{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:322KQFX5CM6DTCW7UNCYZEDM6N","short_pith_number":"pith:322KQFX5","canonical_record":{"source":{"id":"2402.18700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T20:41:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e04ae76ee06947a0048da31ae3f90d04b5a71aa179c5966ed5a410bc2fd611b0","abstract_canon_sha256":"0c2c92e3d7115b089f055ac88f6369653b9876ee879a89648bf7cf907e959d0f"},"schema_version":"1.0"},"canonical_sha256":"deb4a816fd133c398adfa3458c906cf3604c90efc9612e61cba3ef82edefd84e","source":{"kind":"arxiv","id":"2402.18700","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18700","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18700v2","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18700","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"322KQFX5CM6D","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"322KQFX5CM6DTCW7","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"322KQFX5","created_at":"2026-07-05T08:03:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:322KQFX5CM6DTCW7UNCYZEDM6N","target":"record","payload":{"canonical_record":{"source":{"id":"2402.18700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T20:41:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e04ae76ee06947a0048da31ae3f90d04b5a71aa179c5966ed5a410bc2fd611b0","abstract_canon_sha256":"0c2c92e3d7115b089f055ac88f6369653b9876ee879a89648bf7cf907e959d0f"},"schema_version":"1.0"},"canonical_sha256":"deb4a816fd133c398adfa3458c906cf3604c90efc9612e61cba3ef82edefd84e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:10.814348Z","signature_b64":"V14Z9qqMeSRrgElK9aBmtOvaGLUivXalYmbzH5dbUtKFQhk225pr+19h4if/0gKg4qz5t2Y4uzXYb+2KHNOICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"deb4a816fd133c398adfa3458c906cf3604c90efc9612e61cba3ef82edefd84e","last_reissued_at":"2026-07-05T08:03:10.813842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:10.813842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.18700","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CmbBH4p0vOZMRw6nEDZZyKwzEa/SqHfYAWpZYETM8xHGjigcs40XYJD4w4XefmD5i80aRhTbrk4WnVBB3gcYAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:17:04.289782Z"},"content_sha256":"08c662bdb33d92e02811b43f5fc1a7402dea0fb123fef862d2b2277ce445a5fa","schema_version":"1.0","event_id":"sha256:08c662bdb33d92e02811b43f5fc1a7402dea0fb123fef862d2b2277ce445a5fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:322KQFX5CM6DTCW7UNCYZEDM6N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Compress Prompt in Natural Language Formats","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chia-Yuan Chang, Tianwei Xing, Xia Hu, Xun Chen, Yu-Neng Chuang, Zirui Liu","submitted_at":"2024-02-28T20:41:21Z","abstract_excerpt":"Large language models (LLMs) are great at processing multiple natural language processing tasks, but their abilities are constrained by inferior performance with long context, slow inference speed, and the high cost of computing the results. Deploying LLMs with precise and informative context helps users process large-scale datasets more effectively and cost-efficiently. Existing works rely on compressing long prompt contexts into soft prompts. However, soft prompt compression encounters limitations in transferability across different LLMs, especially API-based LLMs. To this end, this work aim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18700","kind":"arxiv","version":2},"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/2402.18700/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":"2026-07-05T08:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQiWBkyzYlVFSQM6OwQgXfoESKQingeK9NT/uJjLuopHO3S+Qzg/sai/x2QjgiMuQdGV5LS9WHtfqDiR+1r8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:17:04.290305Z"},"content_sha256":"a78cf8998d8ce567f16abf36528daef25c3751bdfe1f5719077534a437e9eb91","schema_version":"1.0","event_id":"sha256:a78cf8998d8ce567f16abf36528daef25c3751bdfe1f5719077534a437e9eb91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/322KQFX5CM6DTCW7UNCYZEDM6N/bundle.json","state_url":"https://pith.science/