{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QP5HLF4NYKNOCLZUKT3UO3SWCP","short_pith_number":"pith:QP5HLF4N","schema_version":"1.0","canonical_sha256":"83fa75978dc29ae12f3454f7476e5613e1971f80a797eed9a9cc54ad3130fc86","source":{"kind":"arxiv","id":"2607.11149","version":1},"attestation_state":"computed","paper":{"title":"The Hidden Footprint: Making Storage a First-Class Metric for LLM Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenglin Yu, Hongquan Gui, Hongxia Yang, Ming Li, Ying Yu","submitted_at":"2026-07-13T06:44:33Z","abstract_excerpt":"LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces. We introduce AgentFootprint, a cross-framework benchmark of post-run agent storage footprint. Its serialization-aware metric suite measures total retention, channel composition, duplication, growth, compressibility, and conversation-history reconstructability. It addresses a measurement trap: naive byte-level measurement understates duplication by an order of magnitude because database paging an"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.11149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T06:44:33Z","cross_cats_sorted":[],"title_canon_sha256":"c324ceb51e60fb92b5eb3269559de171da97ca831b9a7d11881ef5fa9eb4c861","abstract_canon_sha256":"c821cd5d4f7fe5aef3b0a0cdf2848fab614baf729eced6034dde0c865489a0a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:19.071264Z","signature_b64":"uUPMDV9wGJuvj9sZcwKucx8COzSrCVeBrzuK/YAuGRgBZojCGzftzgMsYIDXvjlNAG650MCaXXYTiQ1+tJUPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83fa75978dc29ae12f3454f7476e5613e1971f80a797eed9a9cc54ad3130fc86","last_reissued_at":"2026-07-14T01:22:19.070388Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:19.070388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Hidden Footprint: Making Storage a First-Class Metric for LLM Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenglin Yu, Hongquan Gui, Hongxia Yang, Ming Li, Ying Yu","submitted_at":"2026-07-13T06:44:33Z","abstract_excerpt":"LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces. We introduce AgentFootprint, a cross-framework benchmark of post-run agent storage footprint. Its serialization-aware metric suite measures total retention, channel composition, duplication, growth, compressibility, and conversation-history reconstructability. It addresses a measurement trap: naive byte-level measurement understates duplication by an order of magnitude because database paging an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11149","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/2607.11149/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.11149","created_at":"2026-07-14T01:22:19.070832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11149v1","created_at":"2026-07-14T01:22:19.070832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11149","created_at":"2026-07-14T01:22:19.070832+00:00"},{"alias_kind":"pith_short_12","alias_value":"QP5HLF4NYKNO","created_at":"2026-07-14T01:22:19.070832+00:00"},{"alias_kind":"pith_short_16","alias_value":"QP5HLF4NYKNOCLZU","created_at":"2026-07-14T01:22:19.070832+00:00"},{"alias_kind":"pith_short_8","alias_value":"QP5HLF4N","created_at":"2026-07-14T01:22:19.070832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QP5HLF4NYKNOCLZUKT3UO3SWCP","json":"https://pith.science/pith/QP5HLF4NYKNOCLZUKT3UO3SWCP.json","graph_json":"https://pith.science/api/pith-number/QP5HLF4NYKNOCLZUKT3UO3SWCP/graph.json","events_json":"https://pith.science/api/pith-number/QP5HLF4NYKNOCLZUKT3UO3SWCP/events.json","paper":"https://pith.science/paper/QP5HLF4N"},"agent_actions":{"view_html":"https://pith.science/pith/QP5HLF4NYKNOCLZUKT3UO3SWCP","download_json":"https://pith.science/pith/QP5HLF4NYKNOCLZUKT3UO3SWCP.json","view_paper":"https://pith.science/paper/QP5HLF4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11149&json=true","fetch_graph":"https://pith.science/api/pith-number/QP5HLF4NYKNOCLZUKT3UO3SWCP/graph.json","fetch_events":"https://pith.science/api/pith-number/QP5HLF4NYKNOCLZUKT3UO3SWCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QP5HLF4NYKNOCLZUKT3UO3SWCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QP5HLF4NYKNOCLZUKT3UO3SWCP/action/storage_attestation","attest_author":"https://pith.science/pith/QP5HLF4NYKNOCLZUKT3UO3SWCP/action/author_attestation","sign_citation":"https://pith.science/pith/QP5HLF4NYKNOCLZUKT3UO3SWCP/action/citation_signature","submit_replication":"https://pith.science/pith/QP5HLF4NYKNOCLZUKT3UO3SWCP/action/replication_record"}},"created_at":"2026-07-14T01:22:19.070832+00:00","updated_at":"2026-07-14T01:22:19.070832+00:00"}