{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZJVVLSV44WYNA7EEU6CL4BFLJN","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":"5f1ddac023f759fd4476fdce543cdfee30551481e9c307d18fb2ae177c3c0add","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T06:52:31Z","title_canon_sha256":"8942a854360627862df6344df0b8c5da8c6af530a5f5efde16e785270f22bad1"},"schema_version":"1.0","source":{"id":"2506.09445","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09445","created_at":"2026-07-05T11:19:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09445v1","created_at":"2026-07-05T11:19:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09445","created_at":"2026-07-05T11:19:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZJVVLSV44WYN","created_at":"2026-07-05T11:19:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZJVVLSV44WYNA7EE","created_at":"2026-07-05T11:19:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZJVVLSV4","created_at":"2026-07-05T11:19:37Z"}],"graph_snapshots":[{"event_id":"sha256:9d1d3de1ad133c92fd7c6e6ed8ee6bdf59a57124550682edd5a890d58630d1b5","target":"graph","created_at":"2026-07-05T11:19:37Z","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/2506.09445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of video question answering (video QA) with temporal grounding in a weakly supervised setup, without any temporal annotations. Given a video and a question, we generate an open-ended answer grounded with the start and end time. For this task, we propose TOGA: a vision-language model for Temporally Grounded Open-Ended Video QA with Weak Supervision. We instruct-tune TOGA to jointly generate the answer and the temporal grounding. We operate in a weakly supervised setup where the temporal grounding annotations are not available. We generate pseudo labels for temporal ground","authors_text":"Alvaro Velasquez, Anirban Roy, Ayush Gupta, Nathaniel D. Bastian, Rama Chellappa, Susmit Jha","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T06:52:31Z","title":"TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09445","kind":"arxiv","version":1},"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:bf07decbb491013eb1610f180d67220c372a63564d6c13524bb2b9448529281c","target":"record","created_at":"2026-07-05T11:19:37Z","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":"5f1ddac023f759fd4476fdce543cdfee30551481e9c307d18fb2ae177c3c0add","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T06:52:31Z","title_canon_sha256":"8942a854360627862df6344df0b8c5da8c6af530a5f5efde16e785270f22bad1"},"schema_version":"1.0","source":{"id":"2506.09445","kind":"arxiv","version":1}},"canonical_sha256":"ca6b55cabce5b0d07c84a784be04ab4b42450bb9a116694bddbaf5c0af8258ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca6b55cabce5b0d07c84a784be04ab4b42450bb9a116694bddbaf5c0af8258ae","first_computed_at":"2026-07-05T11:19:37.492077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:37.492077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TvS711U+9bm6gIEoDvEzl7dRmKHK9RGNXRc7lan6mYXk9cm0Y5IYpILGZh/PBeivP9NtakSm4PV3exF6GhaVCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:37.492564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09445","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf07decbb491013eb1610f180d67220c372a63564d6c13524bb2b9448529281c","sha256:9d1d3de1ad133c92fd7c6e6ed8ee6bdf59a57124550682edd5a890d58630d1b5"],"state_sha256":"4680d2df6c40254ac885456708360d27f2bb07cd4d1b84a7a2859fd46d0b15a2"}