{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:32UD7DB3LKMDCPQDSLPQRSRY6E","short_pith_number":"pith:32UD7DB3","canonical_record":{"source":{"id":"2606.08090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-06T10:32:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"baa5a0253475c089c3b3282ea150bc6ce0f2830c23c44ad5550eeca51df3b182","abstract_canon_sha256":"96055d798877191355dd8119c9a179942a8710181c9e2033ca5bd8de10a28d1c"},"schema_version":"1.0"},"canonical_sha256":"dea83f8c3b5a98313e0392df08ca38f13816bc3ad668b06b6194c93a4c9be069","source":{"kind":"arxiv","id":"2606.08090","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08090","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08090v1","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08090","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"32UD7DB3LKMD","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"32UD7DB3LKMDCPQD","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"32UD7DB3","created_at":"2026-06-09T01:05:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:32UD7DB3LKMDCPQDSLPQRSRY6E","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-06T10:32:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"baa5a0253475c089c3b3282ea150bc6ce0f2830c23c44ad5550eeca51df3b182","abstract_canon_sha256":"96055d798877191355dd8119c9a179942a8710181c9e2033ca5bd8de10a28d1c"},"schema_version":"1.0"},"canonical_sha256":"dea83f8c3b5a98313e0392df08ca38f13816bc3ad668b06b6194c93a4c9be069","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:25.979815Z","signature_b64":"pMijKw6ho/eL1U+RUrWlZi3KhBw+th0iMZA5Lx2d4qzPx8SYdgD3KhByJpiAKyDQLPa5ZI+vzt4A2MZvyW/YAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dea83f8c3b5a98313e0392df08ca38f13816bc3ad668b06b6194c93a4c9be069","last_reissued_at":"2026-06-09T01:05:25.979350Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:25.979350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08090","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":"2026-06-09T01:05:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2z8u9WYlVT2vCEjMP2yEEQ94aVkyJBo+JaVUm+mlFsY+eo4WwQXa9UFJKsKkyo2tpm5FlK6USnWKWhn9pLeLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T16:43:07.171758Z"},"content_sha256":"2b47af757114024aabced2f8dc34d8e477019606b0bc13602a390a5c6f1f4335","schema_version":"1.0","event_id":"sha256:2b47af757114024aabced2f8dc34d8e477019606b0bc13602a390a5c6f1f4335"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:32UD7DB3LKMDCPQDSLPQRSRY6E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Anastasia Ailamaki, Kyoungmin Kim, Martin Catheland","submitted_at":"2026-06-06T10:32:16Z","abstract_excerpt":"Evaluating a natural-language yes/no predicate over a document corpus under an accuracy target - the semantic filter - is a cornerstone of LLM-based data processing. Calling the LLM on every document (the oracle) is prohibitive, so cascades pair the oracle with a fast proxy. As deployed today, they leave four limitations on the table. (1) Each cascade family - model-free clustering, prebuilt small-LLM proxies, online-trained proxies - commits to a single representation and pipeline, and wins on only a narrow query regime. (2) The strongest online proxy invests in a custom training scheme on a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08090","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/2606.08090/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":"2026-06-09T01:05:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mQ57K3ZaYWPkltRFrM4j8FYIihPtx9jIitShK/4C6ce5+9vd3whIZrPZHkgIhSOYd1PmBA3oUrchkYodmNAqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T16:43:07.172137Z"},"content_sha256":"1d3f201c9f8afb656a961612c18e185bf9d12c32fc0066bdaf1f9b2a310e2c29","schema_version":"1.0","event_id":"sha256:1d3f201c9f8afb656a961612c18e185bf9d12c32fc0066bdaf1f9b2a310e2c29"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/32UD7DB3LKMDCPQDSLPQRSRY6E/bundle.json","state_url":"https://pith.science/pith/32UD7DB3LKMDCPQDSLPQRSRY6E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/32UD7DB3LKMDCPQDSLPQRSRY6E/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":"2026-06-28T16:43:07Z","links":{"resolver":"https://pith.science/pith/32UD7DB3LKMDCPQDSLPQRSRY6E","bundle":"https://pith.science/pith/32UD7DB3LKMDCPQDSLPQRSRY6E/bundle.json","state":"https://pith.science/pith/32UD7DB3LKMDCPQDSLPQRSRY6E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/32UD7DB3LKMDCPQDSLPQRSRY6E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:32UD7DB3LKMDCPQDSLPQRSRY6E","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":"96055d798877191355dd8119c9a179942a8710181c9e2033ca5bd8de10a28d1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-06T10:32:16Z","title_canon_sha256":"baa5a0253475c089c3b3282ea150bc6ce0f2830c23c44ad5550eeca51df3b182"},"schema_version":"1.0","source":{"id":"2606.08090","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08090","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08090v1","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08090","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"32UD7DB3LKMD","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"32UD7DB3LKMDCPQD","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"32UD7DB3","created_at":"2026-06-09T01:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:1d3f201c9f8afb656a961612c18e185bf9d12c32fc0066bdaf1f9b2a310e2c29","target":"graph","created_at":"2026-06-09T01:05:25Z","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/2606.08090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating a natural-language yes/no predicate over a document corpus under an accuracy target - the semantic filter - is a cornerstone of LLM-based data processing. Calling the LLM on every document (the oracle) is prohibitive, so cascades pair the oracle with a fast proxy. As deployed today, they leave four limitations on the table. (1) Each cascade family - model-free clustering, prebuilt small-LLM proxies, online-trained proxies - commits to a single representation and pipeline, and wins on only a narrow query regime. (2) The strongest online proxy invests in a custom training scheme on a ","authors_text":"Anastasia Ailamaki, Kyoungmin Kim, Martin Catheland","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-06T10:32:16Z","title":"Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08090","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":"sha256:2b47af757114024aabced2f8dc34d8e477019606b0bc13602a390a5c6f1f4335","target":"record","created_at":"2026-06-09T01:05:25Z","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":"96055d798877191355dd8119c9a179942a8710181c9e2033ca5bd8de10a28d1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-06T10:32:16Z","title_canon_sha256":"baa5a0253475c089c3b3282ea150bc6ce0f2830c23c44ad5550eeca51df3b182"},"schema_version":"1.0","source":{"id":"2606.08090","kind":"arxiv","version":1}},"canonical_sha256":"dea83f8c3b5a98313e0392df08ca38f13816bc3ad668b06b6194c93a4c9be069","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dea83f8c3b5a98313e0392df08ca38f13816bc3ad668b06b6194c93a4c9be069","first_computed_at":"2026-06-09T01:05:25.979350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:25.979350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pMijKw6ho/eL1U+RUrWlZi3KhBw+th0iMZA5Lx2d4qzPx8SYdgD3KhByJpiAKyDQLPa5ZI+vzt4A2MZvyW/YAA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:25.979815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08090","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b47af757114024aabced2f8dc34d8e477019606b0bc13602a390a5c6f1f4335","sha256:1d3f201c9f8afb656a961612c18e185bf9d12c32fc0066bdaf1f9b2a310e2c29"],"state_sha256":"30519887a7902056596fdf4ff1b7f1074a15692ded98fc751c4e3c3d6d347fff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GnEtDxLftOsMsxx/2lyX7htPvqoSTnnm3/bvP7fdxKp2VuhP4ycM4hn5tI50jaoKLbaWZWKopgjknw/ujDcCCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T16:43:07.174485Z","bundle_sha256":"d4d3fcad6df24166d4820db43332e541d541aae6b97a762ce42c760005da1ae7"}}