{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AQNGG43AKDZP5AKSKULOWX5QIA","short_pith_number":"pith:AQNGG43A","schema_version":"1.0","canonical_sha256":"041a63736050f2fe81525516eb5fb0401db3584a653641c51113dc5fd94c9c9c","source":{"kind":"arxiv","id":"2606.11654","version":1},"attestation_state":"computed","paper":{"title":"The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.SI"],"primary_cat":"cs.IR","authors_text":"Kazuki Nakayashiki, Keisuke Watanabe","submitted_at":"2026-06-10T04:37:23Z","abstract_excerpt":"A social highlighter's most useful signal -- which passages a crowd of readers marks -- exists only for documents people have already read. Can the aggregate crowd salience of a document be predicted from its text before its marks accumulate? Prior work on this data found that zero-shot language models recover highlight locations worse than a trivial lead (position) baseline, so we ask whether a model trained on the highlight corpus can beat that baseline. Using a pre-registered ladder of models and a by-document cluster bootstrap, we find a small but robust edge: a logistic ranker over senten"},"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":"2606.11654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-10T04:37:23Z","cross_cats_sorted":["cs.CL","cs.HC","cs.SI"],"title_canon_sha256":"54051240e9eb4e396019d59010281e081b5a9491907cf60a39db9e7a9ca6db6f","abstract_canon_sha256":"c4b88125b25fa5d9542da4a20a1e0a8fea714b749a2826ab9bb626227b0608af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:01.157861Z","signature_b64":"fHtq5g+1xKHEHhNGU4RcZ5DOw6OY96eRCiy0eKYdfHi8aIr1OPjzo2clze//6MMEf0ooKy88oYsg1hlGWeNLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"041a63736050f2fe81525516eb5fb0401db3584a653641c51113dc5fd94c9c9c","last_reissued_at":"2026-06-11T01:10:01.157058Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:01.157058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.SI"],"primary_cat":"cs.IR","authors_text":"Kazuki Nakayashiki, Keisuke Watanabe","submitted_at":"2026-06-10T04:37:23Z","abstract_excerpt":"A social highlighter's most useful signal -- which passages a crowd of readers marks -- exists only for documents people have already read. Can the aggregate crowd salience of a document be predicted from its text before its marks accumulate? Prior work on this data found that zero-shot language models recover highlight locations worse than a trivial lead (position) baseline, so we ask whether a model trained on the highlight corpus can beat that baseline. Using a pre-registered ladder of models and a by-document cluster bootstrap, we find a small but robust edge: a logistic ranker over senten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11654","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/2606.11654/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":"2606.11654","created_at":"2026-06-11T01:10:01.157160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11654v1","created_at":"2026-06-11T01:10:01.157160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11654","created_at":"2026-06-11T01:10:01.157160+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQNGG43AKDZP","created_at":"2026-06-11T01:10:01.157160+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQNGG43AKDZP5AKS","created_at":"2026-06-11T01:10:01.157160+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQNGG43A","created_at":"2026-06-11T01:10:01.157160+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/AQNGG43AKDZP5AKSKULOWX5QIA","json":"https://pith.science/pith/AQNGG43AKDZP5AKSKULOWX5QIA.json","graph_json":"https://pith.science/api/pith-number/AQNGG43AKDZP5AKSKULOWX5QIA/graph.json","events_json":"https://pith.science/api/pith-number/AQNGG43AKDZP5AKSKULOWX5QIA/events.json","paper":"https://pith.science/paper/AQNGG43A"},"agent_actions":{"view_html":"https://pith.science/pith/AQNGG43AKDZP5AKSKULOWX5QIA","download_json":"https://pith.science/pith/AQNGG43AKDZP5AKSKULOWX5QIA.json","view_paper":"https://pith.science/paper/AQNGG43A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11654&json=true","fetch_graph":"https://pith.science/api/pith-number/AQNGG43AKDZP5AKSKULOWX5QIA/graph.json","fetch_events":"https://pith.science/api/pith-number/AQNGG43AKDZP5AKSKULOWX5QIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQNGG43AKDZP5AKSKULOWX5QIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQNGG43AKDZP5AKSKULOWX5QIA/action/storage_attestation","attest_author":"https://pith.science/pith/AQNGG43AKDZP5AKSKULOWX5QIA/action/author_attestation","sign_citation":"https://pith.science/pith/AQNGG43AKDZP5AKSKULOWX5QIA/action/citation_signature","submit_replication":"https://pith.science/pith/AQNGG43AKDZP5AKSKULOWX5QIA/action/replication_record"}},"created_at":"2026-06-11T01:10:01.157160+00:00","updated_at":"2026-06-11T01:10:01.157160+00:00"}