{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NROAGGSPD5IJDNJLE6KGEYOJDG","short_pith_number":"pith:NROAGGSP","canonical_record":{"source":{"id":"2411.12921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-19T23:19:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba1183f5a2346d0f0f3c07d0c5ac30fe1dadbd5ffa638546f911c4164d022a0e","abstract_canon_sha256":"a9ff4d5fafb516048a406045181bba48ed2b212ea34fbcc7934e9b50f9e12697"},"schema_version":"1.0"},"canonical_sha256":"6c5c031a4f1f5091b52b27946261c919abeafb1cc54ad273c6dd998912524df4","source":{"kind":"arxiv","id":"2411.12921","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12921","created_at":"2026-07-05T09:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12921v2","created_at":"2026-07-05T09:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12921","created_at":"2026-07-05T09:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"NROAGGSPD5IJ","created_at":"2026-07-05T09:52:40Z"},{"alias_kind":"pith_short_16","alias_value":"NROAGGSPD5IJDNJL","created_at":"2026-07-05T09:52:40Z"},{"alias_kind":"pith_short_8","alias_value":"NROAGGSP","created_at":"2026-07-05T09:52:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NROAGGSPD5IJDNJLE6KGEYOJDG","target":"record","payload":{"canonical_record":{"source":{"id":"2411.12921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-19T23:19:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba1183f5a2346d0f0f3c07d0c5ac30fe1dadbd5ffa638546f911c4164d022a0e","abstract_canon_sha256":"a9ff4d5fafb516048a406045181bba48ed2b212ea34fbcc7934e9b50f9e12697"},"schema_version":"1.0"},"canonical_sha256":"6c5c031a4f1f5091b52b27946261c919abeafb1cc54ad273c6dd998912524df4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:40.475327Z","signature_b64":"sAV9xZxESh7FvjuEuqI2NvGN8wbN2DYxIRu2Ge/RPoWdJ+D8oUqhb7VzQ2M+nrpQbm1BhJu+3FaCvUa52DPaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c5c031a4f1f5091b52b27946261c919abeafb1cc54ad273c6dd998912524df4","last_reissued_at":"2026-07-05T09:52:40.474881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:40.474881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.12921","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ut5+nRgxvx+n0lMbGAfpFQVPfs8SztJ4GELvg7AFKMPeukjc9nFNlM8TACOXYEu01UGF7GOlHlMowZTK7NGLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:02:31.938549Z"},"content_sha256":"a476b960d736d607730cf6484f31c1c1119c1164c94d6323e67a4544ac159084","schema_version":"1.0","event_id":"sha256:a476b960d736d607730cf6484f31c1c1119c1164c94d6323e67a4544ac159084"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NROAGGSPD5IJDNJLE6KGEYOJDG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study of Text Retrieval Models on DaReCzech","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jakub Stetina, Martin Fajcik, Michal Hradis, Michal Stefanik","submitted_at":"2024-11-19T23:19:46Z","abstract_excerpt":"This article presents a comprehensive evaluation of 7 off-the-shelf document retrieval models: Splade, Plaid, Plaid-X, SimCSE, Contriever, OpenAI ADA and Gemma2 chosen to determine their performance on the Czech retrieval dataset DaReCzech. The primary objective of our experiments is to estimate the quality of modern retrieval approaches in the Czech language. Our analyses include retrieval quality, speed, and memory footprint. Secondly, we analyze whether it is better to use the model directly in Czech text, or to use machine translation into English, followed by retrieval in English. Our exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12921","kind":"arxiv","version":2},"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/2411.12921/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQYhvr8or/9CChqYtwsyDlTyRNk2m8fCRSG+Tyo7wHRvCDn1wZ7k6kT68kpyft4pL1eKcCMYL6ms/uQC8pEgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:02:31.939377Z"},"content_sha256":"9a55ad1269e826d046045cfa924325f791893c3720e6109003d1aa8bc158d4b3","schema_version":"1.0","event_id":"sha256:9a55ad1269e826d046045cfa924325f791893c3720e6109003d1aa8bc158d4b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NROAGGSPD5IJDNJLE6KGEYOJDG/bundle.json","state_url":"https://pith.science/pith/NROAGGSPD5IJDNJLE6KGEYOJDG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