{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RY4PNJH3S3E6JF7X4AWO7KXTLC","short_pith_number":"pith:RY4PNJH3","canonical_record":{"source":{"id":"2506.04997","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-05T13:06:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1f19adb2ad78196cb756f0e3f9606463ed06024521c9a8a60982acaf5ec9737f","abstract_canon_sha256":"8f8ffb75819278d0a0e13b504aa5336ac64e6996c6b6ce3a0d64eec28b605310"},"schema_version":"1.0"},"canonical_sha256":"8e38f6a4fb96c9e497f7e02cefaaf358810a038e20ab0d59e85867d324758f84","source":{"kind":"arxiv","id":"2506.04997","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04997","created_at":"2026-07-05T11:16:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04997v1","created_at":"2026-07-05T11:16:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04997","created_at":"2026-07-05T11:16:40Z"},{"alias_kind":"pith_short_12","alias_value":"RY4PNJH3S3E6","created_at":"2026-07-05T11:16:40Z"},{"alias_kind":"pith_short_16","alias_value":"RY4PNJH3S3E6JF7X","created_at":"2026-07-05T11:16:40Z"},{"alias_kind":"pith_short_8","alias_value":"RY4PNJH3","created_at":"2026-07-05T11:16:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RY4PNJH3S3E6JF7X4AWO7KXTLC","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04997","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-05T13:06:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1f19adb2ad78196cb756f0e3f9606463ed06024521c9a8a60982acaf5ec9737f","abstract_canon_sha256":"8f8ffb75819278d0a0e13b504aa5336ac64e6996c6b6ce3a0d64eec28b605310"},"schema_version":"1.0"},"canonical_sha256":"8e38f6a4fb96c9e497f7e02cefaaf358810a038e20ab0d59e85867d324758f84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:40.574795Z","signature_b64":"kbusaizMv/hfkv43ThimDdavQYXDlyZPYdA1i57EyU93p0jkkmaG8/2OAYtMKHEnDpUqCNv150Cof60ddaXtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e38f6a4fb96c9e497f7e02cefaaf358810a038e20ab0d59e85867d324758f84","last_reissued_at":"2026-07-05T11:16:40.573982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:40.573982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04997","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":"2026-07-05T11:16:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RflgVx23Dupod5y/0tzM0N8jCvDtTheVjFcLYujJb++ax/NkhGIcCBST//FL0d6Wt7pCZwcU6JlWEssD1iFxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:15:36.642278Z"},"content_sha256":"c775c6d986fdd884b35fc93c7b970f3d18b9d1fcb834b59dee7faaac6c1f2487","schema_version":"1.0","event_id":"sha256:c775c6d986fdd884b35fc93c7b970f3d18b9d1fcb834b59dee7faaac6c1f2487"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RY4PNJH3S3E6JF7X4AWO7KXTLC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Aixin Sun, Haodong Duan, Jiaqi Wang, Jinsong Li, Pan Zhang, Xiaobao Wu, Xiaoyi Dong, Yixin Cao, Yubo Ma, Yuhang Cao, Yuhang Zang","submitted_at":"2025-06-05T13:06:01Z","abstract_excerpt":"Despite the strong performance of ColPali/ColQwen2 in Visualized Document Retrieval (VDR), it encodes each page into multiple patch-level embeddings and leads to excessive memory usage. This empirical study investigates methods to reduce patch embeddings per page at minimum performance degradation. We evaluate two token-reduction strategies: token pruning and token merging. Regarding token pruning, we surprisingly observe that a simple random strategy outperforms other sophisticated pruning methods, though still far from satisfactory. Further analysis reveals that pruning is inherently unsuita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04997","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.04997/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":"2026-07-05T11:16:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6guQFIAmxFxfOlURiFK1iVmykflwqkcXPnn4fLtzP+zf0B2R8IynC6omVNTmF7kHEFcixc+8hGb5E5pdY3tCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:15:36.643371Z"},"content_sha256":"f3df875e9202120d9d3fdf7eae943c1fa8165412a71940f50f4aa7b5f8fb54f6","schema_version":"1.0","event_id":"sha256:f3df875e9202120d9d3fdf7eae943c1fa8165412a71940f50f4aa7b5f8fb54f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RY4PNJH3S3E6JF7X4AWO7KXTLC/bundle.json","state_url":"https://pith.science/pith/RY4PNJH3S3E6JF7X