{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GK5SYN5HPQRSEKVRHD74OP4CB5","short_pith_number":"pith:GK5SYN5H","canonical_record":{"source":{"id":"2606.29532","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-28T17:57:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a4a240ba7172e69018d00731fe2d1a0b0192486acdd93423ca46b36bcc3a655","abstract_canon_sha256":"734f413f7428a5a2986aa2d84838e6e5d0422a19182362c9fe0f4974f22cfcda"},"schema_version":"1.0"},"canonical_sha256":"32bb2c37a77c23222ab138ffc73f820f6ca873317ab803618be2c99ab8dbb13b","source":{"kind":"arxiv","id":"2606.29532","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29532","created_at":"2026-06-30T01:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29532v1","created_at":"2026-06-30T01:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29532","created_at":"2026-06-30T01:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"GK5SYN5HPQRS","created_at":"2026-06-30T01:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"GK5SYN5HPQRSEKVR","created_at":"2026-06-30T01:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"GK5SYN5H","created_at":"2026-06-30T01:18:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GK5SYN5HPQRSEKVRHD74OP4CB5","target":"record","payload":{"canonical_record":{"source":{"id":"2606.29532","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-28T17:57:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a4a240ba7172e69018d00731fe2d1a0b0192486acdd93423ca46b36bcc3a655","abstract_canon_sha256":"734f413f7428a5a2986aa2d84838e6e5d0422a19182362c9fe0f4974f22cfcda"},"schema_version":"1.0"},"canonical_sha256":"32bb2c37a77c23222ab138ffc73f820f6ca873317ab803618be2c99ab8dbb13b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:10.647523Z","signature_b64":"2WfbBprl10+vPkp0L2iB9a2sHdw+LqK5OLhHzNisMvbVKwBtEMI/5IS4EBEsXt64KsUSS/P++8Hw2d4wE137CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32bb2c37a77c23222ab138ffc73f820f6ca873317ab803618be2c99ab8dbb13b","last_reissued_at":"2026-06-30T01:18:10.646992Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:10.646992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.29532","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":"2026-06-30T01:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cAWsOU9/EJIlw0Tw1ftbWkzkXjR7bQL+Yk0yVfE1NKq1u3VAG0DewXTlHFGzcToSVZFPn8ab7qkk+kCB/x2mBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:06:35.677886Z"},"content_sha256":"b5e754bf113fdb636d7985aba0ae4147993d1116886c07ce59923244f3239980","schema_version":"1.0","event_id":"sha256:b5e754bf113fdb636d7985aba0ae4147993d1116886c07ce59923244f3239980"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GK5SYN5HPQRSEKVRHD74OP4CB5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SemJoin: Semantic Join Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Aditya Banerjee, Christopher Gou, Chunwei Liu, Jiaxuan Wang","submitted_at":"2026-06-28T17:57:10Z","abstract_excerpt":"Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis. A semantic join, joining two tables under a natural-language predicate, can be evaluated with a large language model (LLM), but comparing every pair of tuples requires O(M x N) LLM invocations and is cost-prohibitive at scale. Existing systems reduce this cost but typically commit to a single fixed strategy (e.g., embedding similarity or one batched scheme) regardless of the data or the join predicate. We propose an LLM-agent-based decision pipeli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29532","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/2606.29532/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":"2026-06-30T01:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKVsDNsa4GR8PVyjA0Nkie+k1NjX7H56AWqEhhGdT00EOAuC4hJiRv1uu2kL6lmJS5t1P2D/kqXh6rxetsRGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T02:06:35.678245Z"},"content_sha256":"3c2a4acfbf59a41a4ebaaaa973fdf651168364b563b12730317e9422fc9f5913","schema_version":"1.0","event_id":"sha256:3c2a4acfbf59a41a4ebaaaa973fdf651168364b563b12730317e9422fc9f5913"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/bundle.json","state_url":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/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":"2026-07-17T02:06:35Z","links":{"resolver":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5","bundle":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/bundle.json","state":"https://pith.science/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GK5SYN5HPQRSEKVRHD74OP4CB5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GK5SYN5HPQRSEKVRHD74OP4CB5","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":"734f413f7428a5a2986aa2d84838e6e5d0422a19182362c9fe0f4974f22cfcda","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-28T17:57:10Z","title_canon_sha256":"2a4a240ba7172e69018d00731fe2d1a0b0192486acdd93423ca46b36bcc3a655"},"schema_version":"1.0","source":{"id":"2606.29532","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29532","created_at":"2026-06-30T01:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29532v1","created_at":"2026-06-30T01:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29532","created_at":"2026-06-30T01:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"GK5SYN5HPQRS","created_at":"2026-06-30T01:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"GK5SYN5HPQRSEKVR","created_at":"2026-06-30T01:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"GK5SYN5H","created_at":"2026-06-30T01:18:10Z"}],"graph_snapshots":[{"event_id":"sha256:3c2a4acfbf59a41a4ebaaaa973fdf651168364b563b12730317e9422fc9f5913","target":"graph","created_at":"2026-06-30T01:18:10Z","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/2606.29532/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis. A semantic join, joining two tables under a natural-language predicate, can be evaluated with a large language model (LLM), but comparing every pair of tuples requires O(M x N) LLM invocations and is cost-prohibitive at scale. Existing systems reduce this cost but typically commit to a single fixed strategy (e.g., embedding similarity or one batched scheme) regardless of the data or the join predicate. We propose an LLM-agent-based decision pipeli","authors_text":"Aditya Banerjee, Christopher Gou, Chunwei Liu, Jiaxuan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-28T17:57:10Z","title":"SemJoin: Semantic Join Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29532","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:b5e754bf113fdb636d7985aba0ae4147993d1116886c07ce59923244f3239980","target":"record","created_at":"2026-06-30T01:18:10Z","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":"734f413f7428a5a2986aa2d84838e6e5d0422a19182362c9fe0f4974f22cfcda","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-28T17:57:10Z","title_canon_sha256":"2a4a240ba7172e69018d00731fe2d1a0b0192486acdd93423ca46b36bcc3a655"},"schema_version":"1.0","source":{"id":"2606.29532","kind":"arxiv","version":1}},"canonical_sha256":"32bb2c37a77c23222ab138ffc73f820f6ca873317ab803618be2c99ab8dbb13b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32bb2c37a77c23222ab138ffc73f820f6ca873317ab803618be2c99ab8dbb13b","first_computed_at":"2026-06-30T01:18:10.646992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:10.646992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2WfbBprl10+vPkp0L2iB9a2sHdw+LqK5OLhHzNisMvbVKwBtEMI/5IS4EBEsXt64KsUSS/P++8Hw2d4wE137CQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:10.647523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29532","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5e754bf113fdb636d7985aba0ae4147993d1116886c07ce59923244f3239980","sha256:3c2a4acfbf59a41a4ebaaaa973fdf651168364b563b12730317e9422fc9f5913"],"state_sha256":"88ec404319574b5a841b7c7a3e6f7c2023c1566c3eab762f393da8c4ba4e3d1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l4Z+LvwhJU6ignO7hX30FRgaax6mPYheI85mGkHwiapueIKcVXsr22rM+NxOIcEJbnWFXchv3+A4fDZILNXbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T02:06:35.680383Z","bundle_sha256":"3b1724c3d1f66c9c6505beb0b5d1dbbaaeea5c73eb0615604fc87e13b00f53ce"}}