{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IF4BBJGOORKHKPLWKCCWKTKI4U","short_pith_number":"pith:IF4BBJGO","schema_version":"1.0","canonical_sha256":"417810a4ce7454753d765085654d48e535e7b08a0379c1290708eb1f4b331e8d","source":{"kind":"arxiv","id":"2507.04529","version":1},"attestation_state":"computed","paper":{"title":"A Data-Driven Novelty Score for Diverse In-Vehicle Data Recording","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Petri, Eric Sax, Jacob Langner, Joshua Ransiek, Philipp Reis","submitted_at":"2025-07-06T20:46:19Z","abstract_excerpt":"High-quality datasets are essential for training robust perception systems in autonomous driving. However, real-world data collection is often biased toward common scenes and objects, leaving novel cases underrepresented. This imbalance hinders model generalization and compromises safety. The core issue is the curse of rarity. Over time, novel events occur infrequently, and standard logging methods fail to capture them effectively. As a result, large volumes of redundant data are stored, while critical novel cases are diluted, leading to biased datasets. This work presents a real-time data sel"},"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":"2507.04529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-06T20:46:19Z","cross_cats_sorted":[],"title_canon_sha256":"6505f1850de459d0db50c9623eb2fc514d6d3ccaabe669b804fb16325c5c7b70","abstract_canon_sha256":"21670824774bb98a35410e66ccd5682dbbe74c455c5614fc13cd41d55a6dfc7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:49.416567Z","signature_b64":"eHEpDCOtpfYY/pbB6UeJSFM2Rs0Tgvs/N9Hz3JHisW0kKu0BzIOpmGxupXLvZDPNexwdGje4JBirQavoiktsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"417810a4ce7454753d765085654d48e535e7b08a0379c1290708eb1f4b331e8d","last_reissued_at":"2026-07-05T11:32:49.416088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:49.416088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Data-Driven Novelty Score for Diverse In-Vehicle Data Recording","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Petri, Eric Sax, Jacob Langner, Joshua Ransiek, Philipp Reis","submitted_at":"2025-07-06T20:46:19Z","abstract_excerpt":"High-quality datasets are essential for training robust perception systems in autonomous driving. However, real-world data collection is often biased toward common scenes and objects, leaving novel cases underrepresented. This imbalance hinders model generalization and compromises safety. The core issue is the curse of rarity. Over time, novel events occur infrequently, and standard logging methods fail to capture them effectively. As a result, large volumes of redundant data are stored, while critical novel cases are diluted, leading to biased datasets. This work presents a real-time data sel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04529","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/2507.04529/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":"2507.04529","created_at":"2026-07-05T11:32:49.416134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04529v1","created_at":"2026-07-05T11:32:49.416134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04529","created_at":"2026-07-05T11:32:49.416134+00:00"},{"alias_kind":"pith_short_12","alias_value":"IF4BBJGOORKH","created_at":"2026-07-05T11:32:49.416134+00:00"},{"alias_kind":"pith_short_16","alias_value":"IF4BBJGOORKHKPLW","created_at":"2026-07-05T11:32:49.416134+00:00"},{"alias_kind":"pith_short_8","alias_value":"IF4BBJGO","created_at":"2026-07-05T11:32:49.416134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13046","citing_title":"A Domain-Specific Language for LLM-Driven Trigger Generation in Multimodal Data Collection","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IF4BBJGOORKHKPLWKCCWKTKI4U","json":"https://pith.science/pith/IF4BBJGOORKHKPLWKCCWKTKI4U.json","graph_json":"https://pith.science/api/pith-number/IF4BBJGOORKHKPLWKCCWKTKI4U/graph.json","events_json":"https://pith.science/api/pith-number/IF4BBJGOORKHKPLWKCCWKTKI4U/events.json","paper":"https://pith.science/paper/IF4BBJGO"},"agent_actions":{"view_html":"https://pith.science/pith/IF4BBJGOORKHKPLWKCCWKTKI4U","download_json":"https://pith.science/pith/IF4BBJGOORKHKPLWKCCWKTKI4U.json","view_paper":"https://pith.science/paper/IF4BBJGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04529&json=true","fetch_graph":"https://pith.science/api/pith-number/IF4BBJGOORKHKPLWKCCWKTKI4U/graph.json","fetch_events":"https://pith.science/api/pith-number/IF4BBJGOORKHKPLWKCCWKTKI4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IF4BBJGOORKHKPLWKCCWKTKI4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IF4BBJGOORKHKPLWKCCWKTKI4U/action/storage_attestation","attest_author":"https://pith.science/pith/IF4BBJGOORKHKPLWKCCWKTKI4U/action/author_attestation","sign_citation":"https://pith.science/pith/IF4BBJGOORKHKPLWKCCWKTKI4U/action/citation_signature","submit_replication":"https://pith.science/pith/IF4BBJGOORKHKPLWKCCWKTKI4U/action/replication_record"}},"created_at":"2026-07-05T11:32:49.416134+00:00","updated_at":"2026-07-05T11:32:49.416134+00:00"}