{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DRBMGR6CGXMS6GQO5WKDFEDG4R","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":"e96a04bea25270c6478b3f2cee7aadbfa63619ff0e2e4b71b80773127d95aed7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-13T10:24:54Z","title_canon_sha256":"bdd1a59e33d37673bef0d3c0110ba23cc7f3aeab2b62f3cff62bc86c7537449c"},"schema_version":"1.0","source":{"id":"2112.06540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06540","created_at":"2026-07-05T03:40:14Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06540v1","created_at":"2026-07-05T03:40:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06540","created_at":"2026-07-05T03:40:14Z"},{"alias_kind":"pith_short_12","alias_value":"DRBMGR6CGXMS","created_at":"2026-07-05T03:40:14Z"},{"alias_kind":"pith_short_16","alias_value":"DRBMGR6CGXMS6GQO","created_at":"2026-07-05T03:40:14Z"},{"alias_kind":"pith_short_8","alias_value":"DRBMGR6C","created_at":"2026-07-05T03:40:14Z"}],"graph_snapshots":[{"event_id":"sha256:9e5e5daf71c782e37a2fcc93cca233a43780e53e7e1d555960132c7cf27ee680","target":"graph","created_at":"2026-07-05T03:40:14Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.06540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ColBERT model has recently been proposed as an effective BERT based ranker. By adopting a late interaction mechanism, a major advantage of ColBERT is that document representations can be precomputed in advance. However, the big downside of the model is the index size, which scales linearly with the number of tokens in the collection. In this paper, we study various designs for ColBERT models in order to attack this problem. While compression techniques have been explored to reduce the index size, in this paper we study token pruning techniques for ColBERT. We compare simple heuristics, as ","authors_text":"Carlos Lassance, Joohee Park, Maroua Maachou, St\\'ephane Clinchant","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-13T10:24:54Z","title":"A Study on Token Pruning for ColBERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06540","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:cf50a313698969d83f4dd8a3f0e4e1f316793e128abb5f45c3a9806ff288dea7","target":"record","created_at":"2026-07-05T03:40:14Z","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":"e96a04bea25270c6478b3f2cee7aadbfa63619ff0e2e4b71b80773127d95aed7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-13T10:24:54Z","title_canon_sha256":"bdd1a59e33d37673bef0d3c0110ba23cc7f3aeab2b62f3cff62bc86c7537449c"},"schema_version":"1.0","source":{"id":"2112.06540","kind":"arxiv","version":1}},"canonical_sha256":"1c42c347c235d92f1a0eed94329066e475571d91c5b6e03d54494a0732308ad1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c42c347c235d92f1a0eed94329066e475571d91c5b6e03d54494a0732308ad1","first_computed_at":"2026-07-05T03:40:14.743431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:14.743431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yy/yFexgwUYrx0QpbvqABR1c4utkvj+zUbyZRFSyk0dzIy0bw9uEuE/6ZtyzSpfQRUPXFezXf1Tb+f47oxZ5Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:14.743860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.06540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf50a313698969d83f4dd8a3f0e4e1f316793e128abb5f45c3a9806ff288dea7","sha256:9e5e5daf71c782e37a2fcc93cca233a43780e53e7e1d555960132c7cf27ee680"],"state_sha256":"f3fca74c7faca9c1babdbbfd9d1d0bb7e5b1e693586b0a71b0077ca7c7912fdd"}