{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OKAJ6JF7FBRKQUATLCQA3SJUE2","short_pith_number":"pith:OKAJ6JF7","schema_version":"1.0","canonical_sha256":"72809f24bf2862a8501358a00dc934268351ed65217101e87c516da92237c57d","source":{"kind":"arxiv","id":"2411.08753","version":4},"attestation_state":"computed","paper":{"title":"Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kristen Grauman, Reina Pradhan, Sagnik Majumder, Tushar Nagarajan, Ziad Al-Halah","submitted_at":"2024-11-13T16:31:08Z","abstract_excerpt":"Given a multi-view video, which viewpoint is most informative for a human observer? Existing methods rely on heuristics or expensive \"best-view\" supervision to answer this question, limiting their applicability. We propose a weakly supervised approach that leverages language accompanying an instructional multi-view video as a means to recover its most informative viewpoint(s). Our key hypothesis is that the more accurately an individual view can predict a view-agnostic text summary, the more informative it is. To put this into action, we propose LangView, a framework that uses the relative acc"},"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":"2411.08753","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T16:31:08Z","cross_cats_sorted":[],"title_canon_sha256":"2d5e0524c9f1846e76a9473eb0f3488383f980acac1657c806e6d0d894c3989f","abstract_canon_sha256":"97b38573b68b240c2785abba7f8b565fe1c1c5a239316dc56463258515d4220d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:58.498987Z","signature_b64":"e4ejqg9lTfmkDlFViOVFiAjDcXDxgciSgXCUmZ4aLn9C0j9Y6nB8mm8Gny4v2A5kL+V3KwNsRPdtgLx736Q4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72809f24bf2862a8501358a00dc934268351ed65217101e87c516da92237c57d","last_reissued_at":"2026-07-05T10:46:58.498484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:58.498484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kristen Grauman, Reina Pradhan, Sagnik Majumder, Tushar Nagarajan, Ziad Al-Halah","submitted_at":"2024-11-13T16:31:08Z","abstract_excerpt":"Given a multi-view video, which viewpoint is most informative for a human observer? Existing methods rely on heuristics or expensive \"best-view\" supervision to answer this question, limiting their applicability. We propose a weakly supervised approach that leverages language accompanying an instructional multi-view video as a means to recover its most informative viewpoint(s). Our key hypothesis is that the more accurately an individual view can predict a view-agnostic text summary, the more informative it is. To put this into action, we propose LangView, a framework that uses the relative acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08753","kind":"arxiv","version":4},"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/2411.08753/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":"2411.08753","created_at":"2026-07-05T10:46:58.498551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.08753v4","created_at":"2026-07-05T10:46:58.498551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08753","created_at":"2026-07-05T10:46:58.498551+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKAJ6JF7FBRK","created_at":"2026-07-05T10:46:58.498551+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKAJ6JF7FBRKQUAT","created_at":"2026-07-05T10:46:58.498551+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKAJ6JF7","created_at":"2026-07-05T10:46:58.498551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06253","citing_title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","ref_index":187,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKAJ6JF7FBRKQUATLCQA3SJUE2","json":"https://pith.science/pith/OKAJ6JF7FBRKQUATLCQA3SJUE2.json","graph_json":"https://pith.science/api/pith-number/OKAJ6JF7FBRKQUATLCQA3SJUE2/graph.json","events_json":"https://pith.science/api/pith-number/OKAJ6JF7FBRKQUATLCQA3SJUE2/events.json","paper":"https://pith.science/paper/OKAJ6JF7"},"agent_actions":{"view_html":"https://pith.science/pith/OKAJ6JF7FBRKQUATLCQA3SJUE2","download_json":"https://pith.science/pith/OKAJ6JF7FBRKQUATLCQA3SJUE2.json","view_paper":"https://pith.science/paper/OKAJ6JF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.08753&json=true","fetch_graph":"https://pith.science/api/pith-number/OKAJ6JF7FBRKQUATLCQA3SJUE2/graph.json","fetch_events":"https://pith.science/api/pith-number/OKAJ6JF7FBRKQUATLCQA3SJUE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKAJ6JF7FBRKQUATLCQA3SJUE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKAJ6JF7FBRKQUATLCQA3SJUE2/action/storage_attestation","attest_author":"https://pith.science/pith/OKAJ6JF7FBRKQUATLCQA3SJUE2/action/author_attestation","sign_citation":"https://pith.science/pith/OKAJ6JF7FBRKQUATLCQA3SJUE2/action/citation_signature","submit_replication":"https://pith.science/pith/OKAJ6JF7FBRKQUATLCQA3SJUE2/action/replication_record"}},"created_at":"2026-07-05T10:46:58.498551+00:00","updated_at":"2026-07-05T10:46:58.498551+00:00"}