{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2TZUVD65EXTVWRW4OG52XM3RTI","short_pith_number":"pith:2TZUVD65","schema_version":"1.0","canonical_sha256":"d4f34a8fdd25e75b46dc71bbabb3719a3bd9b8887d8b4fa1316314117a7a4473","source":{"kind":"arxiv","id":"2606.09547","version":1},"attestation_state":"computed","paper":{"title":"Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Apratim Bhattacharyya, Litian Liu, Rajeev Yasarla, Reza Pourreza, Risheek Garrepalli, Roland Memisevic, Sanjay Haresh, Shweta Mahajan","submitted_at":"2026-06-08T14:27:20Z","abstract_excerpt":"Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos. This opens the door to the use of video (and multimodal) large language models (LLMs) as task guidance assistants. A crucial capability for the real-world success of a prospective task guidance assistant is it's ability to intervene proactively as soon as a mistake is apparent in order to guide the user. To evaluate this crucial capability, we introduce Ego-MC-Bench (Mistake Corrections), a benchmark for evaluating reactive, step-by-step task guidance in realistic cooking scenarios."},"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":"2606.09547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T14:27:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0572d95f79f1d0669bd75f27c94966b24955295bb43a45413969681b457fdfd","abstract_canon_sha256":"4d2643baa35f8f0250fbf28bbdc0aee357660fcb90fe92a1a62f98b975dfaf05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:54.374578Z","signature_b64":"3PDua3gCVfteHv9W/L6szoy3/g4TLneFvDGg4VXYkOeqiDr6ZW9n5P/A1JNCboYR9e3TRfUd+gMJy/UCmo9qAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4f34a8fdd25e75b46dc71bbabb3719a3bd9b8887d8b4fa1316314117a7a4473","last_reissued_at":"2026-06-09T02:08:54.372395Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:54.372395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Apratim Bhattacharyya, Litian Liu, Rajeev Yasarla, Reza Pourreza, Risheek Garrepalli, Roland Memisevic, Sanjay Haresh, Shweta Mahajan","submitted_at":"2026-06-08T14:27:20Z","abstract_excerpt":"Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos. This opens the door to the use of video (and multimodal) large language models (LLMs) as task guidance assistants. A crucial capability for the real-world success of a prospective task guidance assistant is it's ability to intervene proactively as soon as a mistake is apparent in order to guide the user. To evaluate this crucial capability, we introduce Ego-MC-Bench (Mistake Corrections), a benchmark for evaluating reactive, step-by-step task guidance in realistic cooking scenarios."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09547","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/2606.09547/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":"2606.09547","created_at":"2026-06-09T02:08:54.373721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09547v1","created_at":"2026-06-09T02:08:54.373721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09547","created_at":"2026-06-09T02:08:54.373721+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TZUVD65EXTV","created_at":"2026-06-09T02:08:54.373721+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TZUVD65EXTVWRW4","created_at":"2026-06-09T02:08:54.373721+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TZUVD65","created_at":"2026-06-09T02:08:54.373721+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/2TZUVD65EXTVWRW4OG52XM3RTI","json":"https://pith.science/pith/2TZUVD65EXTVWRW4OG52XM3RTI.json","graph_json":"https://pith.science/api/pith-number/2TZUVD65EXTVWRW4OG52XM3RTI/graph.json","events_json":"https://pith.science/api/pith-number/2TZUVD65EXTVWRW4OG52XM3RTI/events.json","paper":"https://pith.science/paper/2TZUVD65"},"agent_actions":{"view_html":"https://pith.science/pith/2TZUVD65EXTVWRW4OG52XM3RTI","download_json":"https://pith.science/pith/2TZUVD65EXTVWRW4OG52XM3RTI.json","view_paper":"https://pith.science/paper/2TZUVD65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09547&json=true","fetch_graph":"https://pith.science/api/pith-number/2TZUVD65EXTVWRW4OG52XM3RTI/graph.json","fetch_events":"https://pith.science/api/pith-number/2TZUVD65EXTVWRW4OG52XM3RTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TZUVD65EXTVWRW4OG52XM3RTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TZUVD65EXTVWRW4OG52XM3RTI/action/storage_attestation","attest_author":"https://pith.science/pith/2TZUVD65EXTVWRW4OG52XM3RTI/action/author_attestation","sign_citation":"https://pith.science/pith/2TZUVD65EXTVWRW4OG52XM3RTI/action/citation_signature","submit_replication":"https://pith.science/pith/2TZUVD65EXTVWRW4OG52XM3RTI/action/replication_record"}},"created_at":"2026-06-09T02:08:54.373721+00:00","updated_at":"2026-06-09T02:08:54.373721+00:00"}