{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:U53DPWSNKMQRN5UKSLYBR2JALG","short_pith_number":"pith:U53DPWSN","canonical_record":{"source":{"id":"2607.00254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-06-30T23:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"945c12b95c4b4c1e7f02b46b8fa76fcf064a131cd10d2d5bcc7338b8e0298427","abstract_canon_sha256":"abca73342354cd8c1c0b4bd5a21b2214773348a34cc42a966dda2f896fc99f58"},"schema_version":"1.0"},"canonical_sha256":"a77637da4d532116f68a92f018e9205991f15c89289ee4a9c0eb37ef7df0ce86","source":{"kind":"arxiv","id":"2607.00254","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00254","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00254v1","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00254","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_12","alias_value":"U53DPWSNKMQR","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_16","alias_value":"U53DPWSNKMQRN5UK","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_8","alias_value":"U53DPWSN","created_at":"2026-07-02T00:18:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:U53DPWSNKMQRN5UKSLYBR2JALG","target":"record","payload":{"canonical_record":{"source":{"id":"2607.00254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-06-30T23:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"945c12b95c4b4c1e7f02b46b8fa76fcf064a131cd10d2d5bcc7338b8e0298427","abstract_canon_sha256":"abca73342354cd8c1c0b4bd5a21b2214773348a34cc42a966dda2f896fc99f58"},"schema_version":"1.0"},"canonical_sha256":"a77637da4d532116f68a92f018e9205991f15c89289ee4a9c0eb37ef7df0ce86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:41.229832Z","signature_b64":"GdZzTNC+rP4FZ2ULTFFi3jK/qDVMvJDM6N4lCoXUiZLX6Efyxaj6ROSrB60rWrZztKsOwtIO1SxgmYm6mVg5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a77637da4d532116f68a92f018e9205991f15c89289ee4a9c0eb37ef7df0ce86","last_reissued_at":"2026-07-02T00:18:41.228878Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:41.228878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.00254","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":"2026-07-02T00:18:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uyxl2wO41IPLDO82wcGcl78jEaMWOCU6sC2kiBu1YqbYR1oi6upUqLwNdAWxeBG4h+G5NE0N4rzShieP4XR8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T04:12:13.667643Z"},"content_sha256":"45232c4ffb8010f9f8835c6f6f69ea7459ab1fc9063af1ef89badbeb7b535121","schema_version":"1.0","event_id":"sha256:45232c4ffb8010f9f8835c6f6f69ea7459ab1fc9063af1ef89badbeb7b535121"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:U53DPWSNKMQRN5UKSLYBR2JALG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Query-Centric Optimization of AI Workflows via Approximate Query Processing and Proxy Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Gromit Yeuk-Yin Chan, Huayi Wang, Jun Xu","submitted_at":"2026-06-30T23:05:59Z","abstract_excerpt":"Many modern AI workflows, ranging from LLM post-training pipelines to agentic reasoning tasks, can be expressed as declarative queries whose expensive predicate is evaluated by a large model or reward function. We propose a query-centric formulation of these workflows and show that classical database techniques, namely approximate query processing (AQP) and proxy-model (PM) based filtering, can substantially reduce the number of expensive model invocations without requiring changes to the underlying models or pipelines. Our first strategy treats the workflow as an online aggregation problem: i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00254","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/2607.00254/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":"2026-07-02T00:18:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"268S4/4TpAh1vZjA0gKu4s4cGR8dUus89m1SY4enFm0lDrfTAdQ+iV8RHmIVDgGgxYXIAc9+4DIdqBjqFc4LBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T04:12:13.668015Z"},"content_sha256":"59efab9b168b502cfb2d39681aa442243cd0b90cd8ec8a069dcc5ad8b61b68b2","schema_version":"1.0","event_id":"sha256:59efab9b168b502cfb2d39681aa442243cd0b90cd8ec8a069dcc5ad8b61b68b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U53DPWSNKMQRN5UKSLYBR2JALG/bundle.json","