{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NYNXCKPUHXACL52OUUIQ3JS4HN","short_pith_number":"pith:NYNXCKPU","canonical_record":{"source":{"id":"2410.12388","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T09:13:23Z","cross_cats_sorted":[],"title_canon_sha256":"d02b76be5fcd2cf2db8fa3d7ddbe32132e88e871dde6ab5a8fb39b9dc4e100a1","abstract_canon_sha256":"7a737048756203920724851a651a80fda99be9ce35393ea0251b14e1242bb7d5"},"schema_version":"1.0"},"canonical_sha256":"6e1b7129f43dc025f74ea5110da65c3b564c352f9c64377e9eaace07b3b16d3d","source":{"kind":"arxiv","id":"2410.12388","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12388","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12388v2","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12388","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"NYNXCKPUHXAC","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"NYNXCKPUHXACL52O","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"NYNXCKPU","created_at":"2026-07-05T09:21:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NYNXCKPUHXACL52OUUIQ3JS4HN","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12388","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T09:13:23Z","cross_cats_sorted":[],"title_canon_sha256":"d02b76be5fcd2cf2db8fa3d7ddbe32132e88e871dde6ab5a8fb39b9dc4e100a1","abstract_canon_sha256":"7a737048756203920724851a651a80fda99be9ce35393ea0251b14e1242bb7d5"},"schema_version":"1.0"},"canonical_sha256":"6e1b7129f43dc025f74ea5110da65c3b564c352f9c64377e9eaace07b3b16d3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:50.699179Z","signature_b64":"GJ/j4kIUS+c68PHT2oov4DDnQDOMddCBkW5zd+yLvbcDa/RDS+bZP7I+woguRJNCp0RB24KArMKw9ax2TIokBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e1b7129f43dc025f74ea5110da65c3b564c352f9c64377e9eaace07b3b16d3d","last_reissued_at":"2026-07-05T09:21:50.698673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:50.698673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12388","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":"2026-07-05T09:21:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vdNLp83qhTF1zGuu2cg/g/esChqL+bp6lAzIqSkqYQPe3H47vEFRO7RKrj6PibUVq7punVreaPQAHDHCPlwhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T04:26:14.938792Z"},"content_sha256":"dec2c6f17dde2415e1666fc23228511ce6a008dd33b9484e9a4e3ae9f6cfa222","schema_version":"1.0","event_id":"sha256:dec2c6f17dde2415e1666fc23228511ce6a008dd33b9484e9a4e3ae9f6cfa222"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NYNXCKPUHXACL52OUUIQ3JS4HN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompt Compression for Large Language Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nigel Collier, Yinhong Liu, Yixuan Su, Zongqian Li","submitted_at":"2024-10-16T09:13:23Z","abstract_excerpt":"Leveraging large language models (LLMs) for complex natural language tasks typically requires long-form prompts to convey detailed requirements and information, which results in increased memory usage and inference costs. To mitigate these challenges, multiple efficient methods have been proposed, with prompt compression gaining significant research interest. This survey provides an overview of prompt compression techniques, categorized into hard prompt methods and soft prompt methods. First, the technical approaches of these methods are compared, followed by an exploration of various ways to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12388","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/2410.12388/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":"2026-07-05T09:21:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uClzeH37LC1W9wQpJb2G2JqWhL4redpae+YSsaX1hMDmQZKtf/Jso3olH3CBHG2JLYFIHNkUpo/C85nkjz9dAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T04:26:14.939172Z"},"content_sha256":"de4118d4e71d9781638333444791331cf9af4051a7eacc497401f041f51fed64","schema_version":"1.0","event_id":"sha256:de4118d4e71d9781638333444791331cf9af4051a7eacc497401f041f51fed64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NYNXCKPUHXACL52OUUIQ3JS4HN/bundle.json","state_url":"https://pith.science/pith/NYNXCKPUHXACL52OUUIQ3JS4HN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NYNXCKPUHXACL52OUUIQ3JS4HN/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":"2026-07-26T04:26:14Z","links":{"resolver":"https://pith.science/pith/NYNXCKPUHXACL52OUUIQ3JS4HN","bundle":"https://pith.science/pith/NYNXCKPUHXACL52OUUIQ3JS4HN/bundle.json","state":"https://pith.science/pith/NYNXCKPUHXACL52OUUIQ3JS4HN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NYNXCKPUHXACL52OUUIQ3JS4HN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NYNXCKPUHXACL52OUUIQ3JS4HN","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":"7a737048756203920724851a651a80fda99be9ce35393ea0251b14e1242bb7d5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T09:13:23Z","title_canon_sha256":"d02b76be5fcd2cf2db8fa3d7ddbe32132e88e871dde6ab5a8fb39b9dc4e100a1"},"schema_version":"1.0","source":{"id":"2410.12388","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12388","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12388v2","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12388","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"NYNXCKPUHXAC","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"NYNXCKPUHXACL52O","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"NYNXCKPU","created_at":"2026-07-05T09:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:de4118d4e71d9781638333444791331cf9af4051a7eacc497401f041f51fed64","target":"graph","created_at":"2026-07-05T09:21:50Z","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/2410.12388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leveraging large language models (LLMs) for complex natural language tasks typically requires long-form prompts to convey detailed requirements and information, which results in increased memory usage and inference costs. To mitigate these challenges, multiple efficient methods have been proposed, with prompt compression gaining significant research interest. This survey provides an overview of prompt compression techniques, categorized into hard prompt methods and soft prompt methods. First, the technical approaches of these methods are compared, followed by an exploration of various ways to ","authors_text":"Nigel Collier, Yinhong Liu, Yixuan Su, Zongqian Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T09:13:23Z","title":"Prompt Compression for Large Language Models: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12388","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:dec2c6f17dde2415e1666fc23228511ce6a008dd33b9484e9a4e3ae9f6cfa222","target":"record","created_at":"2026-07-05T09:21:50Z","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":"7a737048756203920724851a651a80fda99be9ce35393ea0251b14e1242bb7d5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T09:13:23Z","title_canon_sha256":"d02b76be5fcd2cf2db8fa3d7ddbe32132e88e871dde6ab5a8fb39b9dc4e100a1"},"schema_version":"1.0","source":{"id":"2410.12388","kind":"arxiv","version":2}},"canonical_sha256":"6e1b7129f43dc025f74ea5110da65c3b564c352f9c64377e9eaace07b3b16d3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e1b7129f43dc025f74ea5110da65c3b564c352f9c64377e9eaace07b3b16d3d","first_computed_at":"2026-07-05T09:21:50.698673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:50.698673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GJ/j4kIUS+c68PHT2oov4DDnQDOMddCBkW5zd+yLvbcDa/RDS+bZP7I+woguRJNCp0RB24KArMKw9ax2TIokBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:50.699179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12388","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dec2c6f17dde2415e1666fc23228511ce6a008dd33b9484e9a4e3ae9f6cfa222","sha256:de4118d4e71d9781638333444791331cf9af4051a7eacc497401f041f51fed64"],"state_sha256":"d81a0319c73030adc982deb6b7fb7c32dd12c23acb51a5cf1282b428a9e7a470"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UsiPS31B64mzQo2sItm2yt0Xr4kWcghBP+P5LvQM3jgSj1WjYLyxi/rRwMFmoPncYt1zFQIZUMJ2K2HpuYSaBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T04:26:14.941796Z","bundle_sha256":"239972837f176810db8e6c65d15dde70ea8787a19b83cd575cca755bd344f964"}}