{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4ADTH7PIS3BZG2OPQMLC2OIYZZ","short_pith_number":"pith:4ADTH7PI","canonical_record":{"source":{"id":"2607.08964","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T21:56:37Z","cross_cats_sorted":[],"title_canon_sha256":"4135207d0342336a5bf7fe52755d32f4499f6d0e4d3ceac8d307496353d448b6","abstract_canon_sha256":"0e7f95d6b75c53e64d0cfef1ea1f3593ff9eb53a3bcb54e82d6f99e87887620e"},"schema_version":"1.0"},"canonical_sha256":"e00733fde896c39369cf83162d3918ce608b34677b9ae93604d0d32bea26d6a6","source":{"kind":"arxiv","id":"2607.08964","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08964","created_at":"2026-07-13T00:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08964v1","created_at":"2026-07-13T00:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08964","created_at":"2026-07-13T00:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"4ADTH7PIS3BZ","created_at":"2026-07-13T00:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"4ADTH7PIS3BZG2OP","created_at":"2026-07-13T00:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"4ADTH7PI","created_at":"2026-07-13T00:17:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4ADTH7PIS3BZG2OPQMLC2OIYZZ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.08964","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T21:56:37Z","cross_cats_sorted":[],"title_canon_sha256":"4135207d0342336a5bf7fe52755d32f4499f6d0e4d3ceac8d307496353d448b6","abstract_canon_sha256":"0e7f95d6b75c53e64d0cfef1ea1f3593ff9eb53a3bcb54e82d6f99e87887620e"},"schema_version":"1.0"},"canonical_sha256":"e00733fde896c39369cf83162d3918ce608b34677b9ae93604d0d32bea26d6a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:30.454811Z","signature_b64":"uaks/b8GMNGp1wBVXCFZnZEnKzKlOwsd1xcqm1hcvIsBfR6Ybdi0JtaXNR4OtRMkQS6JiI5aQGDxaHPqm/nDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e00733fde896c39369cf83162d3918ce608b34677b9ae93604d0d32bea26d6a6","last_reissued_at":"2026-07-13T00:17:30.453435Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:30.453435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.08964","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":"2026-07-13T00:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qcwxIZAptKzO6Qv5LSBrAVcoTdJwaElcI6DzQzvadPXgHgRLTTjdglxLkD+Ke61HB4Qr1BueIlqZLynUj+4EAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:21:55.897288Z"},"content_sha256":"4dc9716b8f4745505b97f335ba0883b4f76e26738ee6228be61fdbfd54d9e8de","schema_version":"1.0","event_id":"sha256:4dc9716b8f4745505b97f335ba0883b4f76e26738ee6228be61fdbfd54d9e8de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4ADTH7PIS3BZG2OPQMLC2OIYZZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anhao Li, Haotao Mi, Junyao Yang, Leoweiliang, Lichao Sun, Ninghao Liu, Ruhan Wang, Xiyang Wu, Yucheng Shi, Yue Yu, Zhichao Liu, Zhongzhi Li, Zongxia Li","submitted_at":"2026-07-09T21:56:37Z","abstract_excerpt":"AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome. This setup overlooks intermediate progress and partial solutions, yielding sparse reward signals and an incomplete picture of agent capability. We introduce Long-Horizon-Terminal-Bench, a terminal benchmark of 46 long-horizon tasks spanning nine categories, including experiment reproduction, software engineering, multimodal analysis, interactive games, and scientific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08964","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/2607.08964/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":"2026-07-13T00:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rlw44kR9gr3ihNppmoby/Dvfo3Rab++I/LLz8qlNszH3aDE1eFQT2KLiR6RBTjcILuFu6caDTOVYhuwJrqBZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:21:55.897860Z"},"content_sha256":"26a8ae32d2425c102034f271ca085d54ef5f2e06f00538af624eeb36fdae848d","schema_version":"1.0","event_id":"sha256:26a8ae32d2425c102034f271ca085d54ef5f2e06f00538af624eeb36fdae848d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ADTH7PIS3BZG2OPQMLC2OIYZZ/bundle.json","