{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:G5LAUIJFNICYJSRLTDIOEXF6PB","short_pith_number":"pith:G5LAUIJF","canonical_record":{"source":{"id":"2608.00765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T16:59:49Z","cross_cats_sorted":[],"title_canon_sha256":"57d19ea78babfefe559306985704e49078cf8c119dc75fee99e604176911e585","abstract_canon_sha256":"7d6e7ae5742df4ec1b5a70436ec059af6e8ee0eaabe72279d7d88b7ebdb29f65"},"schema_version":"1.0"},"canonical_sha256":"37560a21256a0584ca2b98d0e25cbe7848bd333225441ecb02fa9b2241165a5f","source":{"kind":"arxiv","id":"2608.00765","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00765","created_at":"2026-08-04T01:54:54Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00765v1","created_at":"2026-08-04T01:54:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00765","created_at":"2026-08-04T01:54:54Z"},{"alias_kind":"pith_short_12","alias_value":"G5LAUIJFNICY","created_at":"2026-08-04T01:54:54Z"},{"alias_kind":"pith_short_16","alias_value":"G5LAUIJFNICYJSRL","created_at":"2026-08-04T01:54:54Z"},{"alias_kind":"pith_short_8","alias_value":"G5LAUIJF","created_at":"2026-08-04T01:54:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:G5LAUIJFNICYJSRLTDIOEXF6PB","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T16:59:49Z","cross_cats_sorted":[],"title_canon_sha256":"57d19ea78babfefe559306985704e49078cf8c119dc75fee99e604176911e585","abstract_canon_sha256":"7d6e7ae5742df4ec1b5a70436ec059af6e8ee0eaabe72279d7d88b7ebdb29f65"},"schema_version":"1.0"},"canonical_sha256":"37560a21256a0584ca2b98d0e25cbe7848bd333225441ecb02fa9b2241165a5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:54:54.192685Z","signature_b64":"O5MBrSV81oMHTe5jS2rKcftvj2ZOcDPrYk+NVUyxX20fOv8Apxb9ncIILe19vwKogeJ/R/r7z0zAfsPtA+LvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37560a21256a0584ca2b98d0e25cbe7848bd333225441ecb02fa9b2241165a5f","last_reissued_at":"2026-08-04T01:54:54.190991Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:54:54.190991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00765","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":"2026-08-04T01:54:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"56UN2l/DDq51CfKXBDirZSE6FKeqaF+gZQ+IqMl/wBe+fHRFCYotZfWEmsk7UA7nspcvq+rZFjJp1rwfNBUADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:05:36.529410Z"},"content_sha256":"c94d7eca63d52931d2af8ec26c5fcf56963751035426ed3b3191f0ff7892868d","schema_version":"1.0","event_id":"sha256:c94d7eca63d52931d2af8ec26c5fcf56963751035426ed3b3191f0ff7892868d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:G5LAUIJFNICYJSRLTDIOEXF6PB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jialun Zhong, Jiayang Yu, Lei Zou","submitted_at":"2026-08-01T16:59:49Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become essential for knowledge-intensive question answering, yet scaling RAG pipelines remains challenging due to the prohibitive computational cost of processing lengthy retrieved contexts. Existing compression approaches face a fundamental trade-off: hard compression methods operate online in a query-aware fashion but achieve only modest compression rates and typically require fine-tuning the generative model, while soft compression methods attain higher ratios but rely on costly offline encoding that is entirely agnostic to the input query. To bridge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00765","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/2608.00765/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":"2026-08-04T01:54:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6BlPJYyhT23uFJTHB/in2hlljGU7015kRc1hpofsEJTKR+XBjfYiWgl++Kq6xUfmwWzLFBcck/cnypqkAi4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:05:36.531263Z"},"content_sha256":"71ba958d2b4156c5be860e0b8312ae527f40be1afbb889c380a51315a06b4af2","schema_version":"1.0","event_id":"sha256:71ba958d2b4156c5be860e0b8312ae527f40be1afbb889c380a51315a06b4af2"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:G5LAUIJFNICYJSRLTDIOEXF6PB","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2023.emnlp-main.825) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2023. LLM- Lingua: Compressing Prompts for Accelerated Inference of Large Language Mod- els. InProceedings of the 2023 Conference on Empirical Methods in Natural Language ","arxiv_id":"2608.00765","detector":"doi_compliance","evidence":{"ref_index":14,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/2023.emnlp-","reconstructed_doi":"10.18653/v1/2023.emnlp-main.825"},"severity":"advisory","ref_index":14,"audited_at":"2026-08-05T00:29:34.864277Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2023.emnlp-main.825","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"9676150e1ce12986514409339457121545aa6738074c3c76d46074ba92826af0","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17981,"payload_sha256":"5f7307c4722f41875944582bd72559bd9aafedc500531afb0d9d376fbb20620f","signature_b64":"cBaigLYqrK70CmZYWC06sIH4SATCLy5iPeM0++iHuAl3Z0UQ+RyB+cHIwzL0hq1hOCZuS01EEidJ8Iqm62GGDA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T00:33:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o45rZ8XP/aIuN+1154My9Oo6QzNkaaZa1ELpJIG9/zchRvqoZfx7VdPxxag4EDNGvW/qyuupgGMEHAFpnulsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:05:36.543252Z"},"content_sha256":"e848497106b20c36945d90a54b0a494b9c25755d872add6837b48f984f38de5c","schema_version":"1.0","event_id":"sha256:e848497106b20c36945d90a54b0a494b9c25755d872add6837b48f984f38de5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/bundle.json","state_url":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/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":"2026-08-05T11:05:36Z","links":{"resolver":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB","bundle":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/bundle.json","state":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G5LAUIJFNICYJSRLTDIOEXF6PB","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7d6e7ae5742df4ec1b5a70436ec059af6e8ee0eaabe72279d7d88b7ebdb29f65","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T16:59:49Z","title_canon_sha256":"57d19ea78babfefe559306985704e49078cf8c119dc75fee99e604176911e585"},"schema_version":"1.0","source":{"id":"2608.00765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00765","created_at":"2026-08-04T01:54:54Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00765v1","created_at":"2026-08-04T01:54:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00765","created_at":"2026-08-04T01:54:54Z"},{"alias_kind":"pith_short_12","alias_value":"G5LAUIJFNICY","created_at":"2026-08-04T01:54:54Z"},{"alias_kind":"pith_short_16","alias_value":"G5LAUIJFNICYJSRL","created_at":"2026-08-04T01:54:54Z"},{"alias_kind":"pith_short_8","alias_value":"G5LAUIJF","created_at":"2026-08-04T01:54:54Z"}],"graph_snapshots":[{"event_id":"sha256:71ba958d2b4156c5be860e0b8312ae527f40be1afbb889c380a51315a06b4af2","target":"graph","created_at":"2026-08-04T01:54:54Z","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/2608.00765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become essential for knowledge-intensive question answering, yet scaling RAG pipelines remains challenging due to the prohibitive computational cost of processing lengthy retrieved contexts. Existing compression approaches face a fundamental trade-off: hard compression methods operate online in a query-aware fashion but achieve only modest compression rates and typically require fine-tuning the generative model, while soft compression methods attain higher ratios but rely on costly offline encoding that is entirely agnostic to the input query. To bridge","authors_text":"Jialun Zhong, Jiayang Yu, Lei Zou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T16:59:49Z","title":"RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00765","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:c94d7eca63d52931d2af8ec26c5fcf56963751035426ed3b3191f0ff7892868d","target":"record","created_at":"2026-08-04T01:54:54Z","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":"7d6e7ae5742df4ec1b5a70436ec059af6e8ee0eaabe72279d7d88b7ebdb29f65","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T16:59:49Z","title_canon_sha256":"57d19ea78babfefe559306985704e49078cf8c119dc75fee99e604176911e585"},"schema_version":"1.0","source":{"id":"2608.00765","kind":"arxiv","version":1}},"canonical_sha256":"37560a21256a0584ca2b98d0e25cbe7848bd333225441ecb02fa9b2241165a5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37560a21256a0584ca2b98d0e25cbe7848bd333225441ecb02fa9b2241165a5f","first_computed_at":"2026-08-04T01:54:54.190991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:54:54.190991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O5MBrSV81oMHTe5jS2rKcftvj2ZOcDPrYk+NVUyxX20fOv8Apxb9ncIILe19vwKogeJ/R/r7z0zAfsPtA+LvAA==","signature_status":"signed_v1","signed_at":"2026-08-04T01:54:54.192685Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c94d7eca63d52931d2af8ec26c5fcf56963751035426ed3b3191f0ff7892868d","sha256:71ba958d2b4156c5be860e0b8312ae527f40be1afbb889c380a51315a06b4af2","sha256:e848497106b20c36945d90a54b0a494b9c25755d872add6837b48f984f38de5c"],"state_sha256":"ad1224b22a45f518e6b57fd39387e029a67067d34e34c1fa037235ca5d0d2dda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uFTu7pUXy8wyZhGzxIB5JLPUcYvgMUxWUENvUs+86mhIMTCsboSZlg5hQd85cNJ9+zTlIRIr0RPWAy6R4Iz0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:05:36.554150Z","bundle_sha256":"006b14b142883af9108d4e292162e71a714a1b67958cf41f94ab0fac959441ab"}}