{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DZFY33WWU26E4CXZ36CZI2QQA4","short_pith_number":"pith:DZFY33WW","canonical_record":{"source":{"id":"2407.00085","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-24T17:43:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2567774ebb4adefbc21a88825edd308b68ff5fd7b9844de7dac2f94757a34276","abstract_canon_sha256":"2cdafcf52b09d7f9220543b4614e5e63a0ae94f31526d8cbd4e9f2d0f6c1d9d4"},"schema_version":"1.0"},"canonical_sha256":"1e4b8deed6a6bc4e0af9df85946a10070c883ee9640f3f319d8afbba01662738","source":{"kind":"arxiv","id":"2407.00085","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00085","created_at":"2026-07-05T10:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00085v2","created_at":"2026-07-05T10:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00085","created_at":"2026-07-05T10:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"DZFY33WWU26E","created_at":"2026-07-05T10:46:55Z"},{"alias_kind":"pith_short_16","alias_value":"DZFY33WWU26E4CXZ","created_at":"2026-07-05T10:46:55Z"},{"alias_kind":"pith_short_8","alias_value":"DZFY33WW","created_at":"2026-07-05T10:46:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DZFY33WWU26E4CXZ36CZI2QQA4","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00085","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-24T17:43:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2567774ebb4adefbc21a88825edd308b68ff5fd7b9844de7dac2f94757a34276","abstract_canon_sha256":"2cdafcf52b09d7f9220543b4614e5e63a0ae94f31526d8cbd4e9f2d0f6c1d9d4"},"schema_version":"1.0"},"canonical_sha256":"1e4b8deed6a6bc4e0af9df85946a10070c883ee9640f3f319d8afbba01662738","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:55.707087Z","signature_b64":"K58CL5zuN4yqJYIkl8Os1tJtPGJpejl97rgo5ru6WHQt6ZX5Op6jqdKY/XBTvlv8HAJBDnJUofiwDWs+Kf7vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e4b8deed6a6bc4e0af9df85946a10070c883ee9640f3f319d8afbba01662738","last_reissued_at":"2026-07-05T10:46:55.706677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:55.706677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00085","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:46:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2a4l0MBAzPG341M7mAdXE+Og3s+6ZsJnW+N9iEioWoFNgKawNdZPtN0FTqbMPO2ca8o6BevPUG7nsl/nOJxHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:00:50.058830Z"},"content_sha256":"ddaca1d8a30b0a49020dca59a72bcabc4f032e440b4839e47f055370c9647182","schema_version":"1.0","event_id":"sha256:ddaca1d8a30b0a49020dca59a72bcabc4f032e440b4839e47f055370c9647182"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DZFY33WWU26E4CXZ36CZI2QQA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compressing Search with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Jennifer L. Steele, Thomas Mulc","submitted_at":"2024-06-24T17:43:49Z","abstract_excerpt":"Millions of people turn to Google Search each day for information on things as diverse as new cars or flu symptoms. The terms that they enter contain valuable information on their daily intent and activities, but the information in these search terms has been difficult to fully leverage. User-defined categorical filters have been the most common way to shrink the dimensionality of search data to a tractable size for analysis and modeling. In this paper we present a new approach to reducing the dimensionality of search data while retaining much of the information in the individual terms without"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00085","kind":"arxiv","version":2},"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/2407.00085/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":"2026-07-05T10:46:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zvPR7C2kpwgIW5wwVYwxySEbkfk9Q0jnYgmXzjTRFktpBTgy8idlEo9cIzGLH0vGSeDkYhkwDJ+BDnusqyepDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:00:50.059314Z"},"content_sha256":"7ee11cd40110e9b1bb0120bc1dd9bdd24bfc3c602f481a579870bb3b5dbe9ea4","schema_version":"1.0","event_id":"sha256:7ee11cd40110e9b1bb0120bc1dd9bdd24bfc3c602f481a579870bb3b5dbe9ea4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZFY33WWU26E4CXZ36CZI2QQA4/bundle.json","state_url":"https://