{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PF4CORSPRES5N6PYYWQLZBFWTP","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":"d19b1b9a2a75d7750cf4c8c3fcfb661c89d6b9ccfb41ada197e43cb12f98b40d","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T18:54:48Z","title_canon_sha256":"6ac11784b7db87887baf202094038908db95c5114ee004f39c77bea0b621aae8"},"schema_version":"1.0","source":{"id":"2412.09582","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09582","created_at":"2026-07-05T10:02:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09582v2","created_at":"2026-07-05T10:02:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09582","created_at":"2026-07-05T10:02:25Z"},{"alias_kind":"pith_short_12","alias_value":"PF4CORSPRES5","created_at":"2026-07-05T10:02:25Z"},{"alias_kind":"pith_short_16","alias_value":"PF4CORSPRES5N6PY","created_at":"2026-07-05T10:02:25Z"},{"alias_kind":"pith_short_8","alias_value":"PF4CORSP","created_at":"2026-07-05T10:02:25Z"}],"graph_snapshots":[{"event_id":"sha256:e6103ee2253c0c24762191adabeae7589ac0fdf39543ed38228752e88199ed73","target":"graph","created_at":"2026-07-05T10:02:25Z","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/2412.09582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Neptune, a benchmark for long video understanding that requires reasoning over long time horizons and across different modalities. Many existing video datasets and models are focused on short clips (10s-30s). While some long video datasets do exist, they can often be solved by powerful image models applied per frame (and often to very few frames) in a video, and are usually manually annotated at high cost. In order to mitigate both these problems, we propose a scalable dataset creation pipeline which leverages large models (VLMs and LLMs), to automatically generate dense, time-ali","authors_text":"Arsha Nagrani, Austin Myers, Boqing Gong, Cordelia Schmid, Mikhail Sirotenko, Mingda Zhang, Nilpa Jha, Nitesh Bharadwaj Gundavarapu, Rachel Hornung, Ramin Mehran, Tobias Weyand, Xingyi Zhou, Yukun Zhu","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T18:54:48Z","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09582","kind":"arxiv","version":2},"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:c392c7cb434eff48e719d48893cfcab0ea031966d24b404d4324f886ba4ca9e6","target":"record","created_at":"2026-07-05T10:02:25Z","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":"d19b1b9a2a75d7750cf4c8c3fcfb661c89d6b9ccfb41ada197e43cb12f98b40d","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T18:54:48Z","title_canon_sha256":"6ac11784b7db87887baf202094038908db95c5114ee004f39c77bea0b621aae8"},"schema_version":"1.0","source":{"id":"2412.09582","kind":"arxiv","version":2}},"canonical_sha256":"797827464f8925d6f9f8c5a0bc84b69bf774bea450dba2311521167bba167cf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"797827464f8925d6f9f8c5a0bc84b69bf774bea450dba2311521167bba167cf0","first_computed_at":"2026-07-05T10:02:25.710046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:25.710046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FPMb+pEGGeRd8XtUxy7vvPEWGkIldH0caQSXntwBAA6hEaGIgVjHzxCcmjorWb4BunDjG3XD0te5Gv6kzhunBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:25.710508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09582","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c392c7cb434eff48e719d48893cfcab0ea031966d24b404d4324f886ba4ca9e6","sha256:e6103ee2253c0c24762191adabeae7589ac0fdf39543ed38228752e88199ed73"],"state_sha256":"167d507328ffc22ea9ee1b615ebba5945f0ad024dd7c63ad14d233adaab05930"}