{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:I2ABPB5Q2GUL7BRG3NBYKCDQVI","short_pith_number":"pith:I2ABPB5Q","canonical_record":{"source":{"id":"2608.01347","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:10:02Z","cross_cats_sorted":[],"title_canon_sha256":"4fa7819aa660b360b797304279f758bd8684289e60cecc383b3150336e523c12","abstract_canon_sha256":"1ecf121474480551235578dfec0edab4aa3954198bb0ca6dcf8f39be288f737f"},"schema_version":"1.0"},"canonical_sha256":"46801787b0d1a8bf8626db43850870aa3e27b9a689a9b9157926e7def9c7b49a","source":{"kind":"arxiv","id":"2608.01347","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01347","created_at":"2026-08-04T02:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01347v1","created_at":"2026-08-04T02:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01347","created_at":"2026-08-04T02:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"I2ABPB5Q2GUL","created_at":"2026-08-04T02:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"I2ABPB5Q2GUL7BRG","created_at":"2026-08-04T02:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"I2ABPB5Q","created_at":"2026-08-04T02:04:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:I2ABPB5Q2GUL7BRG3NBYKCDQVI","target":"record","payload":{"canonical_record":{"source":{"id":"2608.01347","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:10:02Z","cross_cats_sorted":[],"title_canon_sha256":"4fa7819aa660b360b797304279f758bd8684289e60cecc383b3150336e523c12","abstract_canon_sha256":"1ecf121474480551235578dfec0edab4aa3954198bb0ca6dcf8f39be288f737f"},"schema_version":"1.0"},"canonical_sha256":"46801787b0d1a8bf8626db43850870aa3e27b9a689a9b9157926e7def9c7b49a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:04:37.327703Z","signature_b64":"AwD9rtj+VoDdBxc3VnqtRGkUTjHwzIc1cIWO2I89STcMj2v/l4gZtVvbKfctcN5RvhQW4M7xHHO66+FQlL3ODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46801787b0d1a8bf8626db43850870aa3e27b9a689a9b9157926e7def9c7b49a","last_reissued_at":"2026-08-04T02:04:37.325864Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:04:37.325864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.01347","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":"2026-08-04T02:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TrYFIlEv+2amI+1aP1ijvswPf3TDEOawA+9H4Vs8y7kz8crvSpbsyVnTEVOVyPj6mWjkA14x00UICkjBMQeDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:48:43.223986Z"},"content_sha256":"0aeb72f15cb56cb998894dc99a98a49c448fbb60eccf57bb61f19a4fc0d872cd","schema_version":"1.0","event_id":"sha256:0aeb72f15cb56cb998894dc99a98a49c448fbb60eccf57bb61f19a4fc0d872cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:I2ABPB5Q2GUL7BRG3NBYKCDQVI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompt-Induced Waste in Large Reasoning Models: A Preregistered Two-Harness Benchmark of Coding Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Hozez, Sarel Weinberger","submitted_at":"2026-08-02T16:10:02Z","abstract_excerpt":"Large reasoning models used as coding agents incur costs from deliberation, tool calls, and repeated agent turns, yet the causal effect of prompt wording on this spend has not been measured systematically. We present a preregistered benchmark across six large reasoning models, two real agent harnesses, and 24 deterministic coding tasks with hidden evaluators. Across 4,643 valid runs, including screening, stress, holdout, replication, and cross-provider studies, we find that prompt formulation can multiply reasoning cost without improving correctness. Asking the model to develop and compare sev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01347","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/2608.01347/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":"2026-08-04T02:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DIxNMSGg0SeHesadOEvjx7h+IeoXcu9XbgE2Ql6CTDhNFRMZ2s6QHjcsodcIMSOly/MbggnE6K6TQ3JkMld0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:48:43.224511Z"},"content_sha256":"2a89f614ebc41dfcf50bf51d0585cde389d1099c9f3aef400c55bd43204d4fed","schema_version":"1.0","event_id":"sha256:2a89f614ebc41dfcf50bf51d0585cde389d1099c9f3aef400c55bd43204d4fed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I2ABPB5Q2GUL7BRG3NBYKCDQVI/bundle.json","state_url":"https://pith.science