NROAGGSPD5IJDNJLE6KGEYOJDG/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":"2026-08-13T08:02:31Z","links":{"resolver":"https://pith.science/pith/NROAGGSPD5IJDNJLE6KGEYOJDG","bundle":"https://pith.science/pith/NROAGGSPD5IJDNJLE6KGEYOJDG/bundle.json","state":"https://pith.science/pith/NROAGGSPD5IJDNJLE6KGEYOJDG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NROAGGSPD5IJDNJLE6KGEYOJDG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NROAGGSPD5IJDNJLE6KGEYOJDG","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":"a9ff4d5fafb516048a406045181bba48ed2b212ea34fbcc7934e9b50f9e12697","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-19T23:19:46Z","title_canon_sha256":"ba1183f5a2346d0f0f3c07d0c5ac30fe1dadbd5ffa638546f911c4164d022a0e"},"schema_version":"1.0","source":{"id":"2411.12921","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12921","created_at":"2026-07-05T09:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12921v2","created_at":"2026-07-05T09:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12921","created_at":"2026-07-05T09:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"NROAGGSPD5IJ","created_at":"2026-07-05T09:52:40Z"},{"alias_kind":"pith_short_16","alias_value":"NROAGGSPD5IJDNJL","created_at":"2026-07-05T09:52:40Z"},{"alias_kind":"pith_short_8","alias_value":"NROAGGSP","created_at":"2026-07-05T09:52:40Z"}],"graph_snapshots":[{"event_id":"sha256:9a55ad1269e826d046045cfa924325f791893c3720e6109003d1aa8bc158d4b3","target":"graph","created_at":"2026-07-05T09:52:40Z","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/2411.12921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This article presents a comprehensive evaluation of 7 off-the-shelf document retrieval models: Splade, Plaid, Plaid-X, SimCSE, Contriever, OpenAI ADA and Gemma2 chosen to determine their performance on the Czech retrieval dataset DaReCzech. The primary objective of our experiments is to estimate the quality of modern retrieval approaches in the Czech language. Our analyses include retrieval quality, speed, and memory footprint. Secondly, we analyze whether it is better to use the model directly in Czech text, or to use machine translation into English, followed by retrieval in English. Our exp","authors_text":"Jakub Stetina, Martin Fajcik, Michal Hradis, Michal Stefanik","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-19T23:19:46Z","title":"A Comparative Study of Text Retrieval Models on DaReCzech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12921","kind":"arxiv","version":2},"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:a476b960d736d607730cf6484f31c1c1119c1164c94d6323e67a4544ac159084","target":"record","created_at":"2026-07-05T09:52:40Z","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":"a9ff4d5fafb516048a406045181bba48ed2b212ea34fbcc7934e9b50f9e12697","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-19T23:19:46Z","title_canon_sha256":"ba1183f5a2346d0f0f3c07d0c5ac30fe1dadbd5ffa638546f911c4164d022a0e"},"schema_version":"1.0","source":{"id":"2411.12921","kind":"arxiv","version":2}},"canonical_sha256":"6c5c031a4f1f5091b52b27946261c919abeafb1cc54ad273c6dd998912524df4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c5c031a4f1f5091b52b27946261c919abeafb1cc54ad273c6dd998912524df4","first_computed_at":"2026-07-05T09:52:40.474881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:40.474881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sAV9xZxESh7FvjuEuqI2NvGN8wbN2DYxIRu2Ge/RPoWdJ+D8oUqhb7VzQ2M+nrpQbm1BhJu+3FaCvUa52DPaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:40.475327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12921","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a476b960d736d607730cf6484f31c1c1119c1164c94d6323e67a4544ac159084","sha256:9a55ad1269e826d046045cfa924325f791893c3720e6109003d1aa8bc158d4b3"],"state_sha256":"3a3d901a7f3d68d3d2d39a4d05c330908cda313f1a8c1b3c41ae2838cc1f9738"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oYK+8rCLeuw7XrwIAaOr1cUJEFQEUfI2AxnFLtJr/XzYkJwzB32PAoijOqcJN8plQh8cPLDhWbWC6wxjmTtlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T08:02:31.944152Z","bundle_sha256":"6199e6875b9017f27ef97fa8fd4e0c0676f854aadf32440405483d1da3efdf97"}}