{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SYTFBG3VXJXZVW2MMZVBYF7EV3","short_pith_number":"pith:SYTFBG3V","canonical_record":{"source":{"id":"2412.10701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-14T06:18:19Z","cross_cats_sorted":[],"title_canon_sha256":"07ff344c27cec0ab5fc58de2b81ce185e654d0e814fda7c6c9c122fa884cae3a","abstract_canon_sha256":"75746ca53e7a12e1d77509df50e22fdbab9d2dab0e946d4d7f07ca83bd1be747"},"schema_version":"1.0"},"canonical_sha256":"9626509b75ba6f9adb4c666a1c17e4aee3d65d38e1e38a4782d171c120c54428","source":{"kind":"arxiv","id":"2412.10701","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10701","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10701v1","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10701","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"SYTFBG3VXJXZ","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"SYTFBG3VXJXZVW2M","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"SYTFBG3V","created_at":"2026-07-05T09:49:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SYTFBG3VXJXZVW2MMZVBYF7EV3","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-14T06:18:19Z","cross_cats_sorted":[],"title_canon_sha256":"07ff344c27cec0ab5fc58de2b81ce185e654d0e814fda7c6c9c122fa884cae3a","abstract_canon_sha256":"75746ca53e7a12e1d77509df50e22fdbab9d2dab0e946d4d7f07ca83bd1be747"},"schema_version":"1.0"},"canonical_sha256":"9626509b75ba6f9adb4c666a1c17e4aee3d65d38e1e38a4782d171c120c54428","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:20.068279Z","signature_b64":"5nCKOcwwSbo4oBhXDhB7W+4e4m3EZFuuotlNhHqJFjg07cq010V04ExHHDPnWrzn7algq1tLr+jEUdbf6kR+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9626509b75ba6f9adb4c666a1c17e4aee3d65d38e1e38a4782d171c120c54428","last_reissued_at":"2026-07-05T09:49:20.067843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:20.067843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10701","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":"2026-07-05T09:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yY0pNATNQJ6ItJlV+nXF6sM7lQZGcSUdqes4LcLSGePPYf9XNiaX4sMlRmw0LRDwTJAoobJwEr3STqXmi5RVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T05:59:38.220844Z"},"content_sha256":"4bcdc91c56d8d6e4db1f8e5965e828889ab45a5240b148543a27b134b338e640","schema_version":"1.0","event_id":"sha256:4bcdc91c56d8d6e4db1f8e5965e828889ab45a5240b148543a27b134b338e640"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SYTFBG3VXJXZVW2MMZVBYF7EV3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Quantile Methods: Improved Top-K Threshold Estimation for Traditional and Learned Sparse Indexes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jinrui Gou, Minghao Shao, Torsten Suel, Yifan Liu","submitted_at":"2024-12-14T06:18:19Z","abstract_excerpt":"Top-k threshold estimation is the problem of estimating the score of the k-th highest ranking result of a search query. A good estimate can be used to speed up many common top-k query processing algorithms, and thus a number of researchers have recently studied the problem. Among the various approaches that have been proposed, quantile methods appear to give the best estimates overall at modest computational costs, followed by sampling-based methods in certain cases. In this paper, we make two main contributions. First, we study how to get even better estimates than the state of the art. Start"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10701","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/2412.10701/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":"2026-07-05T09:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4+0G5h9xVDw5QNm9PJOUuORGvQRhWH0vKlIjMpr7q8gfCv9oPuedVw/4h54gWOKwKPOKEfJLMkR7uyFwq6ZBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T05:59:38.221329Z"},"content_sha256":"8ad58ff628fee3b1cf056d1c97de2490b9308d47d0048fe51da5dfe752448138","schema_version":"1.0","event_id":"sha256:8ad58ff628fee3b1cf056d1c97de2490b9308d47d0048fe51da5dfe752448138"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYTFBG3VXJXZVW2MMZVBYF7EV3/bundle.json","state_url":"https://pith.science/pith