4AWO7KXTLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RY4PNJH3S3E6JF7X4AWO7KXTLC/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":"2026-08-09T04:15:36Z","links":{"resolver":"https://pith.science/pith/RY4PNJH3S3E6JF7X4AWO7KXTLC","bundle":"https://pith.science/pith/RY4PNJH3S3E6JF7X4AWO7KXTLC/bundle.json","state":"https://pith.science/pith/RY4PNJH3S3E6JF7X4AWO7KXTLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RY4PNJH3S3E6JF7X4AWO7KXTLC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RY4PNJH3S3E6JF7X4AWO7KXTLC","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":"8f8ffb75819278d0a0e13b504aa5336ac64e6996c6b6ce3a0d64eec28b605310","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-05T13:06:01Z","title_canon_sha256":"1f19adb2ad78196cb756f0e3f9606463ed06024521c9a8a60982acaf5ec9737f"},"schema_version":"1.0","source":{"id":"2506.04997","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04997","created_at":"2026-07-05T11:16:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04997v1","created_at":"2026-07-05T11:16:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04997","created_at":"2026-07-05T11:16:40Z"},{"alias_kind":"pith_short_12","alias_value":"RY4PNJH3S3E6","created_at":"2026-07-05T11:16:40Z"},{"alias_kind":"pith_short_16","alias_value":"RY4PNJH3S3E6JF7X","created_at":"2026-07-05T11:16:40Z"},{"alias_kind":"pith_short_8","alias_value":"RY4PNJH3","created_at":"2026-07-05T11:16:40Z"}],"graph_snapshots":[{"event_id":"sha256:f3df875e9202120d9d3fdf7eae943c1fa8165412a71940f50f4aa7b5f8fb54f6","target":"graph","created_at":"2026-07-05T11:16:40Z","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/2506.04997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the strong performance of ColPali/ColQwen2 in Visualized Document Retrieval (VDR), it encodes each page into multiple patch-level embeddings and leads to excessive memory usage. This empirical study investigates methods to reduce patch embeddings per page at minimum performance degradation. We evaluate two token-reduction strategies: token pruning and token merging. Regarding token pruning, we surprisingly observe that a simple random strategy outperforms other sophisticated pruning methods, though still far from satisfactory. Further analysis reveals that pruning is inherently unsuita","authors_text":"Aixin Sun, Haodong Duan, Jiaqi Wang, Jinsong Li, Pan Zhang, Xiaobao Wu, Xiaoyi Dong, Yixin Cao, Yubo Ma, Yuhang Cao, Yuhang Zang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-05T13:06:01Z","title":"Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04997","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:c775c6d986fdd884b35fc93c7b970f3d18b9d1fcb834b59dee7faaac6c1f2487","target":"record","created_at":"2026-07-05T11:16:40Z","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":"8f8ffb75819278d0a0e13b504aa5336ac64e6996c6b6ce3a0d64eec28b605310","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-05T13:06:01Z","title_canon_sha256":"1f19adb2ad78196cb756f0e3f9606463ed06024521c9a8a60982acaf5ec9737f"},"schema_version":"1.0","source":{"id":"2506.04997","kind":"arxiv","version":1}},"canonical_sha256":"8e38f6a4fb96c9e497f7e02cefaaf358810a038e20ab0d59e85867d324758f84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e38f6a4fb96c9e497f7e02cefaaf358810a038e20ab0d59e85867d324758f84","first_computed_at":"2026-07-05T11:16:40.573982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:40.573982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kbusaizMv/hfkv43ThimDdavQYXDlyZPYdA1i57EyU93p0jkkmaG8/2OAYtMKHEnDpUqCNv150Cof60ddaXtBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:40.574795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04997","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c775c6d986fdd884b35fc93c7b970f3d18b9d1fcb834b59dee7faaac6c1f2487","sha256:f3df875e9202120d9d3fdf7eae943c1fa8165412a71940f50f4aa7b5f8fb54f6"],"state_sha256":"4c75d24288ee71c50e43a69e6640f6a1a0838d36d38a6ffb24f02a57eb6781db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"65Lz7L5QhZCcwdhHFuS9YXQoo9SGjAd9oYIXhpvvtbZzp8i31wuq+61l1C31RQ72atIrzGUazdXe/8op/uB7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:15:36.650753Z","bundle_sha256":"27af2de9d39e6c96856ef958e4b8f01b77c40435539d61ce0e7979e4c85aa3b2"}}