{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SMVXYZQTTAFSZ7PRJDRULCWXLQ","short_pith_number":"pith:SMVXYZQT","schema_version":"1.0","canonical_sha256":"932b7c6613980b2cfdf148e3458ad75c0d29fbab7a7dc43173ec1a7b94400f29","source":{"kind":"arxiv","id":"2607.01972","version":1},"attestation_state":"computed","paper":{"title":"Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jan Drchal","submitted_at":"2026-07-02T10:07:34Z","abstract_excerpt":"Large language models (LLMs) are often asked to produce JSON conforming to a fixed schema, powering information extraction, tool calling, agentic planning, and knowledge-graph construction. Measuring how closely an output matches a gold reference is essential yet surprisingly hard: exact match is brittle, text similarity ignores structure, and an LLM judge is expensive, opaque, and non-deterministic. We address this with Object Aligner (OA), an open-source Python library that scores two JSON objects deterministically by recursively aligning their trees (the Hungarian algorithm for unordered co"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.01972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-02T10:07:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"59b1c9b04601ad5a1f8ebfc3fd7a1cee5e908b3c66e6ffc6081177d8a729b66b","abstract_canon_sha256":"a7278f3d840f6f708fce17bbf03ec2b3a3dd3c368071df5995cfa7165721cb3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:35.832859Z","signature_b64":"3+Zl5Rh8HN3F5z2Rrie74fQrT9+bSgXRg3R6KaLHDyPE4bfl+2MJ9evvSAuIj/cfG4wp3MEDEHFo6YpcJlaxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"932b7c6613980b2cfdf148e3458ad75c0d29fbab7a7dc43173ec1a7b94400f29","last_reissued_at":"2026-07-03T01:17:35.832362Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:35.832362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jan Drchal","submitted_at":"2026-07-02T10:07:34Z","abstract_excerpt":"Large language models (LLMs) are often asked to produce JSON conforming to a fixed schema, powering information extraction, tool calling, agentic planning, and knowledge-graph construction. Measuring how closely an output matches a gold reference is essential yet surprisingly hard: exact match is brittle, text similarity ignores structure, and an LLM judge is expensive, opaque, and non-deterministic. We address this with Object Aligner (OA), an open-source Python library that scores two JSON objects deterministically by recursively aligning their trees (the Hungarian algorithm for unordered co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01972","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/2607.01972/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.01972","created_at":"2026-07-03T01:17:35.832421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01972v1","created_at":"2026-07-03T01:17:35.832421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01972","created_at":"2026-07-03T01:17:35.832421+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMVXYZQTTAFS","created_at":"2026-07-03T01:17:35.832421+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMVXYZQTTAFSZ7PR","created_at":"2026-07-03T01:17:35.832421+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMVXYZQT","created_at":"2026-07-03T01:17:35.832421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMVXYZQTTAFSZ7PRJDRULCWXLQ","json":"https://pith.science/pith/SMVXYZQTTAFSZ7PRJDRULCWXLQ.json","graph_json":"https://pith.science/api/pith-number/SMVXYZQTTAFSZ7PRJDRULCWXLQ/graph.json","events_json":"https://pith.science/api/pith-number/SMVXYZQTTAFSZ7PRJDRULCWXLQ/events.json","paper":"https://pith.science/paper/SMVXYZQT"},"agent_actions":{"view_html":"https://pith.science/pith/SMVXYZQTTAFSZ7PRJDRULCWXLQ","download_json":"https://pith.science/pith/SMVXYZQTTAFSZ7PRJDRULCWXLQ.json","view_paper":"https://pith.science/paper/SMVXYZQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01972&json=true","fetch_graph":"https://pith.science/api/pith-number/SMVXYZQTTAFSZ7PRJDRULCWXLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SMVXYZQTTAFSZ7PRJDRULCWXLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMVXYZQTTAFSZ7PRJDRULCWXLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMVXYZQTTAFSZ7PRJDRULCWXLQ/action/storage_attestation","attest_author":"https://pith.science/pith/SMVXYZQTTAFSZ7PRJDRULCWXLQ/action/author_attestation","sign_citation":"https://pith.science/pith/SMVXYZQTTAFSZ7PRJDRULCWXLQ/action/citation_signature","submit_replication":"https://pith.science/pith/SMVXYZQTTAFSZ7PRJDRULCWXLQ/action/replication_record"}},"created_at":"2026-07-03T01:17:35.832421+00:00","updated_at":"2026-07-03T01:17:35.832421+00:00"}