{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BYUKVK5CPEQAJZ7VBC754HUQYQ","short_pith_number":"pith:BYUKVK5C","canonical_record":{"source":{"id":"1711.06004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-11-16T09:50:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"27e9bcc1598bc36343015995aeee264c9d402c451f3305ac5bf701d66b621ea9","abstract_canon_sha256":"e55a910a8453de93fb259686218bf399158ad77920ed8b5b72a54eb7d436c9c7"},"schema_version":"1.0"},"canonical_sha256":"0e28aaaba2792004e7f508bfde1e90c406cac6526158dd4f99e0bef89c5571c7","source":{"kind":"arxiv","id":"1711.06004","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.06004","created_at":"2026-05-18T00:30:23Z"},{"alias_kind":"arxiv_version","alias_value":"1711.06004v1","created_at":"2026-05-18T00:30:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06004","created_at":"2026-05-18T00:30:23Z"},{"alias_kind":"pith_short_12","alias_value":"BYUKVK5CPEQA","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BYUKVK5CPEQAJZ7V","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BYUKVK5C","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BYUKVK5CPEQAJZ7VBC754HUQYQ","target":"record","payload":{"canonical_record":{"source":{"id":"1711.06004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-11-16T09:50:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"27e9bcc1598bc36343015995aeee264c9d402c451f3305ac5bf701d66b621ea9","abstract_canon_sha256":"e55a910a8453de93fb259686218bf399158ad77920ed8b5b72a54eb7d436c9c7"},"schema_version":"1.0"},"canonical_sha256":"0e28aaaba2792004e7f508bfde1e90c406cac6526158dd4f99e0bef89c5571c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:23.576252Z","signature_b64":"jao+29vbxmPECdyihFCXFJQ5jAXQyTC1XVjpV6VmYdQB+QzKyP2H2pweGrTRs4eR1JCNhU2cp1uZLwpqAofhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e28aaaba2792004e7f508bfde1e90c406cac6526158dd4f99e0bef89c5571c7","last_reissued_at":"2026-05-18T00:30:23.575635Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:23.575635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.06004","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":"2026-05-18T00:30:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ja35p5mcHPRgnXIAyRkQ5geIyUIfM5d6J+wjlNg9kQ2b2zrMUTeFwguyhb3klts/g6wSyAUSF7iYzGCqhW0cCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T05:37:22.627489Z"},"content_sha256":"8992d4740b3f4f3958a950987463a15ac5995d1aa43e4e2e00825ece560060b8","schema_version":"1.0","event_id":"sha256:8992d4740b3f4f3958a950987463a15ac5995d1aa43e4e2e00825ece560060b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BYUKVK5CPEQAJZ7VBC754HUQYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Remedies against the Vocabulary Gap in Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Christophe Van Gysel","submitted_at":"2017-11-16T09:50:52Z","abstract_excerpt":"Search engines rely heavily on term-based approaches that represent queries and documents as bags of words. Text---a document or a query---is represented by a bag of its words that ignores grammar and word order, but retains word frequency counts. When presented with a search query, the engine then ranks documents according to their relevance scores by computing, among other things, the matching degrees between query and document terms. While term-based approaches are intuitive and effective in practice, they are based on the hypothesis that documents that exactly contain the query terms are h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06004","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZZNd6H3Y/+vP8rf3+KoVChKpV84+qfF02mK98Pt8g17hEld3qw4PKr420uWq0BINY3JQ4RVztJDirke+T6X1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T05:37:22.627824Z"},"content_sha256":"ea8f768fc676ec66a6eefb08cab8dfe402fda8be38f3bab6b6b90dab513af2e6","schema_version":"1.0","event_id":"sha256:ea8f768fc676ec66a6eefb08cab8dfe402fda8be38f3bab6b6b90dab513af2e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYUKVK5CPEQAJZ7VBC754HUQYQ/bundle.json","state_url":"https://pith.science/pith/BYUKVK5CPEQAJZ7VBC754HUQYