22f99d12932b8a37f7fa7b1606"}}