{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:URUH7CGY5JSYYLUFN72GO7KPYG","short_pith_number":"pith:URUH7CGY","canonical_record":{"source":{"id":"2605.17640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-17T20:19:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d7845a728df11776d8f1b0be42546af7c1e0a67091959524c8612dbf44164cd5","abstract_canon_sha256":"dbdcec7d7b0396ab89a39f08f277a62bae79d552ff17ac74ba103c97e80cd862"},"schema_version":"1.0"},"canonical_sha256":"a4687f88d8ea658c2e856ff4677d4fc1a9b6b0c91ec3b57072c2704a10da90eb","source":{"kind":"arxiv","id":"2605.17640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17640","created_at":"2026-05-20T00:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17640v1","created_at":"2026-05-20T00:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17640","created_at":"2026-05-20T00:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"URUH7CGY5JSY","created_at":"2026-05-20T00:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"URUH7CGY5JSYYLUF","created_at":"2026-05-20T00:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"URUH7CGY","created_at":"2026-05-20T00:04:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:URUH7CGY5JSYYLUFN72GO7KPYG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-17T20:19:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d7845a728df11776d8f1b0be42546af7c1e0a67091959524c8612dbf44164cd5","abstract_canon_sha256":"dbdcec7d7b0396ab89a39f08f277a62bae79d552ff17ac74ba103c97e80cd862"},"schema_version":"1.0"},"canonical_sha256":"a4687f88d8ea658c2e856ff4677d4fc1a9b6b0c91ec3b57072c2704a10da90eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:50.177758Z","signature_b64":"/u6fVElGjfAjQ+o2MM96eGH1AvotITXj9i4MDhCQiHTi37iF5O6EMScXIfIQDQAgleNgBKRDN13qd3kYOaKEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4687f88d8ea658c2e856ff4677d4fc1a9b6b0c91ec3b57072c2704a10da90eb","last_reissued_at":"2026-05-20T00:04:50.176880Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:50.176880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17640","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":"2026-05-20T00:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EyuqdmH7ojuQfra7iLDD3iVdcwLn45deeWkD8eBdHOswHbu1NzHXpSl0VTeRCJ0JNhMI2v9Ng4ZASwvipAKsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T15:37:03.739003Z"},"content_sha256":"231012abce467c59dc3345f54bf71be69e37517e1c36188ce54217fefadf72b0","schema_version":"1.0","event_id":"sha256:231012abce467c59dc3345f54bf71be69e37517e1c36188ce54217fefadf72b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:URUH7CGY5JSYYLUFN72GO7KPYG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MARQUIS is a three-stage pipeline that lifts video retrieval-augmented generation performance on complex queries and long contexts.","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Alexander Martin, Benjamin Van Durme, Debashish Chakraborty, Dengjia Zhang, Hanting Liu, Hanxiang Qin, Jialiang Jin, Katherine Guerrerio, Reno Kriz, Tyler Skow","submitted_at":"2026-05-17T20:19:04Z","abstract_excerpt":"Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into coherent, attributed text. Current approaches struggle at both ends: retrieval methods fail on complex, multi-faceted queries that cannot be captured by a single embedding, while generation methods lack the high-level reasoning needed to synthesize across multiple videos and face memory constraints over long, multi-video contexts. We present MARQUIS: a three-stage pipeline that addresses these limitations through (1) query expansion, fusion, and rerank"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the MAGMaR2026 shared task, we improve retrieval performance from 0.195 to 0.759 (nDCG@10). For article generation, ITER-QA-BASE improves average human score from 3.09 to 3.83 over the CAG baseline, while MARQUIS-RLM achieves a human score of 3.30 and the strongest citation recall among non-QA systems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The improvements are attributable to the three-stage pipeline design rather than implementation details, baseline choices, or task-specific tuning not described in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MARQUIS is a three-stage pipeline for video RAG that boosts retrieval nDCG@10 from 0.195 to 0.759 and generation human scores on the MAGMaR2026 shared task.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MARQUIS is a three-stage pipeline that lifts video retrieval-augmented generation performance on complex queries and long contexts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"904bb27fdb0fac14a69bd5a3035c4a79d513aa3fd9e91240c04c9dbfb5cf4717"},"source":{"id":"2605.17640","kind":"arxiv","version":1},"verdict":{"id":"e481fff4-0d5a-4803-8a78-15654ab8ac84","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T22:34:18.815023Z","strongest_claim":"On the MAGMaR2026 shared task, we improve retrieval performance from 0.195 to 0.759 (nDCG@10). For article generation, ITER-QA-BASE improves average human score from 3.09 to 3.83 over the CAG baseline, while MARQUIS-RLM achieves a human score of 3.30 and the strongest citation recall among non-QA systems.","one_line_summary":"MARQUIS is a three-stage pipeline for video RAG that boosts retrieval nDCG@10 from 0.195 to 0.759 and generation human scores on the MAGMaR2026 shared task.