{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XTCYA42EUOO5UKKLWD6DRGADVJ","short_pith_number":"pith:XTCYA42E","canonical_record":{"source":{"id":"2501.16075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T14:26:27Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"1342ef3d6991f4421fffcf8c26bad8f5e9d966da16fb3b0b1ab9d924fed73452","abstract_canon_sha256":"f750d734a02e856ad943296891d129399af7c2e9b4cea5010a4e319ad86ee2d4"},"schema_version":"1.0"},"canonical_sha256":"bcc5807344a39dda294bb0fc389803aa48b83f53f4e5fe888847a2967945c3aa","source":{"kind":"arxiv","id":"2501.16075","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16075","created_at":"2026-07-05T10:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16075v1","created_at":"2026-07-05T10:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16075","created_at":"2026-07-05T10:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"XTCYA42EUOO5","created_at":"2026-07-05T10:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"XTCYA42EUOO5UKKL","created_at":"2026-07-05T10:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"XTCYA42E","created_at":"2026-07-05T10:05:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XTCYA42EUOO5UKKLWD6DRGADVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2501.16075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T14:26:27Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"1342ef3d6991f4421fffcf8c26bad8f5e9d966da16fb3b0b1ab9d924fed73452","abstract_canon_sha256":"f750d734a02e856ad943296891d129399af7c2e9b4cea5010a4e319ad86ee2d4"},"schema_version":"1.0"},"canonical_sha256":"bcc5807344a39dda294bb0fc389803aa48b83f53f4e5fe888847a2967945c3aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:54.783279Z","signature_b64":"deGpsRfmuxmBvSz+ovvBpn9wZ4M81BOyxHdii6deCecQHruQRupORGNf7Co2gdSHyoKcJMMaz8zgUf1URQzXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcc5807344a39dda294bb0fc389803aa48b83f53f4e5fe888847a2967945c3aa","last_reissued_at":"2026-07-05T10:05:54.782636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:54.782636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.16075","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":"2026-07-05T10:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k7hx1YVGmzBN1lVm0z6VeP5CgyRMdN1XLB5asBOtVzVA8WQq1wwpgqJ+l/1SyGgWLdju5Qsk5J1Q+zGAYMpTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:07:59.774505Z"},"content_sha256":"79b969ff0f1f0ae12b00f85b19a8e287a3b146cfbeee1ed432a67b5431dfa465","schema_version":"1.0","event_id":"sha256:79b969ff0f1f0ae12b00f85b19a8e287a3b146cfbeee1ed432a67b5431dfa465"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XTCYA42EUOO5UKKLWD6DRGADVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Herv\\'e D\\'ejean, Maxime Louis, St\\'ephane Clinchant","submitted_at":"2025-01-27T14:26:27Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) pipelines enhance Large Language Models (LLMs) by retrieving relevant documents, but they face scalability issues due to high inference costs and limited context size. Document compression is a practical solution, but current soft compression methods suffer from accuracy losses and require extensive pretraining. In this paper, we introduce PISCO, a novel method that achieves a 16x compression rate with minimal accuracy loss (0-3%) across diverse RAG-based question-answering (QA) tasks. Unlike existing approaches, PISCO requires no pretraining or annotated d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16075","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/2501.16075/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":"2026-07-05T10:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mYlAcuZ9KpsMNFbTre2ZDWhvrroirLEmwQ0eF3oABIsJM5mEDVGATYvYdFn0QiD7+zJ79Rd+bD1kJqchvG57Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:07:59.775003Z"},"content_sha256":"38e54ae52cbdc4d657ddc311e619a0caae50453dc36105576d0238748a3e513c","schema_version":"1.0","event_id":"sha256:38e54ae52cbdc4d657ddc311e619a0caae50453dc36105576d0238748a3e513c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTCYA42EUOO5UKKLWD6DRGADVJ/bundle.json","state_url":"