{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3AM5LGCA5TUJ7TAGPQKL5P6XUR","short_pith_number":"pith:3AM5LGCA","schema_version":"1.0","canonical_sha256":"d819d59840ece89fcc067c14bebfd7a45b6e56248fc3ac6e6e300e30feedbb79","source":{"kind":"arxiv","id":"2505.21058","version":1},"attestation_state":"computed","paper":{"title":"Disentangling Locality and Entropy in Ranking Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Parry, Debasis Ganguly, Sean MacAvaney","submitted_at":"2025-05-27T11:46:37Z","abstract_excerpt":"The training process of ranking models involves two key data selection decisions: a sampling strategy, and a labeling strategy. Modern ranking systems, especially those for performing semantic search, typically use a ``hard negative'' sampling strategy to identify challenging items using heuristics and a distillation labeling strategy to transfer ranking \"knowledge\" from a more capable model. In practice, these approaches have grown increasingly expensive and complex, for instance, popular pretrained rankers from SentenceTransformers involve 12 models in an ensemble with data provenance hamper"},"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":"2505.21058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-27T11:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"b9f71a9e01ad0166d59e6b3a260ad723f75c0f3ca7664d7f178fd9634ad8485e","abstract_canon_sha256":"f44dcad786e7197e83a5787f1b180fac6b290619aa8468b004f40e9278eb7213"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:23.006965Z","signature_b64":"WbPc4TFIjHT7OpyQNp0ap7K1KtoLAKRT4BfZP9dM7+J5MYIJpMrI8PtF/sh7tXBdBb+7qlTxSR1hRsu7m05LAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d819d59840ece89fcc067c14bebfd7a45b6e56248fc3ac6e6e300e30feedbb79","last_reissued_at":"2026-07-05T11:10:23.006477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:23.006477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Locality and Entropy in Ranking Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Parry, Debasis Ganguly, Sean MacAvaney","submitted_at":"2025-05-27T11:46:37Z","abstract_excerpt":"The training process of ranking models involves two key data selection decisions: a sampling strategy, and a labeling strategy. Modern ranking systems, especially those for performing semantic search, typically use a ``hard negative'' sampling strategy to identify challenging items using heuristics and a distillation labeling strategy to transfer ranking \"knowledge\" from a more capable model. In practice, these approaches have grown increasingly expensive and complex, for instance, popular pretrained rankers from SentenceTransformers involve 12 models in an ensemble with data provenance hamper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21058","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/2505.21058/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":"2505.21058","created_at":"2026-07-05T11:10:23.006537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21058v1","created_at":"2026-07-05T11:10:23.006537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21058","created_at":"2026-07-05T11:10:23.006537+00:00"},{"alias_kind":"pith_short_12","alias_value":"3AM5LGCA5TUJ","created_at":"2026-07-05T11:10:23.006537+00:00"},{"alias_kind":"pith_short_16","alias_value":"3AM5LGCA5TUJ7TAG","created_at":"2026-07-05T11:10:23.006537+00:00"},{"alias_kind":"pith_short_8","alias_value":"3AM5LGCA","created_at":"2026-07-05T11:10:23.006537+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/3AM5LGCA5TUJ7TAGPQKL5P6XUR","json":"https://pith.science/pith/3AM5LGCA5TUJ7TAGPQKL5P6XUR.json","graph_json":"https://pith.science/api/pith-number/3AM5LGCA5TUJ7TAGPQKL5P6XUR/graph.json","events_json":"https://pith.science/api/pith-number/3AM5LGCA5TUJ7TAGPQKL5P6XUR/events.json","paper":"https://pith.science/paper/3AM5LGCA"},"agent_actions":{"view_html":"https://pith.science/pith/3AM5LGCA5TUJ7TAGPQKL5P6XUR","download_json":"https://pith.science/pith/3AM5LGCA5TUJ7TAGPQKL5P6XUR.json","view_paper":"https://pith.science/paper/3AM5LGCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21058&json=true","fetch_graph":"https://pith.science/api/pith-number/3AM5LGCA5TUJ7TAGPQKL5P6XUR/graph.json","fetch_events":"https://pith.science/api/pith-number/3AM5LGCA5TUJ7TAGPQKL5P6XUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3AM5LGCA5TUJ7TAGPQKL5P6XUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3AM5LGCA5TUJ7TAGPQKL5P6XUR/action/storage_attestation","attest_author":"https://pith.science/pith/3AM5LGCA5TUJ7TAGPQKL5P6XUR/action/author_attestation","sign_citation":"https://pith.science/pith/3AM5LGCA5TUJ7TAGPQKL5P6XUR/action/citation_signature","submit_replication":"https://pith.science/pith/3AM5LGCA5TUJ7TAGPQKL5P6XUR/action/replication_record"}},"created_at":"2026-07-05T11:10:23.006537+00:00","updated_at":"2026-07-05T11:10:23.006537+00:00"}