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The improvements are attributable to the three-stage pipeline design rather than implementation details, baseline choices, or task-specific tuning not described in the abstract.","pith_extraction_headline":"MARQUIS is a three-stage pipeline that lifts video retrieval-augmented generation performance on complex queries and long contexts."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17640/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T23:01:19.419980Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:40:54.013250Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T22:22:49.593847Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.553066Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.474662Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d043bf1eb29d6f5527902c711f89d94c0eabfa0eb97e5375b106cd6c07d3c1fc"},"references":{"count":65,"sample":[{"doi":"","year":2018,"title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","work_id":"27eaec54-c105-4969-8188-da5f0fca3688","ref_index":1,"cited_arxiv_id":"2005.11401","is_internal_anchor":true},{"doi":"","year":2022,"title":"Streamlining evaluation with ir-measures. In Advances in Information Retrieval - 44th European Conference on IR Research, ECIR 2022, Stavanger , Norway, April 10-14, 2022, Proceedings, Part II, volume","work_id":"4caa9f2b-6109-43b9-b68d-b9e6d7a89e9d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brock- man, Christine Mcleavey, and Ilya Sutskever","work_id":"d96fb1d9-0710-444d-844a-c3fa30480a4a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"arXiv preprint arXiv:2509.23040 , year=","work_id":"74006986-b24a-48c9-a5c0-d5cfbc5a76ab","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Do not merge separate information needs into one sub-query","work_id":"a8e93cf7-6a17-459e-97b1-6f4c86d815b9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":65,"snapshot_sha256":"0764efb5f9ce85d3f77ac3110f4f8b877ef9462cadeacd382490dd0f94746562","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"567e977a63a2b9527cb78563645db86a21ef925cadda70bd7ac9be622d869b5c"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e481fff4-0d5a-4803-8a78-15654ab8ac84"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hv2jwMKxe8l8iMjtUz2jbWYaPw+Z9r631/4xOaw5przEAR7L2AqA14DqEMNcjDU949/nIlnMab721GZGH9wSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T15:37:03.739817Z"},"content_sha256":"4a3e46efb9ce7755d48f93c08fdac5d57780651ae883c12f059c159cc74b0bb5","schema_version":"1.0","event_id":"sha256:4a3e46efb9ce7755d48f93c08fdac5d57780651ae883c12f059c159cc74b0bb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/URUH7CGY5JSYYLUFN72GO7KPYG/bundle.json","state_url":"https://pith.science/pith/URUH7CGY5JSYYLUFN72GO7KPYG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/URUH7CGY5JSYYLUFN72GO7KPYG/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":"2026-06-04T15:37:03Z","links":{"resolver":"https://pith.science/pith/URUH7CGY5JSYYLUFN72GO7KPYG","bundle":"https://pith.science/pith/URUH7CGY5JSYYLUFN72GO7KPYG/bundle.json","state":"https://pith.science/pith/URUH7CGY5JSYYLUFN72GO7KPYG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/URUH7CGY5JSYYLUFN72GO7KPYG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:URUH7CGY5JSYYLUFN72GO7KPYG","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":"dbdcec7d7b0396ab89a39f08f277a62bae79d552ff17ac74ba103c97e80cd862","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-17T20:19:04Z","title_canon_sha256":"d7845a728df11776d8f1b0be42546af7c1e0a67091959524c8612dbf44164cd5"},"schema_version":"1.0","source":{"id":"2605.17640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17640","created_at":"2026-05-20T00:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17640v1","created_at":"2026-05-20T00:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17640","created_at":"2026-05-20T00:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"URUH7CGY5JSY","created_at":"2026-05-20T00:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"URUH7CGY5JSYYLUF","created_at":"2026-05-20T00:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"URUH7CGY","created_at":"2026-05-20T00:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:4a3e46efb9ce7755d48f93c08fdac5d57780651ae883c12f059c159cc74b0bb5","target":"graph","created_at":"2026-05-20T00:04:50Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"On the MAGMaR2026 shared task, we improve retrieval performance from 0.195 to 0.759 (nDCG@10). For article generation, ITER-QA-BASE improves average human score from 3.09 to 3.83 over the CAG baseline, while MARQUIS-RLM achieves a human score of 3.30 and the strongest citation recall among non-QA systems."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The improvements are attributable to the three-stage pipeline design rather than implementation details, baseline choices, or task-specific tuning not described in the abstract."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MARQUIS is a three-stage pipeline for video RAG that boosts retrieval nDCG@10 from 0.195 to 0.759 and generation human scores on the MAGMaR2026 shared task."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MARQUIS is a three-stage pipeline that lifts video retrieval-augmented generation performance on complex queries and long contexts."