{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G5LAUIJFNICYJSRLTDIOEXF6PB","short_pith_number":"pith:G5LAUIJF","schema_version":"1.0","canonical_sha256":"37560a21256a0584ca2b98d0e25cbe7848bd333225441ecb02fa9b2241165a5f","source":{"kind":"arxiv","id":"2608.00765","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.00765","created_at":"2026-08-04T01:54:54.192405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00765v1","created_at":"2026-08-04T01:54:54.192405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00765","created_at":"2026-08-04T01:54:54.192405+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5LAUIJFNICY","created_at":"2026-08-04T01:54:54.192405+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5LAUIJFNICYJSRL","created_at":"2026-08-04T01:54:54.192405+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5LAUIJF","created_at":"2026-08-04T01:54:54.192405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB","json":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB.json","graph_json":"https://pith.science/api/pith-number/G5LAUIJFNICYJSRLTDIOEXF6PB/graph.json","events_json":"https://pith.science/api/pith-number/G5LAUIJFNICYJSRLTDIOEXF6PB/events.json","paper":"https://pith.science/paper/G5LAUIJF"},"agent_actions":{"view_html":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB","download_json":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB.json","view_paper":"https://pith.science/paper/G5LAUIJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00765&json=true","fetch_graph":"https://pith.science/api/pith-number/G5LAUIJFNICYJSRLTDIOEXF6PB/graph.json","fetch_events":"https://pith.science/api/pith-number/G5LAUIJFNICYJSRLTDIOEXF6PB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/action/storage_attestation","attest_author":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/action/author_attestation","sign_citation":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/action/citation_signature","submit_replication":"https://pith.science/pith/G5LAUIJFNICYJSRLTDIOEXF6PB/action/replication_record"}},"created_at":"2026-08-04T01:54:54.192405+00:00","updated_at":"2026-08-04T01:54:54.192405+00:00"}