{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SA4SQBXD7J2GVLBKWQFVAW3YKA","short_pith_number":"pith:SA4SQBXD","canonical_record":{"source":{"id":"2504.11004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T09:20:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e62dd0dfa6d813643a45374eafe75612533f08bb347adf9479da7440244c2cf2","abstract_canon_sha256":"07d105066c546dc9dbd4b6248830afcf7a6ed6b9eacd30924f927a2b6fa0458d"},"schema_version":"1.0"},"canonical_sha256":"90392806e3fa746aac2ab40b505b78500b5e8178de118802cf3576ebec90c099","source":{"kind":"arxiv","id":"2504.11004","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11004","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11004v1","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11004","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"SA4SQBXD7J2G","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_16","alias_value":"SA4SQBXD7J2GVLBK","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_8","alias_value":"SA4SQBXD","created_at":"2026-07-05T10:49:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SA4SQBXD7J2GVLBKWQFVAW3YKA","target":"record","payload":{"canonical_record":{"source":{"id":"2504.11004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T09:20:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e62dd0dfa6d813643a45374eafe75612533f08bb347adf9479da7440244c2cf2","abstract_canon_sha256":"07d105066c546dc9dbd4b6248830afcf7a6ed6b9eacd30924f927a2b6fa0458d"},"schema_version":"1.0"},"canonical_sha256":"90392806e3fa746aac2ab40b505b78500b5e8178de118802cf3576ebec90c099","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:27.714885Z","signature_b64":"QZWCEILjwEIo+sK7F3DZgRdy1tHukyyPJkDxqflZInfhMFUMRsTdQovQ5dohdMN63JFG4V0Yy7rKKIFfgpMqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90392806e3fa746aac2ab40b505b78500b5e8178de118802cf3576ebec90c099","last_reissued_at":"2026-07-05T10:49:27.714354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:27.714354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.11004","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":"2026-07-05T10:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XQy/BFaZQJqaaqamm3pQekrl5NQVXJPEEvreCkMeUSz/ZtE136ijzeRXOqwG1aD1nMzfE0gpjK00pCR1P4s1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:27:44.067156Z"},"content_sha256":"89be45db20331d28a58f00016ccd68b4db5ae25654fe5bbce45c4dd850b5fcde","schema_version":"1.0","event_id":"sha256:89be45db20331d28a58f00016ccd68b4db5ae25654fe5bbce45c4dd850b5fcde"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SA4SQBXD7J2GVLBKWQFVAW3YKA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Compressing Prompts for Efficient Inference of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Xiao, Jinwu Hu, Mingkui Tan, Qing Du, Wei Zhang, Yufeng Wang, Yu Hu","submitted_at":"2025-04-15T09:20:45Z","abstract_excerpt":"Large Language Models (LLMs) have shown outstanding performance across a variety of tasks, partly due to advanced prompting techniques. However, these techniques often require lengthy prompts, which increase computational costs and can hinder performance because of the limited context windows of LLMs. While prompt compression is a straightforward solution, existing methods confront the challenges of retaining essential information, adapting to context changes, and remaining effective across different tasks. To tackle these issues, we propose a task-agnostic method called Dynamic Compressing Pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11004","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/2504.11004/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":"2026-07-05T10:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zX+O45Zwyn4HiGKlP8N89sJdKX2/5HCDRBoRFFF6xsMIB3pEenovGlxhyz3ZLRAQcFneHGzrjIYVZ2yCMdh5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:27:44.068301Z"},"content_sha256":"5a9f2109b613a32b6887097a97ea01a5689e613f36c12566a87f9ae63d6bc552","schema_version":"1.0","event_id":"sha256:5a9f2109b613a32b6887097a97ea01a5689e613f36c12566a87f9ae63d6bc552"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SA4SQBXD7J2GVLBKWQFVAW3