{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RBHGQU5VIDVGTEJUCY2BJ665QC","short_pith_number":"pith:RBHGQU5V","schema_version":"1.0","canonical_sha256":"884e6853b540ea699134163414fbdd80b4571caedca2eddcaa6344a12e367cc8","source":{"kind":"arxiv","id":"2608.01704","version":1},"attestation_state":"computed","paper":{"title":"Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.IR","authors_text":"Kazuki Nakayashiki, Keisuke Watanabe","submitted_at":"2026-08-03T05:09:49Z","abstract_excerpt":"A benchmark score means nothing without knowing what a trivial method achieves and what the best possible method could achieve. We construct both bounds for a task with a rare kind of ground truth: predicting which sentences a crowd of readers -- highlighting for their own purposes, unpaid, uninstructed, and blind to each other -- marked in 120 web documents. The floor is naive truncation (lead); the ceiling is a split-half oracle: half the crowd predicting the other half. The gap between them is +0.2028 AP [+0.1698, +0.2342, domain-clustered], and three findings structure it. First, the gap i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.01704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-03T05:09:49Z","cross_cats_sorted":["cs.CL","cs.HC"],"title_canon_sha256":"da4a16f5f326c6fadde6238d420c7dc1bb7ef0a869d31e15504d6851a73f7b4d","abstract_canon_sha256":"a6f3c7ac36c1b3681193be35951bcdedd25b2df0e3dea5f5ed118943d789e9b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:06:31.349197Z","signature_b64":"YLiGxos0f8mS7RjB3+eGwmoy/NENAoAenBm1igsI5l6R+iH9WhaC8f02WhK8qEFUgo4/+6AeT9Qj2lBl2S5gDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"884e6853b540ea699134163414fbdd80b4571caedca2eddcaa6344a12e367cc8","last_reissued_at":"2026-08-04T02:06:31.347617Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:06:31.347617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.IR","authors_text":"Kazuki Nakayashiki, Keisuke Watanabe","submitted_at":"2026-08-03T05:09:49Z","abstract_excerpt":"A benchmark score means nothing without knowing what a trivial method achieves and what the best possible method could achieve. We construct both bounds for a task with a rare kind of ground truth: predicting which sentences a crowd of readers -- highlighting for their own purposes, unpaid, uninstructed, and blind to each other -- marked in 120 web documents. The floor is naive truncation (lead); the ceiling is a split-half oracle: half the crowd predicting the other half. The gap between them is +0.2028 AP [+0.1698, +0.2342, domain-clustered], and three findings structure it. First, the gap i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01704","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/2608.01704/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.01704","created_at":"2026-08-04T02:06:31.349118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01704v1","created_at":"2026-08-04T02:06:31.349118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01704","created_at":"2026-08-04T02:06:31.349118+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBHGQU5VIDVG","created_at":"2026-08-04T02:06:31.349118+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBHGQU5VIDVGTEJU","created_at":"2026-08-04T02:06:31.349118+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBHGQU5V","created_at":"2026-08-04T02:06:31.349118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBHGQU5VIDVGTEJUCY2BJ665QC","json":"https://pith.science/pith/RBHGQU5VIDVGTEJUCY2BJ665QC.json","graph_json":"https://pith.science/api/pith-number/RBHGQU5VIDVGTEJUCY2BJ665QC/graph.json","events_json":"https://pith.science/api/pith-number/RBHGQU5VIDVGTEJUCY2BJ665QC/events.json","paper":"https://pith.science/paper/RBHGQU5V"},"agent_actions":{"view_html":"https://pith.science/pith/RBHGQU5VIDVGTEJUCY2BJ665QC","download_json":"https://pith.science/pith/RBHGQU5VIDVGTEJUCY2BJ665QC.json","view_paper":"https://pith.science/paper/RBHGQU5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01704&json=true","fetch_graph":"https://pith.science/api/pith-number/RBHGQU5VIDVGTEJUCY2BJ665QC/graph.json","fetch_events":"https://pith.science/api/pith-number/RBHGQU5VIDVGTEJUCY2BJ665QC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBHGQU5VIDVGTEJUCY2BJ665QC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBHGQU5VIDVGTEJUCY2BJ665QC/action/storage_attestation","attest_author":"https://pith.science/pith/RBHGQU5VIDVGTEJUCY2BJ665QC/action/author_attestation","sign_citation":"https://pith.science/pith/RBHGQU5VIDVGTEJUCY2BJ665QC/action/citation_signature","submit_replication":"https://pith.science/pith/RBHGQU5VIDVGTEJUCY2BJ665QC/action/replication_record"}},"created_at":"2026-08-04T02:06:31.349118+00:00","updated_at":"2026-08-04T02:06:31.349118+00:00"}