{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QFYNVNFQEGJFAW3GS6PY3S7II4","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":"aff35d9191e9f00dd0da27ed387def22481d61110d7450338b10d1d575f54b3b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-09-16T03:18:06Z","title_canon_sha256":"8a6fb74f32e2166d7def0b3d0959b37280af42d0c8a0fe4052e1cdd4b09e2a6a"},"schema_version":"1.0","source":{"id":"2509.12610","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.12610","created_at":"2026-05-22T01:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2509.12610v2","created_at":"2026-05-22T01:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.12610","created_at":"2026-05-22T01:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"QFYNVNFQEGJF","created_at":"2026-05-22T01:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"QFYNVNFQEGJFAW3G","created_at":"2026-05-22T01:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"QFYNVNFQ","created_at":"2026-05-22T01:03:46Z"}],"graph_snapshots":[{"event_id":"sha256:42e7d3771a7077926250d9d8cbf5cce21bd225ff12002654e7b30f355920699f","target":"graph","created_at":"2026-05-22T01:03:46Z","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/2509.12610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Predicates are foundational components in data analysis systems. However, modern workloads increasingly involve unstructured documents, which demands semantic understanding, beyond traditional value-based predicates. Given enormous documents and ad-hoc queries, while Large Language Models (LLMs) demonstrate powerful zero-shot capabilities, their high inference cost leads to unacceptable overhead. Therefore, we introduce \\textsc{ScaleDoc}, a novel system that addresses this by decoupling predicate execution into an offline representation phase and an optimized online filtering phase. In the off","authors_text":"Hengrui Zhang, Huanchen Zhang, Yihao Liu, Yulong Hui","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-09-16T03:18:06Z","title":"ScaleDoc: Scaling LLM-based Predicates over Large Document Collections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.12610","kind":"arxiv","version":2},"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":"sha256:4ce965a6b832112a554a29c6fe4c390e46b3d1b17f98b3a6996a5b49e27d379d","target":"record","created_at":"2026-05-22T01:03:46Z","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":"aff35d9191e9f00dd0da27ed387def22481d61110d7450338b10d1d575f54b3b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-09-16T03:18:06Z","title_canon_sha256":"8a6fb74f32e2166d7def0b3d0959b37280af42d0c8a0fe4052e1cdd4b09e2a6a"},"schema_version":"1.0","source":{"id":"2509.12610","kind":"arxiv","version":2}},"canonical_sha256":"8170dab4b02192505b66979f8dcbe8470db1004d2c83b767a29e97ea4e12a35e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8170dab4b02192505b66979f8dcbe8470db1004d2c83b767a29e97ea4e12a35e","first_computed_at":"2026-05-22T01:03:46.588587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:46.588587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oyQ0tGvwjAstx4JwVQrl5PNo6LVDj2hfm9mr49kw5I9xhJrIszrSRwet/Z4+SuHgUX6FL3zJbGb99X5WoB90BQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:46.589551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.12610","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ce965a6b832112a554a29c6fe4c390e46b3d1b17f98b3a6996a5b49e27d379d","sha256:42e7d3771a7077926250d9d8cbf5cce21bd225ff12002654e7b30f355920699f"],"state_sha256":"620262610727850d4cc7c14dbfa414a375653c0a74c15880ddd682e2170583b6"}