YKA/bundle.json","state_url":"https://pith.science/pith/SA4SQBXD7J2GVLBKWQFVAW3YKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SA4SQBXD7J2GVLBKWQFVAW3YKA/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":"2026-08-18T15:27:44Z","links":{"resolver":"https://pith.science/pith/SA4SQBXD7J2GVLBKWQFVAW3YKA","bundle":"https://pith.science/pith/SA4SQBXD7J2GVLBKWQFVAW3YKA/bundle.json","state":"https://pith.science/pith/SA4SQBXD7J2GVLBKWQFVAW3YKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SA4SQBXD7J2GVLBKWQFVAW3YKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SA4SQBXD7J2GVLBKWQFVAW3YKA","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":"07d105066c546dc9dbd4b6248830afcf7a6ed6b9eacd30924f927a2b6fa0458d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T09:20:45Z","title_canon_sha256":"e62dd0dfa6d813643a45374eafe75612533f08bb347adf9479da7440244c2cf2"},"schema_version":"1.0","source":{"id":"2504.11004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11004","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11004v1","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11004","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"SA4SQBXD7J2G","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_16","alias_value":"SA4SQBXD7J2GVLBK","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_8","alias_value":"SA4SQBXD","created_at":"2026-07-05T10:49:27Z"}],"graph_snapshots":[{"event_id":"sha256:5a9f2109b613a32b6887097a97ea01a5689e613f36c12566a87f9ae63d6bc552","target":"graph","created_at":"2026-07-05T10:49:27Z","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/2504.11004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown outstanding performance across a variety of tasks, partly due to advanced prompting techniques. However, these techniques often require lengthy prompts, which increase computational costs and can hinder performance because of the limited context windows of LLMs. While prompt compression is a straightforward solution, existing methods confront the challenges of retaining essential information, adapting to context changes, and remaining effective across different tasks. To tackle these issues, we propose a task-agnostic method called Dynamic Compressing Pr","authors_text":"Bin Xiao, Jinwu Hu, Mingkui Tan, Qing Du, Wei Zhang, Yufeng Wang, Yu Hu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T09:20:45Z","title":"Dynamic Compressing Prompts for Efficient Inference of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11004","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":"sha256:89be45db20331d28a58f00016ccd68b4db5ae25654fe5bbce45c4dd850b5fcde","target":"record","created_at":"2026-07-05T10:49:27Z","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":"07d105066c546dc9dbd4b6248830afcf7a6ed6b9eacd30924f927a2b6fa0458d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T09:20:45Z","title_canon_sha256":"e62dd0dfa6d813643a45374eafe75612533f08bb347adf9479da7440244c2cf2"},"schema_version":"1.0","source":{"id":"2504.11004","kind":"arxiv","version":1}},"canonical_sha256":"90392806e3fa746aac2ab40b505b78500b5e8178de118802cf3576ebec90c099","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90392806e3fa746aac2ab40b505b78500b5e8178de118802cf3576ebec90c099","first_computed_at":"2026-07-05T10:49:27.714354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:27.714354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QZWCEILjwEIo+sK7F3DZgRdy1tHukyyPJkDxqflZInfhMFUMRsTdQovQ5dohdMN63JFG4V0Yy7rKKIFfgpMqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:27.714885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89be45db20331d28a58f00016ccd68b4db5ae25654fe5bbce45c4dd850b5fcde","sha256:5a9f2109b613a32b6887097a97ea01a5689e613f36c12566a87f9ae63d6bc552"],"state_sha256":"45aaff501c213c0ab995ad308ca20307bbe1a307d4a3ab76bb7a9e8fe765a140"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d+4APeksHOuY9S36GAWlrwziwT7xETFMRfJSMnStCqSqs8eexhJZqqi1T2knX8WagnE1ZN25OKTqLA2XqvkfBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:27:44.082988Z","bundle_sha256":"cdaf9687853c3e060679da8b361632455d2f8c4d572d70833227fd7ab8aeb567"}}