{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EJ7ZPREHXX3HEU6BKMREMQWVCK","short_pith_number":"pith:EJ7ZPREH","canonical_record":{"source":{"id":"2607.28098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T05:08:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e666ba408183f3daea89a17220d9780556f120cc10b7fcce98d1253b72dc2a0f","abstract_canon_sha256":"9376fb5755b364aca308067c23335adfd4b2bb454e80ab09d991ca5cfb3f9306"},"schema_version":"1.0"},"canonical_sha256":"227f97c487bdf67253c153224642d512a4a438d03d10635547485182193c0f96","source":{"kind":"arxiv","id":"2607.28098","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28098","created_at":"2026-07-31T01:35:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28098v1","created_at":"2026-07-31T01:35:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28098","created_at":"2026-07-31T01:35:44Z"},{"alias_kind":"pith_short_12","alias_value":"EJ7ZPREHXX3H","created_at":"2026-07-31T01:35:44Z"},{"alias_kind":"pith_short_16","alias_value":"EJ7ZPREHXX3HEU6B","created_at":"2026-07-31T01:35:44Z"},{"alias_kind":"pith_short_8","alias_value":"EJ7ZPREH","created_at":"2026-07-31T01:35:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EJ7ZPREHXX3HEU6BKMREMQWVCK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T05:08:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e666ba408183f3daea89a17220d9780556f120cc10b7fcce98d1253b72dc2a0f","abstract_canon_sha256":"9376fb5755b364aca308067c23335adfd4b2bb454e80ab09d991ca5cfb3f9306"},"schema_version":"1.0"},"canonical_sha256":"227f97c487bdf67253c153224642d512a4a438d03d10635547485182193c0f96","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"227f97c487bdf67253c153224642d512a4a438d03d10635547485182193c0f96","last_reissued_at":"2026-07-31T01:35:44.963676Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:35:44.963676Z"},"source_kind":"arxiv","source_id":"2607.28098","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":"2026-07-31T01:35:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"te/2ZMCVvhLRrhMinzBu4zGl2UjFDGmkH1Z4+ohpbFFAjgZVeX+x85P+gOxhcrbzkcmuKF+M8ZCJb9CKbfI7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T12:39:35.578472Z"},"content_sha256":"9a000d5c98d965d1d6f0b9c6edc6d40b837e086532a7889e311d6a0916661b94","schema_version":"1.0","event_id":"sha256:9a000d5c98d965d1d6f0b9c6edc6d40b837e086532a7889e311d6a0916661b94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EJ7ZPREHXX3HEU6BKMREMQWVCK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SciDataSailor: Deep Scientific Data Exploring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chi Zhang, Chunfeng Song, Jiyong Rao, Runkai Zhao, Yicheng Qiu","submitted_at":"2026-07-29T05:08:21Z","abstract_excerpt":"Scientific datasets are commonly organized as hierarchical repositories containing heterogeneous and interdependent files, making their inspection, integration, and analysis labor-intensive and reliant on domain expertise. Although large language model (LLM) agents have advanced substantially in planning, reasoning, and tool use, existing research has largely overlooked their ability to interact with real scientific data assets through executable environments. We introduce Deep Scientific Data Exploration, an agentic task paradigm in which agents navigate repositories, interpret heterogeneous "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28098","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/2607.28098/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":"2026-07-31T01:35:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ThNTAvdlDVaDWZNQeI0dHxSM05iFKohBtrR5cBiMVMm32GL2MQO73ygtSE569bJ9+b4bNTYnj+/TBnSMqzrjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T12:39:35.579039Z"},"content_sha256":"9ad96e2d03332cebc429d22256c8e0fd0e04da3dd33d4ca1b090e01380937cd7","schema_version":"1.0","event_id":"sha256:9ad96e2d03332cebc429d22256c8e0fd0e04da3dd33d4ca1b090e01380937cd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EJ7ZPREHXX3HEU6BKMREMQWVCK/bundle