{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TEA7QB2FZCYKWJIOFPSFHT3GIG","short_pith_number":"pith:TEA7QB2F","canonical_record":{"source":{"id":"2305.11186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T20:45:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1e213ac8336dc0a682006ea662d320f5e5c8a5f2ff1c226dabce4875583d6e9b","abstract_canon_sha256":"68b5b8ea9b3d60cc31d9d9092027141f2033fc6ef833fa7b9447182cf183e1af"},"schema_version":"1.0"},"canonical_sha256":"9901f80745c8b0ab250e2be453cf66419fb77159485a7b464e1e7349b771bf83","source":{"kind":"arxiv","id":"2305.11186","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11186","created_at":"2026-07-05T06:58:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11186v2","created_at":"2026-07-05T06:58:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11186","created_at":"2026-07-05T06:58:56Z"},{"alias_kind":"pith_short_12","alias_value":"TEA7QB2FZCYK","created_at":"2026-07-05T06:58:56Z"},{"alias_kind":"pith_short_16","alias_value":"TEA7QB2FZCYKWJIO","created_at":"2026-07-05T06:58:56Z"},{"alias_kind":"pith_short_8","alias_value":"TEA7QB2F","created_at":"2026-07-05T06:58:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TEA7QB2FZCYKWJIOFPSFHT3GIG","target":"record","payload":{"canonical_record":{"source":{"id":"2305.11186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T20:45:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1e213ac8336dc0a682006ea662d320f5e5c8a5f2ff1c226dabce4875583d6e9b","abstract_canon_sha256":"68b5b8ea9b3d60cc31d9d9092027141f2033fc6ef833fa7b9447182cf183e1af"},"schema_version":"1.0"},"canonical_sha256":"9901f80745c8b0ab250e2be453cf66419fb77159485a7b464e1e7349b771bf83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:56.693694Z","signature_b64":"IA+JEB212BbPrMNnx1QeyO3ETz334cMDUXP7gHwSQga6QPanOUM6fp2qU18NY6OhHU+KQGsSB7cPHYNe5242Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9901f80745c8b0ab250e2be453cf66419fb77159485a7b464e1e7349b771bf83","last_reissued_at":"2026-07-05T06:58:56.693269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:56.693269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.11186","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":"2026-07-05T06:58:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDc5vXJykGMTrZzwbB2MNFrvDc1QPtVDIjDj75Qznlmgms+6vZ4+ij+PerHGuS+1RL8ibWo2V2/XrfHaX/ynBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:26:22.096191Z"},"content_sha256":"828d71c620e8c777d18f075baff10f6911a74683e1feb0c2354bf1e9f45c8bb4","schema_version":"1.0","event_id":"sha256:828d71c620e8c777d18f075baff10f6911a74683e1feb0c2354bf1e9f45c8bb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TEA7QB2FZCYKWJIOFPSFHT3GIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anshumali Shrivastava, Beidi Chen, Jue Wang, Kaixiong Zhou, Xia Hu, Yuxin Tang, Zhaozhuo Xu, Zirui Liu","submitted_at":"2023-05-17T20:45:13Z","abstract_excerpt":"While the numerous parameters in Large Language Models (LLMs) contribute to their superior performance, this massive scale makes them inefficient and memory-hungry. Thus, they are hard to deploy on commodity hardware, such as one single GPU. Given the memory and power constraints of such devices, model compression methods are widely employed to reduce both the model size and inference latency, which essentially trades off model quality in return for improved efficiency. Thus, optimizing this accuracy-efficiency trade-off is crucial for the LLM deployment on commodity hardware. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11186","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/2305.11186/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":"2026-07-05T06:58:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g69DxS9hwulYMJLe02+y3B2h/fMvwYYczmDtSXuhf4zdpoY6H3f/pDQb0e+HyeMVU66RnAAF51PUCxHBbI6IDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:26:22.096705Z"},"content_sha256":"916801ab24cdeaf45cbe5161fbfe77a0e86f9b98d2eec931e230c24c2052b340","schema_version":"1.0","event_id":"sha256:916801ab24cdeaf45cbe5161fbfe77a0e86f9b98d2eec931e230c24c2052b340"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TEA7QB2FZCYKWJIOFPSFHT3GIG/bundle.json","state_url":"https://pith.science/pith/TEA7QB2FZCYKWJIOFPSFHT3GIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TEA7QB2FZCYKWJIOFPSFHT3GIG/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":"2026-08-08T21:26:22Z","links":{"resolver":"https://pith.science/pith/TEA7QB2FZCYKWJIOFPSFHT3GIG","bundle":"https://pith.science/pith/TEA7QB2FZCYKWJIOFPSFHT3GIG/bundle.json","state":"https://pith.science/pith/TEA7QB2FZCYKWJIOFPSFHT3GIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TEA7QB2FZCYKWJIOFPSFHT3GIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TEA7QB2FZCYKWJIOFPSFHT3GIG","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":"68b5b8ea9b3d60cc31d9d9092027141f2033fc6ef833fa7b9447182cf183e1af","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T20:45:13Z","title_canon_sha256":"1e213ac8336dc0a682006ea662d320f5e5c8a5f2ff1c226dabce4875583d6e9b"},"schema_version":"1.0","source":{"id":"2305.11186","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11186","created_at":"2026-07-05T06:58:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11186v2","created_at":"2026-07-05T06:58:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11186","created_at":"2026-07-05T06:58:56Z"},{"alias_kind":"pith_short_12","alias_value":"TEA7QB2FZCYK","created_at":"2026-07-05T06:58:56Z"},{"alias_kind":"pith_short_16","alias_value":"TEA7QB2FZCYKWJIO","created_at":"2026-07-05T06:58:56Z"},{"alias_kind":"pith_short_8","alias_value":"TEA7QB2F","created_at":"2026-07-05T06:58:56Z"}],"graph_snapshots":[{"event_id":"sha256:916801ab24cdeaf45cbe5161fbfe77a0e86f9b98d2eec931e230c24c2052b340","target":"graph","created_at":"2026-07-05T06:58:56Z","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/2305.11186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While the numerous parameters in Large Language Models (LLMs) contribute to their superior performance, this massive scale makes them inefficient and memory-hungry. Thus, they are hard to deploy on commodity hardware, such as one single GPU. Given the memory and power constraints of such devices, model compression methods are widely employed to reduce both the model size and inference latency, which essentially trades off model quality in return for improved efficiency. Thus, optimizing this accuracy-efficiency trade-off is crucial for the LLM deployment on commodity hardware. In this paper, w","authors_text":"Anshumali Shrivastava, Beidi Chen, Jue Wang, Kaixiong Zhou, Xia Hu, Yuxin Tang, Zhaozhuo Xu, Zirui Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T20:45:13Z","title":"Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11186","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":"sha256:828d71c620e8c777d18f075baff10f6911a74683e1feb0c2354bf1e9f45c8bb4","target":"record","created_at":"2026-07-05T06:58:56Z","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":"68b5b8ea9b3d60cc31d9d9092027141f2033fc6ef833fa7b9447182cf183e1af","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T20:45:13Z","title_canon_sha256":"1e213ac8336dc0a682006ea662d320f5e5c8a5f2ff1c226dabce4875583d6e9b"},"schema_version":"1.0","source":{"id":"2305.11186","kind":"arxiv","version":2}},"canonical_sha256":"9901f80745c8b0ab250e2be453cf66419fb77159485a7b464e1e7349b771bf83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9901f80745c8b0ab250e2be453cf66419fb77159485a7b464e1e7349b771bf83","first_computed_at":"2026-07-05T06:58:56.693269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:56.693269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IA+JEB212BbPrMNnx1QeyO3ETz334cMDUXP7gHwSQga6QPanOUM6fp2qU18NY6OhHU+KQGsSB7cPHYNe5242Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:56.693694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11186","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:828d71c620e8c777d18f075baff10f6911a74683e1feb0c2354bf1e9f45c8bb4","sha256:916801ab24cdeaf45cbe5161fbfe77a0e86f9b98d2eec931e230c24c2052b340"],"state_sha256":"50da5f3f995722d10da5d038c1815d6eef8556288cb3bd785beb74758f19267c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a/yXC4gC7DjCB6NjwJTwKbOnh4t6lGivucBQhMCz6JTVx/7Q96IlTStJELTolKO2gwyAmGkw5et92Z859n4XAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:26:22.100865Z","bundle_sha256":"647e0a7a7c6a75c267360026578c8c7b88bd0de9d9e566960070601bfc744794"}}