{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RHBK4Q4N3XHFSH7ROZOR62JNDI","short_pith_number":"pith:RHBK4Q4N","schema_version":"1.0","canonical_sha256":"89c2ae438dddce591ff1765d1f692d1a3fe60486c7539266ff360e4e74b33f3b","source":{"kind":"arxiv","id":"2310.02251","version":2},"attestation_state":"computed","paper":{"title":"Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Anushka Jain, Arun K. Singh, K. Madhava Krishna, Krishna Murthy Jatavallabhula, Shivam Chandhok, Shubham Priyadarshan, Siddharth Srivastava, Tushar Choudhary, Vikrant Dewangan","submitted_at":"2023-10-03T17:53:51Z","abstract_excerpt":"Talk2BEV is a large vision-language model (LVLM) interface for bird's-eye view (BEV) maps in autonomous driving contexts. While existing perception systems for autonomous driving scenarios have largely focused on a pre-defined (closed) set of object categories and driving scenarios, Talk2BEV blends recent advances in general-purpose language and vision models with BEV-structured map representations, eliminating the need for task-specific models. This enables a single system to cater to a variety of autonomous driving tasks encompassing visual and spatial reasoning, predicting the intents of tr"},"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":"2310.02251","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-03T17:53:51Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f6da98f08c16d93826fbe1cce15962abfe70b8f34f985c4891308fdcfb4ea89e","abstract_canon_sha256":"44f35ef242176f18fe2602970f5b3e188a065bd8772d898d5d2b95c16379ce10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:37.779990Z","signature_b64":"uPa0xqLKeZwuh9+d5lK6SAJCjQbg4v46eLKys5Z1FFHM7mhhWzDfYfqIK3t5r9mTNkt49uCz81qiPNSAqZAuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89c2ae438dddce591ff1765d1f692d1a3fe60486c7539266ff360e4e74b33f3b","last_reissued_at":"2026-07-05T07:12:37.779538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:37.779538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Anushka Jain, Arun K. Singh, K. Madhava Krishna, Krishna Murthy Jatavallabhula, Shivam Chandhok, Shubham Priyadarshan, Siddharth Srivastava, Tushar Choudhary, Vikrant Dewangan","submitted_at":"2023-10-03T17:53:51Z","abstract_excerpt":"Talk2BEV is a large vision-language model (LVLM) interface for bird's-eye view (BEV) maps in autonomous driving contexts. While existing perception systems for autonomous driving scenarios have largely focused on a pre-defined (closed) set of object categories and driving scenarios, Talk2BEV blends recent advances in general-purpose language and vision models with BEV-structured map representations, eliminating the need for task-specific models. This enables a single system to cater to a variety of autonomous driving tasks encompassing visual and spatial reasoning, predicting the intents of tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02251","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/2310.02251/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":"2310.02251","created_at":"2026-07-05T07:12:37.779595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02251v2","created_at":"2026-07-05T07:12:37.779595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02251","created_at":"2026-07-05T07:12:37.779595+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHBK4Q4N3XHF","created_at":"2026-07-05T07:12:37.779595+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHBK4Q4N3XHFSH7R","created_at":"2026-07-05T07:12:37.779595+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHBK4Q4N","created_at":"2026-07-05T07:12:37.779595+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.11411","citing_title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","ref_index":150,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHBK4Q4N3XHFSH7ROZOR62JNDI","json":"https://pith.science/pith/RHBK4Q4N3XHFSH7ROZOR62JNDI.json","graph_json":"https://pith.science/api/pith-number/RHBK4Q4N3XHFSH7ROZOR62JNDI/graph.json","events_json":"https://pith.science/api/pith-number/RHBK4Q4N3XHFSH7ROZOR62JNDI/events.json","paper":"https://pith.science/paper/RHBK4Q4N"},"agent_actions":{"view_html":"https://pith.science/pith/RHBK4Q4N3XHFSH7ROZOR62JNDI","download_json":"https://pith.science/pith/RHBK4Q4N3XHFSH7ROZOR62JNDI.json","view_paper":"https://pith.science/paper/RHBK4Q4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02251&json=true","fetch_graph":"https://pith.science/api/pith-number/RHBK4Q4N3XHFSH7ROZOR62JNDI/graph.json","fetch_events":"https://pith.science/api/pith-number/RHBK4Q4N3XHFSH7ROZOR62JNDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHBK4Q4N3XHFSH7ROZOR62JNDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHBK4Q4N3XHFSH7ROZOR62JNDI/action/storage_attestation","attest_author":"https://pith.science/pith/RHBK4Q4N3XHFSH7ROZOR62JNDI/action/author_attestation","sign_citation":"https://pith.science/pith/RHBK4Q4N3XHFSH7ROZOR62JNDI/action/citation_signature","submit_replication":"https://pith.science/pith/RHBK4Q4N3XHFSH7ROZOR62JNDI/action/replication_record"}},"created_at":"2026-07-05T07:12:37.779595+00:00","updated_at":"2026-07-05T07:12:37.779595+00:00"}