.json","state_url":"https://pith.science/pith/EJ7ZPREHXX3HEU6BKMREMQWVCK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EJ7ZPREHXX3HEU6BKMREMQWVCK/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":"2026-08-03T12:39:35Z","links":{"resolver":"https://pith.science/pith/EJ7ZPREHXX3HEU6BKMREMQWVCK","bundle":"https://pith.science/pith/EJ7ZPREHXX3HEU6BKMREMQWVCK/bundle.json","state":"https://pith.science/pith/EJ7ZPREHXX3HEU6BKMREMQWVCK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EJ7ZPREHXX3HEU6BKMREMQWVCK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EJ7ZPREHXX3HEU6BKMREMQWVCK","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":"9376fb5755b364aca308067c23335adfd4b2bb454e80ab09d991ca5cfb3f9306","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T05:08:21Z","title_canon_sha256":"e666ba408183f3daea89a17220d9780556f120cc10b7fcce98d1253b72dc2a0f"},"schema_version":"1.0","source":{"id":"2607.28098","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28098","created_at":"2026-07-31T01:35:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28098v1","created_at":"2026-07-31T01:35:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28098","created_at":"2026-07-31T01:35:44Z"},{"alias_kind":"pith_short_12","alias_value":"EJ7ZPREHXX3H","created_at":"2026-07-31T01:35:44Z"},{"alias_kind":"pith_short_16","alias_value":"EJ7ZPREHXX3HEU6B","created_at":"2026-07-31T01:35:44Z"},{"alias_kind":"pith_short_8","alias_value":"EJ7ZPREH","created_at":"2026-07-31T01:35:44Z"}],"graph_snapshots":[{"event_id":"sha256:9ad96e2d03332cebc429d22256c8e0fd0e04da3dd33d4ca1b090e01380937cd7","target":"graph","created_at":"2026-07-31T01:35:44Z","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/2607.28098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scientific datasets are commonly organized as hierarchical repositories containing heterogeneous and interdependent files, making their inspection, integration, and analysis labor-intensive and reliant on domain expertise. Although large language model (LLM) agents have advanced substantially in planning, reasoning, and tool use, existing research has largely overlooked their ability to interact with real scientific data assets through executable environments. We introduce Deep Scientific Data Exploration, an agentic task paradigm in which agents navigate repositories, interpret heterogeneous ","authors_text":"Chi Zhang, Chunfeng Song, Jiyong Rao, Runkai Zhao, Yicheng Qiu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28098","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":"sha256:9a000d5c98d965d1d6f0b9c6edc6d40b837e086532a7889e311d6a0916661b94","target":"record","created_at":"2026-07-31T01:35:44Z","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":"9376fb5755b364aca308067c23335adfd4b2bb454e80ab09d991ca5cfb3f9306","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T05:08:21Z","title_canon_sha256":"e666ba408183f3daea89a17220d9780556f120cc10b7fcce98d1253b72dc2a0f"},"schema_version":"1.0","source":{"id":"2607.28098","kind":"arxiv","version":1}},"canonical_sha256":"227f97c487bdf67253c153224642d512a4a438d03d10635547485182193c0f96","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"227f97c487bdf67253c153224642d512a4a438d03d10635547485182193c0f96","first_computed_at":"2026-07-31T01:35:44.963676Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:35:44.963676Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28098","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a000d5c98d965d1d6f0b9c6edc6d40b837e086532a7889e311d6a0916661b94","sha256:9ad96e2d03332cebc429d22256c8e0fd0e04da3dd33d4ca1b090e01380937cd7"],"state_sha256":"061861bfa8fe0b476cc54c68d4a3dde18b6668fd8970a1c194dfe6bb4f0fa4d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YUtx+GTEPsk2TLTRke0+wqQnr7dDnbAaJveXClG1Ac5mQLIz0ePytGW6TdA6LCpjP9jrOFIQJ9yR/vsJnwQnBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T12:39:35.585071Z","bundle_sha256":"69e3097259076a547f0ae7ecbb11476f9827a48d99e132011959965ae88de630"}}