state_url":"https://pith.science/pith/U53DPWSNKMQRN5UKSLYBR2JALG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U53DPWSNKMQRN5UKSLYBR2JALG/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":"2026-07-03T04:12:13Z","links":{"resolver":"https://pith.science/pith/U53DPWSNKMQRN5UKSLYBR2JALG","bundle":"https://pith.science/pith/U53DPWSNKMQRN5UKSLYBR2JALG/bundle.json","state":"https://pith.science/pith/U53DPWSNKMQRN5UKSLYBR2JALG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U53DPWSNKMQRN5UKSLYBR2JALG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U53DPWSNKMQRN5UKSLYBR2JALG","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":"abca73342354cd8c1c0b4bd5a21b2214773348a34cc42a966dda2f896fc99f58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-06-30T23:05:59Z","title_canon_sha256":"945c12b95c4b4c1e7f02b46b8fa76fcf064a131cd10d2d5bcc7338b8e0298427"},"schema_version":"1.0","source":{"id":"2607.00254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00254","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00254v1","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00254","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_12","alias_value":"U53DPWSNKMQR","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_16","alias_value":"U53DPWSNKMQRN5UK","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_8","alias_value":"U53DPWSN","created_at":"2026-07-02T00:18:41Z"}],"graph_snapshots":[{"event_id":"sha256:59efab9b168b502cfb2d39681aa442243cd0b90cd8ec8a069dcc5ad8b61b68b2","target":"graph","created_at":"2026-07-02T00:18:41Z","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/2607.00254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many modern AI workflows, ranging from LLM post-training pipelines to agentic reasoning tasks, can be expressed as declarative queries whose expensive predicate is evaluated by a large model or reward function. We propose a query-centric formulation of these workflows and show that classical database techniques, namely approximate query processing (AQP) and proxy-model (PM) based filtering, can substantially reduce the number of expensive model invocations without requiring changes to the underlying models or pipelines. Our first strategy treats the workflow as an online aggregation problem: i","authors_text":"Gromit Yeuk-Yin Chan, Huayi Wang, Jun Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-06-30T23:05:59Z","title":"Query-Centric Optimization of AI Workflows via Approximate Query Processing and Proxy Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00254","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":"sha256:45232c4ffb8010f9f8835c6f6f69ea7459ab1fc9063af1ef89badbeb7b535121","target":"record","created_at":"2026-07-02T00:18:41Z","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":"abca73342354cd8c1c0b4bd5a21b2214773348a34cc42a966dda2f896fc99f58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-06-30T23:05:59Z","title_canon_sha256":"945c12b95c4b4c1e7f02b46b8fa76fcf064a131cd10d2d5bcc7338b8e0298427"},"schema_version":"1.0","source":{"id":"2607.00254","kind":"arxiv","version":1}},"canonical_sha256":"a77637da4d532116f68a92f018e9205991f15c89289ee4a9c0eb37ef7df0ce86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a77637da4d532116f68a92f018e9205991f15c89289ee4a9c0eb37ef7df0ce86","first_computed_at":"2026-07-02T00:18:41.228878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T00:18:41.228878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GdZzTNC+rP4FZ2ULTFFi3jK/qDVMvJDM6N4lCoXUiZLX6Efyxaj6ROSrB60rWrZztKsOwtIO1SxgmYm6mVg5Bw==","signature_status":"signed_v1","signed_at":"2026-07-02T00:18:41.229832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45232c4ffb8010f9f8835c6f6f69ea7459ab1fc9063af1ef89badbeb7b535121","sha256:59efab9b168b502cfb2d39681aa442243cd0b90cd8ec8a069dcc5ad8b61b68b2"],"state_sha256":"c7fe5fa30417b705b18f7c158a632a11d72c0c65acc11c7ddbcc3d11b004e1e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X3xBt6iTvQZ4p4KeCJc8Mz8rCn/AbfRjnOmPmIWo/gDA0Ut0/iuWmwSxsm/+HIrscJdOWMKVJAU6ARDNzdEgDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T04:12:13.670225Z","bundle_sha256":"c4a9babb877295347ddc17d803aa60647baa5dcf1e07488a1cdfbcd4f9ae7cfe"}}