{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZJVVLSV44WYNA7EEU6CL4BFLJN","short_pith_number":"pith:ZJVVLSV4","schema_version":"1.0","canonical_sha256":"ca6b55cabce5b0d07c84a784be04ab4b42450bb9a116694bddbaf5c0af8258ae","source":{"kind":"arxiv","id":"2506.09445","version":1},"attestation_state":"computed","paper":{"title":"TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alvaro Velasquez, Anirban Roy, Ayush Gupta, Nathaniel D. Bastian, Rama Chellappa, Susmit Jha","submitted_at":"2025-06-11T06:52:31Z","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"},"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":"2506.09445","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T06:52:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8942a854360627862df6344df0b8c5da8c6af530a5f5efde16e785270f22bad1","abstract_canon_sha256":"5f1ddac023f759fd4476fdce543cdfee30551481e9c307d18fb2ae177c3c0add"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:37.492564Z","signature_b64":"TvS711U+9bm6gIEoDvEzl7dRmKHK9RGNXRc7lan6mYXk9cm0Y5IYpILGZh/PBeivP9NtakSm4PV3exF6GhaVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca6b55cabce5b0d07c84a784be04ab4b42450bb9a116694bddbaf5c0af8258ae","last_reissued_at":"2026-07-05T11:19:37.492077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:37.492077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alvaro Velasquez, Anirban Roy, Ayush Gupta, Nathaniel D. Bastian, Rama Chellappa, Susmit Jha","submitted_at":"2025-06-11T06:52:31Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09445","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/2506.09445/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":"2506.09445","created_at":"2026-07-05T11:19:37.492138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09445v1","created_at":"2026-07-05T11:19:37.492138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09445","created_at":"2026-07-05T11:19:37.492138+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJVVLSV44WYN","created_at":"2026-07-05T11:19:37.492138+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJVVLSV44WYNA7EE","created_at":"2026-07-05T11:19:37.492138+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJVVLSV4","created_at":"2026-07-05T11:19:37.492138+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.17555","citing_title":"GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJVVLSV44WYNA7EEU6CL4BFLJN","json":"https://pith.science/pith/ZJVVLSV44WYNA7EEU6CL4BFLJN.json","graph_json":"https://pith.science/api/pith-number/ZJVVLSV44WYNA7EEU6CL4BFLJN/graph.json","events_json":"https://pith.science/api/pith-number/ZJVVLSV44WYNA7EEU6CL4BFLJN/events.json","paper":"https://pith.science/paper/ZJVVLSV4"},"agent_actions":{"view_html":"https://pith.science/pith/ZJVVLSV44WYNA7EEU6CL4BFLJN","download_json":"https://pith.science/pith/ZJVVLSV44WYNA7EEU6CL4BFLJN.json","view_paper":"https://pith.science/paper/ZJVVLSV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09445&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJVVLSV44WYNA7EEU6CL4BFLJN/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJVVLSV44WYNA7EEU6CL4BFLJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJVVLSV44WYNA7EEU6CL4BFLJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJVVLSV44WYNA7EEU6CL4BFLJN/action/storage_attestation","attest_author":"https://pith.science/pith/ZJVVLSV44WYNA7EEU6CL4BFLJN/action/author_attestation","sign_citation":"https://pith.science/pith/ZJVVLSV44WYNA7EEU6CL4BFLJN/action/citation_signature","submit_replication":"https://pith.science/pith/ZJVVLSV44WYNA7EEU6CL4BFLJN/action/replication_record"}},"created_at":"2026-07-05T11:19:37.492138+00:00","updated_at":"2026-07-05T11:19:37.492138+00:00"}