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYUKVK5CPEQAJZ7VBC754HUQYQ/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":"2026-06-27T05:37:22Z","links":{"resolver":"https://pith.science/pith/BYUKVK5CPEQAJZ7VBC754HUQYQ","bundle":"https://pith.science/pith/BYUKVK5CPEQAJZ7VBC754HUQYQ/bundle.json","state":"https://pith.science/pith/BYUKVK5CPEQAJZ7VBC754HUQYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYUKVK5CPEQAJZ7VBC754HUQYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BYUKVK5CPEQAJZ7VBC754HUQYQ","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":"e55a910a8453de93fb259686218bf399158ad77920ed8b5b72a54eb7d436c9c7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-11-16T09:50:52Z","title_canon_sha256":"27e9bcc1598bc36343015995aeee264c9d402c451f3305ac5bf701d66b621ea9"},"schema_version":"1.0","source":{"id":"1711.06004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.06004","created_at":"2026-05-18T00:30:23Z"},{"alias_kind":"arxiv_version","alias_value":"1711.06004v1","created_at":"2026-05-18T00:30:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06004","created_at":"2026-05-18T00:30:23Z"},{"alias_kind":"pith_short_12","alias_value":"BYUKVK5CPEQA","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BYUKVK5CPEQAJZ7V","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BYUKVK5C","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:ea8f768fc676ec66a6eefb08cab8dfe402fda8be38f3bab6b6b90dab513af2e6","target":"graph","created_at":"2026-05-18T00:30:23Z","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"},"paper":{"abstract_excerpt":"Search engines rely heavily on term-based approaches that represent queries and documents as bags of words. Text---a document or a query---is represented by a bag of its words that ignores grammar and word order, but retains word frequency counts. When presented with a search query, the engine then ranks documents according to their relevance scores by computing, among other things, the matching degrees between query and document terms. While term-based approaches are intuitive and effective in practice, they are based on the hypothesis that documents that exactly contain the query terms are h","authors_text":"Christophe Van Gysel","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-11-16T09:50:52Z","title":"Remedies against the Vocabulary Gap in Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06004","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":"sha256:8992d4740b3f4f3958a950987463a15ac5995d1aa43e4e2e00825ece560060b8","target":"record","created_at":"2026-05-18T00:30:23Z","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":"e55a910a8453de93fb259686218bf399158ad77920ed8b5b72a54eb7d436c9c7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-11-16T09:50:52Z","title_canon_sha256":"27e9bcc1598bc36343015995aeee264c9d402c451f3305ac5bf701d66b621ea9"},"schema_version":"1.0","source":{"id":"1711.06004","kind":"arxiv","version":1}},"canonical_sha256":"0e28aaaba2792004e7f508bfde1e90c406cac6526158dd4f99e0bef89c5571c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e28aaaba2792004e7f508bfde1e90c406cac6526158dd4f99e0bef89c5571c7","first_computed_at":"2026-05-18T00:30:23.575635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:23.575635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jao+29vbxmPECdyihFCXFJQ5jAXQyTC1XVjpV6VmYdQB+QzKyP2H2pweGrTRs4eR1JCNhU2cp1uZLwpqAofhAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:23.576252Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.06004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8992d4740b3f4f3958a950987463a15ac5995d1aa43e4e2e00825ece560060b8","sha256:ea8f768fc676ec66a6eefb08cab8dfe402fda8be38f3bab6b6b90dab513af2e6"],"state_sha256":"1f88f059bc58ad9320d7e2f68554f24a6319cb7171dd35578c07cfd6483bd746"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f2YA1ElOihk2wi7s0ZjAjpyv7FS89nXYWR8puuFCqM5TpzDyTgzLLwk87NyfkbbeeuZ095sWqUfgjCKcZeybBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T05:37:22.629657Z","bundle_sha256":"2cdc330e2f4057d4be9bf9b4f0c498aaf6879553432c653f9acfe5152f703b27"}}