}],"snapshot_sha256":"904bb27fdb0fac14a69bd5a3035c4a79d513aa3fd9e91240c04c9dbfb5cf4717"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"567e977a63a2b9527cb78563645db86a21ef925cadda70bd7ac9be622d869b5c"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T23:01:19.419980Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T22:40:54.013250Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T22:22:49.593847Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.553066Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.474662Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17640/integrity.json","findings":[],"snapshot_sha256":"d043bf1eb29d6f5527902c711f89d94c0eabfa0eb97e5375b106cd6c07d3c1fc","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into coherent, attributed text. Current approaches struggle at both ends: retrieval methods fail on complex, multi-faceted queries that cannot be captured by a single embedding, while generation methods lack the high-level reasoning needed to synthesize across multiple videos and face memory constraints over long, multi-video contexts. We present MARQUIS: a three-stage pipeline that addresses these limitations through (1) query expansion, fusion, and rerank","authors_text":"Alexander Martin, Benjamin Van Durme, Debashish Chakraborty, Dengjia Zhang, Hanting Liu, Hanxiang Qin, Jialiang Jin, Katherine Guerrerio, Reno Kriz, Tyler Skow","cross_cats":["cs.CV"],"headline":"MARQUIS is a three-stage pipeline that lifts video retrieval-augmented generation performance on complex queries and long contexts.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-17T20:19:04Z","title":"MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation"},"references":{"count":65,"internal_anchors":1,"resolved_work":65,"sample":[{"cited_arxiv_id":"2005.11401","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","work_id":"27eaec54-c105-4969-8188-da5f0fca3688","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Streamlining evaluation with ir-measures. In Advances in Information Retrieval - 44th European Conference on IR Research, ECIR 2022, Stavanger , Norway, April 10-14, 2022, Proceedings, Part II, volume","work_id":"4caa9f2b-6109-43b9-b68d-b9e6d7a89e9d","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brock- man, Christine Mcleavey, and Ilya Sutskever","work_id":"d96fb1d9-0710-444d-844a-c3fa30480a4a","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"arXiv preprint arXiv:2509.23040 , year=","work_id":"74006986-b24a-48c9-a5c0-d5cfbc5a76ab","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Do not merge separate information needs into one sub-query","work_id":"a8e93cf7-6a17-459e-97b1-6f4c86d815b9","year":null}],"snapshot_sha256":"0764efb5f9ce85d3f77ac3110f4f8b877ef9462cadeacd382490dd0f94746562"},"source":{"id":"2605.17640","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T22:34:18.815023Z","id":"e481fff4-0d5a-4803-8a78-15654ab8ac84","model_set":{"reader":"grok-4.3"},"one_line_summary":"MARQUIS is a three-stage pipeline for video RAG that boosts retrieval nDCG@10 from 0.195 to 0.759 and generation human scores on the MAGMaR2026 shared task.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MARQUIS is a three-stage pipeline that lifts video retrieval-augmented generation performance on complex queries and long contexts.","strongest_claim":"On the MAGMaR2026 shared task, we improve retrieval performance from 0.195 to 0.759 (nDCG@10). For article generation, ITER-QA-BASE improves average human score from 3.09 to 3.83 over the CAG baseline, while MARQUIS-RLM achieves a human score of 3.30 and the strongest citation recall among non-QA systems.","weakest_assumption":"The improvements are attributable to the three-stage pipeline design rather than implementation details, baseline choices, or task-specific tuning not described in the abstract."}},"verdict_id":"e481fff4-0d5a-4803-8a78-15654ab8ac84"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:231012abce467c59dc3345f54bf71be69e37517e1c36188ce54217fefadf72b0","target":"record","created_at":"2026-05-20T00:04:50Z","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":"dbdcec7d7b0396ab89a39f08f277a62bae79d552ff17ac74ba103c97e80cd862","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-17T20:19:04Z","title_canon_sha256":"d7845a728df11776d8f1b0be42546af7c1e0a67091959524c8612dbf44164cd5"},"schema_version":"1.0","source":{"id":"2605.17640","kind":"arxiv","version":1}},"canonical_sha256":"a4687f88d8ea658c2e856ff4677d4fc1a9b6b0c91ec3b57072c2704a10da90eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4687f88d8ea658c2e856ff4677d4fc1a9b6b0c91ec3b57072c2704a10da90eb","first_computed_at":"2026-05-20T00:04:50.176880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:50.176880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/u6fVElGjfAjQ+o2MM96eGH1AvotITXj9i4MDhCQiHTi37iF5O6EMScXIfIQDQAgleNgBKRDN13qd3kYOaKEAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:50.177758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:231012abce467c59dc3345f54bf71be69e37517e1c36188ce54217fefadf72b0","sha256:4a3e46efb9ce7755d48f93c08fdac5d57780651ae883c12f059c159cc74b0bb5"],"state_sha256":"2794b72a81528597d8a23467d5f5ca25ae6576c84c565f4ff35a68ff513f1912"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YYtHDwXmFJJ5Y/F1brutSPVh9uYD7t9pcZcudQ6RVxNeG28tcJyhLEZ5IPrwWPiOTEQpWhUL8zT/IIOd8I1iAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T15:37:03.742553Z","bundle_sha256":"fe9212a6d07fbd5ff238895cc8c554f991a7388376f17c19c514bdcac542a436"}}