pith.science/pith/DZFY33WWU26E4CXZ36CZI2QQA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZFY33WWU26E4CXZ36CZI2QQA4/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":"2026-08-10T00:00:50Z","links":{"resolver":"https://pith.science/pith/DZFY33WWU26E4CXZ36CZI2QQA4","bundle":"https://pith.science/pith/DZFY33WWU26E4CXZ36CZI2QQA4/bundle.json","state":"https://pith.science/pith/DZFY33WWU26E4CXZ36CZI2QQA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZFY33WWU26E4CXZ36CZI2QQA4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DZFY33WWU26E4CXZ36CZI2QQA4","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":"2cdafcf52b09d7f9220543b4614e5e63a0ae94f31526d8cbd4e9f2d0f6c1d9d4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-24T17:43:49Z","title_canon_sha256":"2567774ebb4adefbc21a88825edd308b68ff5fd7b9844de7dac2f94757a34276"},"schema_version":"1.0","source":{"id":"2407.00085","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00085","created_at":"2026-07-05T10:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00085v2","created_at":"2026-07-05T10:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00085","created_at":"2026-07-05T10:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"DZFY33WWU26E","created_at":"2026-07-05T10:46:55Z"},{"alias_kind":"pith_short_16","alias_value":"DZFY33WWU26E4CXZ","created_at":"2026-07-05T10:46:55Z"},{"alias_kind":"pith_short_8","alias_value":"DZFY33WW","created_at":"2026-07-05T10:46:55Z"}],"graph_snapshots":[{"event_id":"sha256:7ee11cd40110e9b1bb0120bc1dd9bdd24bfc3c602f481a579870bb3b5dbe9ea4","target":"graph","created_at":"2026-07-05T10:46:55Z","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/2407.00085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Millions of people turn to Google Search each day for information on things as diverse as new cars or flu symptoms. The terms that they enter contain valuable information on their daily intent and activities, but the information in these search terms has been difficult to fully leverage. User-defined categorical filters have been the most common way to shrink the dimensionality of search data to a tractable size for analysis and modeling. In this paper we present a new approach to reducing the dimensionality of search data while retaining much of the information in the individual terms without","authors_text":"Jennifer L. Steele, Thomas Mulc","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-24T17:43:49Z","title":"Compressing Search with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00085","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:ddaca1d8a30b0a49020dca59a72bcabc4f032e440b4839e47f055370c9647182","target":"record","created_at":"2026-07-05T10:46:55Z","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":"2cdafcf52b09d7f9220543b4614e5e63a0ae94f31526d8cbd4e9f2d0f6c1d9d4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-24T17:43:49Z","title_canon_sha256":"2567774ebb4adefbc21a88825edd308b68ff5fd7b9844de7dac2f94757a34276"},"schema_version":"1.0","source":{"id":"2407.00085","kind":"arxiv","version":2}},"canonical_sha256":"1e4b8deed6a6bc4e0af9df85946a10070c883ee9640f3f319d8afbba01662738","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e4b8deed6a6bc4e0af9df85946a10070c883ee9640f3f319d8afbba01662738","first_computed_at":"2026-07-05T10:46:55.706677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:55.706677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K58CL5zuN4yqJYIkl8Os1tJtPGJpejl97rgo5ru6WHQt6ZX5Op6jqdKY/XBTvlv8HAJBDnJUofiwDWs+Kf7vBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:55.707087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00085","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddaca1d8a30b0a49020dca59a72bcabc4f032e440b4839e47f055370c9647182","sha256:7ee11cd40110e9b1bb0120bc1dd9bdd24bfc3c602f481a579870bb3b5dbe9ea4"],"state_sha256":"1d0fe0dbd32230e7d9a5307d527ca9c15a8440eeb2c448113182d7b5d117841d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WfBJCtRnCevdeB7/O3yKziynlXVdczcz2bZoMpcA+dwH9Efgh2uWgTPFygGy9PkBtxu3R10vJoLiqXR5TBrNAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:00:50.062656Z","bundle_sha256":"941469d022276d9922199afbdd5d9064a8fa525a154b9eef52e2ff75a7729ce4"}}