/SYTFBG3VXJXZVW2MMZVBYF7EV3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYTFBG3VXJXZVW2MMZVBYF7EV3/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":"2026-08-20T05:59:38Z","links":{"resolver":"https://pith.science/pith/SYTFBG3VXJXZVW2MMZVBYF7EV3","bundle":"https://pith.science/pith/SYTFBG3VXJXZVW2MMZVBYF7EV3/bundle.json","state":"https://pith.science/pith/SYTFBG3VXJXZVW2MMZVBYF7EV3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYTFBG3VXJXZVW2MMZVBYF7EV3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SYTFBG3VXJXZVW2MMZVBYF7EV3","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":"75746ca53e7a12e1d77509df50e22fdbab9d2dab0e946d4d7f07ca83bd1be747","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-14T06:18:19Z","title_canon_sha256":"07ff344c27cec0ab5fc58de2b81ce185e654d0e814fda7c6c9c122fa884cae3a"},"schema_version":"1.0","source":{"id":"2412.10701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10701","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10701v1","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10701","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"SYTFBG3VXJXZ","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"SYTFBG3VXJXZVW2M","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"SYTFBG3V","created_at":"2026-07-05T09:49:20Z"}],"graph_snapshots":[{"event_id":"sha256:8ad58ff628fee3b1cf056d1c97de2490b9308d47d0048fe51da5dfe752448138","target":"graph","created_at":"2026-07-05T09:49:20Z","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/2412.10701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Top-k threshold estimation is the problem of estimating the score of the k-th highest ranking result of a search query. A good estimate can be used to speed up many common top-k query processing algorithms, and thus a number of researchers have recently studied the problem. Among the various approaches that have been proposed, quantile methods appear to give the best estimates overall at modest computational costs, followed by sampling-based methods in certain cases. In this paper, we make two main contributions. First, we study how to get even better estimates than the state of the art. Start","authors_text":"Jinrui Gou, Minghao Shao, Torsten Suel, Yifan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-14T06:18:19Z","title":"Beyond Quantile Methods: Improved Top-K Threshold Estimation for Traditional and Learned Sparse Indexes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10701","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":"sha256:4bcdc91c56d8d6e4db1f8e5965e828889ab45a5240b148543a27b134b338e640","target":"record","created_at":"2026-07-05T09:49:20Z","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":"75746ca53e7a12e1d77509df50e22fdbab9d2dab0e946d4d7f07ca83bd1be747","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-14T06:18:19Z","title_canon_sha256":"07ff344c27cec0ab5fc58de2b81ce185e654d0e814fda7c6c9c122fa884cae3a"},"schema_version":"1.0","source":{"id":"2412.10701","kind":"arxiv","version":1}},"canonical_sha256":"9626509b75ba6f9adb4c666a1c17e4aee3d65d38e1e38a4782d171c120c54428","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9626509b75ba6f9adb4c666a1c17e4aee3d65d38e1e38a4782d171c120c54428","first_computed_at":"2026-07-05T09:49:20.067843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:20.067843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5nCKOcwwSbo4oBhXDhB7W+4e4m3EZFuuotlNhHqJFjg07cq010V04ExHHDPnWrzn7algq1tLr+jEUdbf6kR+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:20.068279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bcdc91c56d8d6e4db1f8e5965e828889ab45a5240b148543a27b134b338e640","sha256:8ad58ff628fee3b1cf056d1c97de2490b9308d47d0048fe51da5dfe752448138"],"state_sha256":"3692eadf7ccd4885dcc642c2ea7c221d4cc6d465790c40aba78c3b367207fd4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PhdY+s+w47n0Lsx8h47LazktrdsI1Il8vVT9Z7JfomLxve3Vrx76v9+7ntAZdBc39EVkuYYMSOHIPz4H8Pe9BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T05:59:38.225246Z","bundle_sha256":"33103c05d32fcfca443253fa398fdb2ea447a493d9168d541b3eb4e25401fc52"}}