{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XRACUM5ZNOW6YKCRB54Z4RPSIO","short_pith_number":"pith:XRACUM5Z","schema_version":"1.0","canonical_sha256":"bc402a33b96badec28510f799e45f243bb6950cc4bfed36e7da5885dfc85122a","source":{"kind":"arxiv","id":"2404.08561","version":2},"attestation_state":"computed","paper":{"title":"IDD-X: A Multi-View Dataset for Ego-relative Important Object Localization and Explanation in Dense and Unstructured Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chirag Parikh, C.V. Jawahar, Ravi Kiran Sarvadevabhatla, Rohit Saluja","submitted_at":"2024-04-12T16:00:03Z","abstract_excerpt":"Intelligent vehicle systems require a deep understanding of the interplay between road conditions, surrounding entities, and the ego vehicle's driving behavior for safe and efficient navigation. This is particularly critical in developing countries where traffic situations are often dense and unstructured with heterogeneous road occupants. Existing datasets, predominantly geared towards structured and sparse traffic scenarios, fall short of capturing the complexity of driving in such environments. To fill this gap, we present IDD-X, a large-scale dual-view driving video dataset. With 697K boun"},"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":"2404.08561","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-12T16:00:03Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"1b64c11a25521fa9cd6c7b358115b034153fdd88d3427ecac829d804f35fea40","abstract_canon_sha256":"c8e73ce1f4c25e8bd69abfd2f534b770ce873def20c080abefc3fdc8762b2083"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:24.137192Z","signature_b64":"sY60xyjijxnz79aZHedVoZbCJV39ishjt530qOPuSnXX0nYyw59CB4cLUJB29nqRmB69EeKez3hsvtDyfhBVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc402a33b96badec28510f799e45f243bb6950cc4bfed36e7da5885dfc85122a","last_reissued_at":"2026-07-05T08:11:24.136717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:24.136717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IDD-X: A Multi-View Dataset for Ego-relative Important Object Localization and Explanation in Dense and Unstructured Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chirag Parikh, C.V. Jawahar, Ravi Kiran Sarvadevabhatla, Rohit Saluja","submitted_at":"2024-04-12T16:00:03Z","abstract_excerpt":"Intelligent vehicle systems require a deep understanding of the interplay between road conditions, surrounding entities, and the ego vehicle's driving behavior for safe and efficient navigation. This is particularly critical in developing countries where traffic situations are often dense and unstructured with heterogeneous road occupants. Existing datasets, predominantly geared towards structured and sparse traffic scenarios, fall short of capturing the complexity of driving in such environments. To fill this gap, we present IDD-X, a large-scale dual-view driving video dataset. With 697K boun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08561","kind":"arxiv","version":2},"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/2404.08561/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":"2404.08561","created_at":"2026-07-05T08:11:24.136775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08561v2","created_at":"2026-07-05T08:11:24.136775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08561","created_at":"2026-07-05T08:11:24.136775+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRACUM5ZNOW6","created_at":"2026-07-05T08:11:24.136775+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRACUM5ZNOW6YKCR","created_at":"2026-07-05T08:11:24.136775+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRACUM5Z","created_at":"2026-07-05T08:11:24.136775+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19406","citing_title":"MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRACUM5ZNOW6YKCRB54Z4RPSIO","json":"https://pith.science/pith/XRACUM5ZNOW6YKCRB54Z4RPSIO.json","graph_json":"https://pith.science/api/pith-number/XRACUM5ZNOW6YKCRB54Z4RPSIO/graph.json","events_json":"https://pith.science/api/pith-number/XRACUM5ZNOW6YKCRB54Z4RPSIO/events.json","paper":"https://pith.science/paper/XRACUM5Z"},"agent_actions":{"view_html":"https://pith.science/pith/XRACUM5ZNOW6YKCRB54Z4RPSIO","download_json":"https://pith.science/pith/XRACUM5ZNOW6YKCRB54Z4RPSIO.json","view_paper":"https://pith.science/paper/XRACUM5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08561&json=true","fetch_graph":"https://pith.science/api/pith-number/XRACUM5ZNOW6YKCRB54Z4RPSIO/graph.json","fetch_events":"https://pith.science/api/pith-number/XRACUM5ZNOW6YKCRB54Z4RPSIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRACUM5ZNOW6YKCRB54Z4RPSIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRACUM5ZNOW6YKCRB54Z4RPSIO/action/storage_attestation","attest_author":"https://pith.science/pith/XRACUM5ZNOW6YKCRB54Z4RPSIO/action/author_attestation","sign_citation":"https://pith.science/pith/XRACUM5ZNOW6YKCRB54Z4RPSIO/action/citation_signature","submit_replication":"https://pith.science/pith/XRACUM5ZNOW6YKCRB54Z4RPSIO/action/replication_record"}},"created_at":"2026-07-05T08:11:24.136775+00:00","updated_at":"2026-07-05T08:11:24.136775+00:00"}