state_url":"https://pith.science/pith/4ADTH7PIS3BZG2OPQMLC2OIYZZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ADTH7PIS3BZG2OPQMLC2OIYZZ/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":"2026-08-03T18:21:55Z","links":{"resolver":"https://pith.science/pith/4ADTH7PIS3BZG2OPQMLC2OIYZZ","bundle":"https://pith.science/pith/4ADTH7PIS3BZG2OPQMLC2OIYZZ/bundle.json","state":"https://pith.science/pith/4ADTH7PIS3BZG2OPQMLC2OIYZZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ADTH7PIS3BZG2OPQMLC2OIYZZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4ADTH7PIS3BZG2OPQMLC2OIYZZ","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":"0e7f95d6b75c53e64d0cfef1ea1f3593ff9eb53a3bcb54e82d6f99e87887620e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T21:56:37Z","title_canon_sha256":"4135207d0342336a5bf7fe52755d32f4499f6d0e4d3ceac8d307496353d448b6"},"schema_version":"1.0","source":{"id":"2607.08964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08964","created_at":"2026-07-13T00:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08964v1","created_at":"2026-07-13T00:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08964","created_at":"2026-07-13T00:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"4ADTH7PIS3BZ","created_at":"2026-07-13T00:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"4ADTH7PIS3BZG2OP","created_at":"2026-07-13T00:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"4ADTH7PI","created_at":"2026-07-13T00:17:30Z"}],"graph_snapshots":[{"event_id":"sha256:26a8ae32d2425c102034f271ca085d54ef5f2e06f00538af624eeb36fdae848d","target":"graph","created_at":"2026-07-13T00:17:30Z","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/2607.08964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome. This setup overlooks intermediate progress and partial solutions, yielding sparse reward signals and an incomplete picture of agent capability. We introduce Long-Horizon-Terminal-Bench, a terminal benchmark of 46 long-horizon tasks spanning nine categories, including experiment reproduction, software engineering, multimodal analysis, interactive games, and scientific","authors_text":"Anhao Li, Haotao Mi, Junyao Yang, Leoweiliang, Lichao Sun, Ninghao Liu, Ruhan Wang, Xiyang Wu, Yucheng Shi, Yue Yu, Zhichao Liu, Zhongzhi Li, Zongxia Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T21:56:37Z","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08964","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":"sha256:4dc9716b8f4745505b97f335ba0883b4f76e26738ee6228be61fdbfd54d9e8de","target":"record","created_at":"2026-07-13T00:17:30Z","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":"0e7f95d6b75c53e64d0cfef1ea1f3593ff9eb53a3bcb54e82d6f99e87887620e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T21:56:37Z","title_canon_sha256":"4135207d0342336a5bf7fe52755d32f4499f6d0e4d3ceac8d307496353d448b6"},"schema_version":"1.0","source":{"id":"2607.08964","kind":"arxiv","version":1}},"canonical_sha256":"e00733fde896c39369cf83162d3918ce608b34677b9ae93604d0d32bea26d6a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e00733fde896c39369cf83162d3918ce608b34677b9ae93604d0d32bea26d6a6","first_computed_at":"2026-07-13T00:17:30.453435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:30.453435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uaks/b8GMNGp1wBVXCFZnZEnKzKlOwsd1xcqm1hcvIsBfR6Ybdi0JtaXNR4OtRMkQS6JiI5aQGDxaHPqm/nDCA==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:30.454811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4dc9716b8f4745505b97f335ba0883b4f76e26738ee6228be61fdbfd54d9e8de","sha256:26a8ae32d2425c102034f271ca085d54ef5f2e06f00538af624eeb36fdae848d"],"state_sha256":"24b6757db1a92d9cc900033f1314b364896b9af511ed9fbfea89bebe581b551b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dn2UnQHADNBxR6CO4Sp6lDJYbVZOOTwVXj6qfRhvBR7Inj+qa0rU/O8HcstcTkbOoas4UTl4Z3y8ILq7g5yCBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:21:55.902690Z","bundle_sha256":"4a07b2c0a1251d31efd31aabed61903e435f1be89589fb250f9a074dd93a9e2a"}}