/pith/I2ABPB5Q2GUL7BRG3NBYKCDQVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I2ABPB5Q2GUL7BRG3NBYKCDQVI/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":"2026-08-06T15:48:43Z","links":{"resolver":"https://pith.science/pith/I2ABPB5Q2GUL7BRG3NBYKCDQVI","bundle":"https://pith.science/pith/I2ABPB5Q2GUL7BRG3NBYKCDQVI/bundle.json","state":"https://pith.science/pith/I2ABPB5Q2GUL7BRG3NBYKCDQVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I2ABPB5Q2GUL7BRG3NBYKCDQVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I2ABPB5Q2GUL7BRG3NBYKCDQVI","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":"1ecf121474480551235578dfec0edab4aa3954198bb0ca6dcf8f39be288f737f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:10:02Z","title_canon_sha256":"4fa7819aa660b360b797304279f758bd8684289e60cecc383b3150336e523c12"},"schema_version":"1.0","source":{"id":"2608.01347","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01347","created_at":"2026-08-04T02:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01347v1","created_at":"2026-08-04T02:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01347","created_at":"2026-08-04T02:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"I2ABPB5Q2GUL","created_at":"2026-08-04T02:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"I2ABPB5Q2GUL7BRG","created_at":"2026-08-04T02:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"I2ABPB5Q","created_at":"2026-08-04T02:04:37Z"}],"graph_snapshots":[{"event_id":"sha256:2a89f614ebc41dfcf50bf51d0585cde389d1099c9f3aef400c55bd43204d4fed","target":"graph","created_at":"2026-08-04T02:04:37Z","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/2608.01347/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large reasoning models used as coding agents incur costs from deliberation, tool calls, and repeated agent turns, yet the causal effect of prompt wording on this spend has not been measured systematically. We present a preregistered benchmark across six large reasoning models, two real agent harnesses, and 24 deterministic coding tasks with hidden evaluators. Across 4,643 valid runs, including screening, stress, holdout, replication, and cross-provider studies, we find that prompt formulation can multiply reasoning cost without improving correctness. Asking the model to develop and compare sev","authors_text":"Amir Hozez, Sarel Weinberger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:10:02Z","title":"Prompt-Induced Waste in Large Reasoning Models: A Preregistered Two-Harness Benchmark of Coding Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01347","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":"sha256:0aeb72f15cb56cb998894dc99a98a49c448fbb60eccf57bb61f19a4fc0d872cd","target":"record","created_at":"2026-08-04T02:04:37Z","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":"1ecf121474480551235578dfec0edab4aa3954198bb0ca6dcf8f39be288f737f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:10:02Z","title_canon_sha256":"4fa7819aa660b360b797304279f758bd8684289e60cecc383b3150336e523c12"},"schema_version":"1.0","source":{"id":"2608.01347","kind":"arxiv","version":1}},"canonical_sha256":"46801787b0d1a8bf8626db43850870aa3e27b9a689a9b9157926e7def9c7b49a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46801787b0d1a8bf8626db43850870aa3e27b9a689a9b9157926e7def9c7b49a","first_computed_at":"2026-08-04T02:04:37.325864Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:04:37.325864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AwD9rtj+VoDdBxc3VnqtRGkUTjHwzIc1cIWO2I89STcMj2v/l4gZtVvbKfctcN5RvhQW4M7xHHO66+FQlL3ODA==","signature_status":"signed_v1","signed_at":"2026-08-04T02:04:37.327703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01347","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0aeb72f15cb56cb998894dc99a98a49c448fbb60eccf57bb61f19a4fc0d872cd","sha256:2a89f614ebc41dfcf50bf51d0585cde389d1099c9f3aef400c55bd43204d4fed"],"state_sha256":"2757ba9bc8b2f66d4975f6e929121bc32ea033e635072e70d659e2be41ca1544"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WmJv8pr4AMaKH7iNL/uC0LDjfeS/RInrL+qREVeTdBRMIf0lbU7VDyNSXFyaDjtr5OtI29MVnj5ocxO2e/F2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:48:43.228613Z","bundle_sha256":"683fb03e00d36316992bb15429284484bac446631fca32ece2efccb0bc51aa1f"}}