{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LDTSUZFSFHHM2DKYTQQSVDEB7G","short_pith_number":"pith:LDTSUZFS","schema_version":"1.0","canonical_sha256":"58e72a64b229cecd0d589c212a8c81f99783b77c8828d0ca3220d50969d9cc98","source":{"kind":"arxiv","id":"2607.09655","version":1},"attestation_state":"computed","paper":{"title":"OpenLongTail: Generative Scaling of Long-Tail Driving Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bangya Liu, Boris Ivanovic, Dilin Wang, Hao Wang, Hezhen Hu, Lulin Liu, Marco Pavone, Nuo Chen, Ruohan Zhang, Weisong Shi, Wenyan Cong, Xinyu Gong, Yang Zhou, Yan Wang, Zhangyang Wang, Zhiwen Fan, Zixiang Xiong, Ziyao Zeng","submitted_at":"2026-07-10T17:54:14Z","abstract_excerpt":"Scaling robust driving policies is fundamentally bottlenecked by the scarcity of edge cases in curated datasets. While the real world continuously captures these critical events, such long-tail events remain underutilized when collected from heterogeneous sources. Specifically, diverse but valuable in-the-wild long-tail videos lack the full view coverage required for training policy models, often missing multi-view poses or originating solely from monocular dash cameras. This modality gap prevents these ubiquitous observations from being converted into scalable training data for long-tail gene"},"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":"2607.09655","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T17:54:14Z","cross_cats_sorted":[],"title_canon_sha256":"c933481b31e5cde19569ab7875adcc475a21c767b50dabad271f7ef806859e48","abstract_canon_sha256":"c7148913274ce2649ab3e4d9a2b2b4f3bd3e18a30703a1684eb3a529f772f5fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:20:27.338305Z","signature_b64":"DjoBQGXDGmdyDKjNXskkxucT/cE/Oh0wa4EfGpKgSfKclLm7vX4SjO9CWwuipPCY9Hl74LPdv+XLcnGqyEuSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58e72a64b229cecd0d589c212a8c81f99783b77c8828d0ca3220d50969d9cc98","last_reissued_at":"2026-07-13T01:20:27.336889Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:20:27.336889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenLongTail: Generative Scaling of Long-Tail Driving Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bangya Liu, Boris Ivanovic, Dilin Wang, Hao Wang, Hezhen Hu, Lulin Liu, Marco Pavone, Nuo Chen, Ruohan Zhang, Weisong Shi, Wenyan Cong, Xinyu Gong, Yang Zhou, Yan Wang, Zhangyang Wang, Zhiwen Fan, Zixiang Xiong, Ziyao Zeng","submitted_at":"2026-07-10T17:54:14Z","abstract_excerpt":"Scaling robust driving policies is fundamentally bottlenecked by the scarcity of edge cases in curated datasets. While the real world continuously captures these critical events, such long-tail events remain underutilized when collected from heterogeneous sources. Specifically, diverse but valuable in-the-wild long-tail videos lack the full view coverage required for training policy models, often missing multi-view poses or originating solely from monocular dash cameras. This modality gap prevents these ubiquitous observations from being converted into scalable training data for long-tail gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09655","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/2607.09655/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":"2607.09655","created_at":"2026-07-13T01:20:27.337672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09655v1","created_at":"2026-07-13T01:20:27.337672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09655","created_at":"2026-07-13T01:20:27.337672+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDTSUZFSFHHM","created_at":"2026-07-13T01:20:27.337672+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDTSUZFSFHHM2DKY","created_at":"2026-07-13T01:20:27.337672+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDTSUZFS","created_at":"2026-07-13T01:20:27.337672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDTSUZFSFHHM2DKYTQQSVDEB7G","json":"https://pith.science/pith/LDTSUZFSFHHM2DKYTQQSVDEB7G.json","graph_json":"https://pith.science/api/pith-number/LDTSUZFSFHHM2DKYTQQSVDEB7G/graph.json","events_json":"https://pith.science/api/pith-number/LDTSUZFSFHHM2DKYTQQSVDEB7G/events.json","paper":"https://pith.science/paper/LDTSUZFS"},"agent_actions":{"view_html":"https://pith.science/pith/LDTSUZFSFHHM2DKYTQQSVDEB7G","download_json":"https://pith.science/pith/LDTSUZFSFHHM2DKYTQQSVDEB7G.json","view_paper":"https://pith.science/paper/LDTSUZFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09655&json=true","fetch_graph":"https://pith.science/api/pith-number/LDTSUZFSFHHM2DKYTQQSVDEB7G/graph.json","fetch_events":"https://pith.science/api/pith-number/LDTSUZFSFHHM2DKYTQQSVDEB7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDTSUZFSFHHM2DKYTQQSVDEB7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDTSUZFSFHHM2DKYTQQSVDEB7G/action/storage_attestation","attest_author":"https://pith.science/pith/LDTSUZFSFHHM2DKYTQQSVDEB7G/action/author_attestation","sign_citation":"https://pith.science/pith/LDTSUZFSFHHM2DKYTQQSVDEB7G/action/citation_signature","submit_replication":"https://pith.science/pith/LDTSUZFSFHHM2DKYTQQSVDEB7G/action/replication_record"}},"created_at":"2026-07-13T01:20:27.337672+00:00","updated_at":"2026-07-13T01:20:27.337672+00:00"}