pith/322KQFX5CM6DTCW7UNCYZEDM6N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/322KQFX5CM6DTCW7UNCYZEDM6N/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":"2026-08-10T04:17:04Z","links":{"resolver":"https://pith.science/pith/322KQFX5CM6DTCW7UNCYZEDM6N","bundle":"https://pith.science/pith/322KQFX5CM6DTCW7UNCYZEDM6N/bundle.json","state":"https://pith.science/pith/322KQFX5CM6DTCW7UNCYZEDM6N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/322KQFX5CM6DTCW7UNCYZEDM6N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:322KQFX5CM6DTCW7UNCYZEDM6N","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":"0c2c92e3d7115b089f055ac88f6369653b9876ee879a89648bf7cf907e959d0f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T20:41:21Z","title_canon_sha256":"e04ae76ee06947a0048da31ae3f90d04b5a71aa179c5966ed5a410bc2fd611b0"},"schema_version":"1.0","source":{"id":"2402.18700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18700","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18700v2","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18700","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"322KQFX5CM6D","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"322KQFX5CM6DTCW7","created_at":"2026-07-05T08:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"322KQFX5","created_at":"2026-07-05T08:03:10Z"}],"graph_snapshots":[{"event_id":"sha256:a78cf8998d8ce567f16abf36528daef25c3751bdfe1f5719077534a437e9eb91","target":"graph","created_at":"2026-07-05T08:03:10Z","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/2402.18700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are great at processing multiple natural language processing tasks, but their abilities are constrained by inferior performance with long context, slow inference speed, and the high cost of computing the results. Deploying LLMs with precise and informative context helps users process large-scale datasets more effectively and cost-efficiently. Existing works rely on compressing long prompt contexts into soft prompts. However, soft prompt compression encounters limitations in transferability across different LLMs, especially API-based LLMs. To this end, this work aim","authors_text":"Chia-Yuan Chang, Tianwei Xing, Xia Hu, Xun Chen, Yu-Neng Chuang, Zirui Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T20:41:21Z","title":"Learning to Compress Prompt in Natural Language Formats"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18700","kind":"arxiv","version":2},"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":"sha256:08c662bdb33d92e02811b43f5fc1a7402dea0fb123fef862d2b2277ce445a5fa","target":"record","created_at":"2026-07-05T08:03:10Z","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":"0c2c92e3d7115b089f055ac88f6369653b9876ee879a89648bf7cf907e959d0f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T20:41:21Z","title_canon_sha256":"e04ae76ee06947a0048da31ae3f90d04b5a71aa179c5966ed5a410bc2fd611b0"},"schema_version":"1.0","source":{"id":"2402.18700","kind":"arxiv","version":2}},"canonical_sha256":"deb4a816fd133c398adfa3458c906cf3604c90efc9612e61cba3ef82edefd84e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"deb4a816fd133c398adfa3458c906cf3604c90efc9612e61cba3ef82edefd84e","first_computed_at":"2026-07-05T08:03:10.813842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:10.813842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V14Z9qqMeSRrgElK9aBmtOvaGLUivXalYmbzH5dbUtKFQhk225pr+19h4if/0gKg4qz5t2Y4uzXYb+2KHNOICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:10.814348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08c662bdb33d92e02811b43f5fc1a7402dea0fb123fef862d2b2277ce445a5fa","sha256:a78cf8998d8ce567f16abf36528daef25c3751bdfe1f5719077534a437e9eb91"],"state_sha256":"075b7adcbf757d61c60fd9848acfc3ddb9455882fe3220cac75f859afbe82878"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6NJz38qzIKzcjgFJr4Wn5h41rg7kl94Ud0WwmrPvvGervT8d6QV9JvxCfSRANGgSDv3hs41D71ot16w1UxTnAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:17:04.296516Z","bundle_sha256":"56ec30e8eae3b92bd32f793e02b4ff61a120f362ee336f8baf064cd73d4adae0"}}