{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_2f23cc98162f2e352b154a13d6e8bc9738a6da4ef931f6fd7a2b11e01610f1f1","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_2f23cc98162f2e352b154a13d6e8bc9738a6da4ef931f6fd7a2b11e01610f1f1","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"4034fea234d1ff113c447613ca5bd56e0f0cb9d0d3f834b8a6bf8013baa78e62","published":"Mon, 20 Jul 2026 00:00:00 -0400","receipt_hash":"4034fea234d1ff113c447613ca5bd56e0f0cb9d0d3f834b8a6bf8013baa78e62","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"4034fea234d1ff113c447613ca5bd56e0f0cb9d0d3f834b8a6bf8013baa78e62","observed_at":"2026-07-20T04:43:09.641409Z","parent_run_hash":"0fd83663f0f57da59b26313ca1a35283a3e9f06e3165d3e143d26f7174743aca","published":"Mon, 20 Jul 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2607.15516v1 Announce Type: cross \nAbstract: Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent). The compression literature has standardized on query-aware methods that produce a different compressed prefix per query, mechanically invalidating the prefix-strict cache on every call. We characterize this cost empirically on Anthropic's Sonnet 4.6 API and find caching is far from the rho=1.0 ideal the literature assumes: Sonnet's cache has a two-tier architecture with a sharp threshold near 3,500 tokens, below which the hit rate plateaus at rho~0.83 across 30-call sessions. Our cost model predicts, and experiments confirm, that under realistic rho, query-aware compression beats naive caching at high compression ratios (r>=6). We propose Cache-Aware Prompt Compression (CAPC), pairing query-agnostic compression with explicit cache_control plus a tier-preserving ratio","title":"Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching","url":"https://arxiv.org/abs/2607.15516","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.15516v1 Announce Type: cross \nAbstract: Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent). The compression literature has standardized on query-aware methods that produce a different compressed prefix per query, mechanically invalidating the prefix-strict cache on every call. We characterize this cost empirically on Anthropic's Sonnet 4.6 API and find caching is far from the rho=1.0 ideal the literature assumes: Sonnet's cache has a two-tier architecture with a sharp threshold near 3,500 tokens, below which the hit rate plateaus at rho~0.83 across 30-call sessions. Our cost model predicts, and experiments confirm, that under realistic rho, query-aware compression beats naive caching at high compression ratios (r>=6). We propose Cache-Aware Prompt Compression (CAPC), pairing query-agnostic compression with explicit cache_control plus a tier-preserving ratio","title":"Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-20T04:43:09Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.15516"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:de6b867b43efc27ec28bb14996727e860cdea5dcd7ff67ffe2292cfd58669122aa7337e06515b70707d5de0fc65bda602cfab1b46d1dfabdb301534ec5454d0d","signer":"crovia.substrate","subject":{"observed_at":"2026-07-20T04:43:09Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.15516"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"bedca7eb4472834e7abb649648af56f0e06b9f057da36bf8ea10059718a52e92","leaf_index":333268,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"223e0e611acb492813af5a1c14861859d613ffaae571353941121a8cbfbbbd94","side":"right"},{"sibling":"d1c840cbbcb58212501f3d95b1124d916674aa19f7bb41f53c71e361c0cc6ed3","side":"right"},{"sibling":"31c9d07817765983b205f25b42195e55d594aa528a3287b1ba13e1f2958d15f7","side":"left"},{"sibling":"f09499fa4b2102c1530141de09298c2d70cbde8eb928d5dff565792be99018f1","side":"right"},{"sibling":"16d1f04aa809a89365e36d82a45301ebe65d517802f2d7a0c2fb8a7c9540ebd6","side":"left"},{"sibling":"a8dc77c640e00bc49c83f5d77a06c176d74fd93fb2d7b210bc761852297a756a","side":"right"},{"sibling":"5dc3f0df8fd6e4cf655b15e7355878576934a564ddee081917870d5b8bcd2ec0","side":"left"},{"sibling":"5e895feb6aeddb3dac892d493e1de271cf5bb255124626b8ae869ebb57ff0c74","side":"left"},{"sibling":"089fcaa13823a284a9c3064c9de337dded31410d6f89ef3761586a5e77c18ff1","side":"left"},{"sibling":"b0d667e95f8746ac275ad4169634f2e9442cd7e445099c6355bed5e0b9e27cbf","side":"right"},{"sibling":"dedd2da92d9447ddf1b1db68fe20109a426ed18359861ed746907ac820021a8d","side":"left"},{"sibling":"a1c43cc7cd9c775fac33940ee5124aece01596733f003fc53743f43483f9f597","side":"right"},{"sibling":"b5ad3eafd7eeb74c063261356fdd9bf6059ee6d0bf1e3c70e60731b394a5536e","side":"left"},{"sibling":"93e399d152203db688c6a5a58d25131205603504f5b79123a1f2b5a5ed9c1e54","side":"right"},{"sibling":"b6e0cad7f6eb9107f0edd276f1a9942635d8cd6d60d2a97e7daac08b110dc209","side":"right"},{"sibling":"80ec062e7e625dc3f9bb5865cb5198696bbec2608e48abae5670677b90695899","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"0aced6f0c9dec3e6cc9e89b68b70f5f8ce7e1eb13606d92db1917b76e57393c7","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":333540,"merkle_root":"ee60f62b8a724dd9bde638d638caf32cefec4440f832018b457ff47a0ec56a8c","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260720T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-20T05:38:36Z","sig_algorithm":"ed25519","signature":"82a3787e628bfab19c377d875220e1aaedfc498736c545f4708a1b887e8398afdf306995994493a36c864ff7139a2d436b905ce7081aaa540789aa4f707dc800","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_2f23cc98162f2e352b154a13d6e8bc9738a6da4ef931f6fd7a2b11e01610f1f1"}}