{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:CBQLQ7DHSRVXEJJCKDSIA7J67E","short_pith_number":"pith:CBQLQ7DH","schema_version":"1.0","canonical_sha256":"1060b87c67946b72252250e4807d3ef91b7f17903e49289027833c3e04ab7c3b","source":{"kind":"arxiv","id":"1507.08198","version":1},"attestation_state":"computed","paper":{"title":"Non-Compositional Term Dependence for Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Birger Larsen, Christina Lioma, Jakob Grue Simonsen, Niels Dalum Hansen","submitted_at":"2015-07-29T16:08:48Z","abstract_excerpt":"Modelling term dependence in IR aims to identify co-occurring terms that are too heavily dependent on each other to be treated as a bag of words, and to adapt the indexing and ranking accordingly. Dependent terms are predominantly identified using lexical frequency statistics, assuming that (a) if terms co-occur often enough in some corpus, they are semantically dependent; (b) the more often they co-occur, the more semantically dependent they are. This assumption is not always correct: the frequency of co-occurring terms can be separate from the strength of their semantic dependence. E.g. \"red"},"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":"1507.08198","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-07-29T16:08:48Z","cross_cats_sorted":[],"title_canon_sha256":"bba9d4e37316052fa5dab789cbc595ca761b0048a2deb2d863af01cdb2a59eec","abstract_canon_sha256":"33fcb00c669a842523d5ce62ccdcf77e6d38426ba8ca07b59c9751b8fa804b9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:01.307344Z","signature_b64":"zx/NNcEgsIowUNXHldgKAIYeDocOsG0LspM4Dzq30mvzuXrR3rQuRhhckYVaem+D5mcVxlBOm2e/yCExijVnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1060b87c67946b72252250e4807d3ef91b7f17903e49289027833c3e04ab7c3b","last_reissued_at":"2026-05-18T01:01:01.306586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:01.306586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Compositional Term Dependence for Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Birger Larsen, Christina Lioma, Jakob Grue Simonsen, Niels Dalum Hansen","submitted_at":"2015-07-29T16:08:48Z","abstract_excerpt":"Modelling term dependence in IR aims to identify co-occurring terms that are too heavily dependent on each other to be treated as a bag of words, and to adapt the indexing and ranking accordingly. Dependent terms are predominantly identified using lexical frequency statistics, assuming that (a) if terms co-occur often enough in some corpus, they are semantically dependent; (b) the more often they co-occur, the more semantically dependent they are. This assumption is not always correct: the frequency of co-occurring terms can be separate from the strength of their semantic dependence. E.g. \"red"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08198","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":""},"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":"1507.08198","created_at":"2026-05-18T01:01:01.306711+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.08198v1","created_at":"2026-05-18T01:01:01.306711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08198","created_at":"2026-05-18T01:01:01.306711+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBQLQ7DHSRVX","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBQLQ7DHSRVXEJJC","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBQLQ7DH","created_at":"2026-05-18T12:29:14.074870+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/CBQLQ7DHSRVXEJJCKDSIA7J67E","json":"https://pith.science/pith/CBQLQ7DHSRVXEJJCKDSIA7J67E.json","graph_json":"https://pith.science/api/pith-number/CBQLQ7DHSRVXEJJCKDSIA7J67E/graph.json","events_json":"https://pith.science/api/pith-number/CBQLQ7DHSRVXEJJCKDSIA7J67E/events.json","paper":"https://pith.science/paper/CBQLQ7DH"},"agent_actions":{"view_html":"https://pith.science/pith/CBQLQ7DHSRVXEJJCKDSIA7J67E","download_json":"https://pith.science/pith/CBQLQ7DHSRVXEJJCKDSIA7J67E.json","view_paper":"https://pith.science/paper/CBQLQ7DH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.08198&json=true","fetch_graph":"https://pith.science/api/pith-number/CBQLQ7DHSRVXEJJCKDSIA7J67E/graph.json","fetch_events":"https://pith.science/api/pith-number/CBQLQ7DHSRVXEJJCKDSIA7J67E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBQLQ7DHSRVXEJJCKDSIA7J67E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBQLQ7DHSRVXEJJCKDSIA7J67E/action/storage_attestation","attest_author":"https://pith.science/pith/CBQLQ7DHSRVXEJJCKDSIA7J67E/action/author_attestation","sign_citation":"https://pith.science/pith/CBQLQ7DHSRVXEJJCKDSIA7J67E/action/citation_signature","submit_replication":"https://pith.science/pith/CBQLQ7DHSRVXEJJCKDSIA7J67E/action/replication_record"}},"created_at":"2026-05-18T01:01:01.306711+00:00","updated_at":"2026-05-18T01:01:01.306711+00:00"}