{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SVFN2ZJZTO2L64SZNJHKZZFBBJ","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":"3800fae71a704a62704469effdee2faf7c9718c924eb5566adb7243a0968d48d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-20T21:39:05Z","title_canon_sha256":"a88f147ac470c3f0b454233312c74e8a278e06869f4ba614c376cdec6a726f1c"},"schema_version":"1.0","source":{"id":"2507.15130","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15130","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15130v1","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15130","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_12","alias_value":"SVFN2ZJZTO2L","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_16","alias_value":"SVFN2ZJZTO2L64SZ","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_8","alias_value":"SVFN2ZJZ","created_at":"2026-07-05T11:40:18Z"}],"graph_snapshots":[{"event_id":"sha256:b3bb8d30163e2b259a4f6eb670f6fdc2332f8bacbbff75bb764dcfd290d1b5f8","target":"graph","created_at":"2026-07-05T11:40:18Z","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/2507.15130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Planning for Assistance (VPA) aims to predict a sequence of user actions required to achieve a specified goal based on a video showing the user's progress. Although recent advances in multimodal large language models (MLLMs) have shown promising results in video understanding, long-horizon visual planning remains a challenging problem. We identify two challenges in training large MLLMs for video-based planning tasks: (1) scarcity of procedural annotations, limiting the model's ability to learn procedural task dynamics effectively, and (2) inefficiency of next-token prediction objective ","authors_text":"Ce Zhang, Gedas Bertasius, Joseph Tighe, Michael Louis Iuzzolino, Ruta Desai, Satwik Kottur, Yale Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-20T21:39:05Z","title":"Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15130","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:c2454f03a5037ef85f065b18263e5deff61cf26738ef964a624ccdfeaf1fd399","target":"record","created_at":"2026-07-05T11:40:18Z","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":"3800fae71a704a62704469effdee2faf7c9718c924eb5566adb7243a0968d48d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-20T21:39:05Z","title_canon_sha256":"a88f147ac470c3f0b454233312c74e8a278e06869f4ba614c376cdec6a726f1c"},"schema_version":"1.0","source":{"id":"2507.15130","kind":"arxiv","version":1}},"canonical_sha256":"954add65399bb4bf72596a4eace4a10a43ff5514dc710da08ac4f4def4ea8386","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"954add65399bb4bf72596a4eace4a10a43ff5514dc710da08ac4f4def4ea8386","first_computed_at":"2026-07-05T11:40:18.906809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:18.906809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BIXfwZwnJ5VVN4rpLp+YyXwpKtnaZ6gGu+He7xW1SAao5keEvpNm6TfZNVDhYwLyNRZ9M9fvVWJN8HpSU5VMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:18.907271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15130","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2454f03a5037ef85f065b18263e5deff61cf26738ef964a624ccdfeaf1fd399","sha256:b3bb8d30163e2b259a4f6eb670f6fdc2332f8bacbbff75bb764dcfd290d1b5f8"],"state_sha256":"a41d5ac85d6115e56c34233e4a5f4e0ac5b22cf8e0df9ccf8c0e378f6aaedae0"}