https://pith.science/pith/XTCYA42EUOO5UKKLWD6DRGADVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTCYA42EUOO5UKKLWD6DRGADVJ/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":"2026-08-09T00:07:59Z","links":{"resolver":"https://pith.science/pith/XTCYA42EUOO5UKKLWD6DRGADVJ","bundle":"https://pith.science/pith/XTCYA42EUOO5UKKLWD6DRGADVJ/bundle.json","state":"https://pith.science/pith/XTCYA42EUOO5UKKLWD6DRGADVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTCYA42EUOO5UKKLWD6DRGADVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XTCYA42EUOO5UKKLWD6DRGADVJ","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":"f750d734a02e856ad943296891d129399af7c2e9b4cea5010a4e319ad86ee2d4","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T14:26:27Z","title_canon_sha256":"1342ef3d6991f4421fffcf8c26bad8f5e9d966da16fb3b0b1ab9d924fed73452"},"schema_version":"1.0","source":{"id":"2501.16075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16075","created_at":"2026-07-05T10:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16075v1","created_at":"2026-07-05T10:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16075","created_at":"2026-07-05T10:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"XTCYA42EUOO5","created_at":"2026-07-05T10:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"XTCYA42EUOO5UKKL","created_at":"2026-07-05T10:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"XTCYA42E","created_at":"2026-07-05T10:05:54Z"}],"graph_snapshots":[{"event_id":"sha256:38e54ae52cbdc4d657ddc311e619a0caae50453dc36105576d0238748a3e513c","target":"graph","created_at":"2026-07-05T10:05:54Z","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/2501.16075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) pipelines enhance Large Language Models (LLMs) by retrieving relevant documents, but they face scalability issues due to high inference costs and limited context size. Document compression is a practical solution, but current soft compression methods suffer from accuracy losses and require extensive pretraining. In this paper, we introduce PISCO, a novel method that achieves a 16x compression rate with minimal accuracy loss (0-3%) across diverse RAG-based question-answering (QA) tasks. Unlike existing approaches, PISCO requires no pretraining or annotated d","authors_text":"Herv\\'e D\\'ejean, Maxime Louis, St\\'ephane Clinchant","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T14:26:27Z","title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16075","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":"sha256:79b969ff0f1f0ae12b00f85b19a8e287a3b146cfbeee1ed432a67b5431dfa465","target":"record","created_at":"2026-07-05T10:05:54Z","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":"f750d734a02e856ad943296891d129399af7c2e9b4cea5010a4e319ad86ee2d4","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T14:26:27Z","title_canon_sha256":"1342ef3d6991f4421fffcf8c26bad8f5e9d966da16fb3b0b1ab9d924fed73452"},"schema_version":"1.0","source":{"id":"2501.16075","kind":"arxiv","version":1}},"canonical_sha256":"bcc5807344a39dda294bb0fc389803aa48b83f53f4e5fe888847a2967945c3aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcc5807344a39dda294bb0fc389803aa48b83f53f4e5fe888847a2967945c3aa","first_computed_at":"2026-07-05T10:05:54.782636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:54.782636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"deGpsRfmuxmBvSz+ovvBpn9wZ4M81BOyxHdii6deCecQHruQRupORGNf7Co2gdSHyoKcJMMaz8zgUf1URQzXDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:54.783279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79b969ff0f1f0ae12b00f85b19a8e287a3b146cfbeee1ed432a67b5431dfa465","sha256:38e54ae52cbdc4d657ddc311e619a0caae50453dc36105576d0238748a3e513c"],"state_sha256":"8d8cc704a008eeeff4e4e3e1a5416dcb2aff57c22fba342afd36f9c407dac3b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9fJJG7rjrpWeFt3vI+Cv2UQcsnDmP8DubgbfNMvHD3GNgh0+GiYYm6GUL5i2l4CS0udlHePIDyYvHIRkmT6pAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:07:59.779700Z","bundle_sha256":"ef10f17b8b768000822525225bd86ad09cb66b3d418d1de390b06d3084fd5ad5"}}