{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K4AFYL3XF6EXZDXSINOACZRW2Q","short_pith_number":"pith:K4AFYL3X","canonical_record":{"source":{"id":"2509.00728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-31T07:45:40Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"730985483ca130002eb98728a9342bf90ae17335888d4c05bc13d60f01b9c34e","abstract_canon_sha256":"e1db9587ba3c16066cb25bbc4ffd83888e66163337a12d580a70ea6c015db124"},"schema_version":"1.0"},"canonical_sha256":"57005c2f772f897c8ef2435c016636d402d938fdb73c4896f228c938c2032be6","source":{"kind":"arxiv","id":"2509.00728","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00728","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00728v1","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00728","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"K4AFYL3XF6EX","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"K4AFYL3XF6EXZDXS","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"K4AFYL3X","created_at":"2026-07-05T12:02:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K4AFYL3XF6EXZDXSINOACZRW2Q","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-31T07:45:40Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"730985483ca130002eb98728a9342bf90ae17335888d4c05bc13d60f01b9c34e","abstract_canon_sha256":"e1db9587ba3c16066cb25bbc4ffd83888e66163337a12d580a70ea6c015db124"},"schema_version":"1.0"},"canonical_sha256":"57005c2f772f897c8ef2435c016636d402d938fdb73c4896f228c938c2032be6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:21.843828Z","signature_b64":"l2ZvNZ8/WJrxKiaM9dE855K8Dp2wobko8eJOXyOzRGRwJ2PcSIFgq6LFO6O6D78qnFe+S6JkUmSteS/iLGFCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57005c2f772f897c8ef2435c016636d402d938fdb73c4896f228c938c2032be6","last_reissued_at":"2026-07-05T12:02:21.843362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:21.843362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00728","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":"2026-07-05T12:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BigQOAhaYE1d50CEaQVmTtIqh6OCFWjIVbDLzb9zoVUt8PytDhfass2VqzVSG32g+fowlh4MpEs6pKu8FcKsAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:58:48.946908Z"},"content_sha256":"aea4a86acff793676aa69291e1459fcf7c338c8320f796bbcac9a7638bd74529","schema_version":"1.0","event_id":"sha256:aea4a86acff793676aa69291e1459fcf7c338c8320f796bbcac9a7638bd74529"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K4AFYL3XF6EXZDXSINOACZRW2Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Open Dataset Search in the LLM Era: Retrospectives and Perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.IR","authors_text":"Brian D. Davison, Hua Dai, Pengyue Li, Sheng Wang, Zhifeng Bao, Zhiyu Chen","submitted_at":"2025-08-31T07:45:40Z","abstract_excerpt":"High-quality datasets are typically required for accomplishing data-driven tasks, such as training medical diagnosis models, predicting real-time traffic conditions, or conducting experiments to validate research hypotheses. Consequently, open dataset search, which aims to ensure the efficient and accurate fulfillment of users' dataset requirements, has emerged as a critical research challenge and has attracted widespread interest. Recent studies have made notable progress in enhancing the flexibility and intelligence of open dataset search, and large language models (LLMs) have demonstrated s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00728","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/2509.00728/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":"2026-07-05T12:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GLYzr5V/mfnj96UAYElH6uwwVawB1kI7+nn+OB3EYBiW/LZCrSPNw8Fzvks0cXD5EJHibZnZR6fNIE6VyZJ4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:58:48.947290Z"},"content_sha256":"5d01ac1e4eb23b4f6a0dbd12e7be1a00bb11c918fbb2d498d02f52091a258955","schema_version":"1.0","event_id":"sha256:5d01ac1e4eb23b4f6a0dbd12e7be1a00bb11c918fbb2d498d02f52091a258955"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4AFYL3XF6EXZDXSINOACZRW2Q/bundle.json","state_url":"https://pith.science/pith/K4AFYL3XF6EXZDXSINOACZRW2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4AFYL3XF6EXZDXSINOACZRW2Q/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":"2026-08-06T00:58:48Z","links":{"resolver":"https://pith.science/pith/K4AFYL3XF6EXZDXSINOACZRW2Q","bundle":"https://pith.science/pith/K4AFYL3XF6EXZDXSINOACZRW2Q/bundle.json","state":"https://pith.science/pith/K4AFYL3XF6EXZDXSINOACZRW2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4AFYL3XF6EXZDXSINOACZRW2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K4AFYL3XF6EXZDXSINOACZRW2Q","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":"e1db9587ba3c16066cb25bbc4ffd83888e66163337a12d580a70ea6c015db124","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-31T07:45:40Z","title_canon_sha256":"730985483ca130002eb98728a9342bf90ae17335888d4c05bc13d60f01b9c34e"},"schema_version":"1.0","source":{"id":"2509.00728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00728","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00728v1","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00728","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"K4AFYL3XF6EX","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"K4AFYL3XF6EXZDXS","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"K4AFYL3X","created_at":"2026-07-05T12:02:21Z"}],"graph_snapshots":[{"event_id":"sha256:5d01ac1e4eb23b4f6a0dbd12e7be1a00bb11c918fbb2d498d02f52091a258955","target":"graph","created_at":"2026-07-05T12:02:21Z","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/2509.00728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality datasets are typically required for accomplishing data-driven tasks, such as training medical diagnosis models, predicting real-time traffic conditions, or conducting experiments to validate research hypotheses. Consequently, open dataset search, which aims to ensure the efficient and accurate fulfillment of users' dataset requirements, has emerged as a critical research challenge and has attracted widespread interest. Recent studies have made notable progress in enhancing the flexibility and intelligence of open dataset search, and large language models (LLMs) have demonstrated s","authors_text":"Brian D. Davison, Hua Dai, Pengyue Li, Sheng Wang, Zhifeng Bao, Zhiyu Chen","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-31T07:45:40Z","title":"A Survey on Open Dataset Search in the LLM Era: Retrospectives and Perspectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00728","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:aea4a86acff793676aa69291e1459fcf7c338c8320f796bbcac9a7638bd74529","target":"record","created_at":"2026-07-05T12:02:21Z","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":"e1db9587ba3c16066cb25bbc4ffd83888e66163337a12d580a70ea6c015db124","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-31T07:45:40Z","title_canon_sha256":"730985483ca130002eb98728a9342bf90ae17335888d4c05bc13d60f01b9c34e"},"schema_version":"1.0","source":{"id":"2509.00728","kind":"arxiv","version":1}},"canonical_sha256":"57005c2f772f897c8ef2435c016636d402d938fdb73c4896f228c938c2032be6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57005c2f772f897c8ef2435c016636d402d938fdb73c4896f228c938c2032be6","first_computed_at":"2026-07-05T12:02:21.843362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:21.843362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l2ZvNZ8/WJrxKiaM9dE855K8Dp2wobko8eJOXyOzRGRwJ2PcSIFgq6LFO6O6D78qnFe+S6JkUmSteS/iLGFCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:21.843828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aea4a86acff793676aa69291e1459fcf7c338c8320f796bbcac9a7638bd74529","sha256:5d01ac1e4eb23b4f6a0dbd12e7be1a00bb11c918fbb2d498d02f52091a258955"],"state_sha256":"dba8c1ec7e4edb5cba1c33969cf810cb440dcfaee7cecb96e4d1164422a7db7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jTVI3BEvcnnbN3XsOreJ0t8k37wklimR9dmADjFrDQvfbL4Q9oTK2AHuGfDNJrfEnkfbzNDsFm3YM7xptkQNAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:58:48.949728Z","bundle_sha256":"af1e0713cad6f28ffc308caf24568f80e393231574c64db53ef08f81e61a3c9f"}}