{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NGYBVWWRZCEDCZK54CYT4GFI5N","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":"5f0e41aa2839e37db40ab3bbae9eabeaa0bc3008f6088ba8e41b6bf649baf68e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T01:21:28Z","title_canon_sha256":"a547bc0041c6f73db79adbcd3c19fd2433265df92014576df45cac6000daa9e8"},"schema_version":"1.0","source":{"id":"2412.02071","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02071","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02071v2","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02071","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"NGYBVWWRZCED","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"pith_short_16","alias_value":"NGYBVWWRZCEDCZK5","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"pith_short_8","alias_value":"NGYBVWWR","created_at":"2026-07-05T10:39:23Z"}],"graph_snapshots":[{"event_id":"sha256:f7ef881deaf05d7c2c4401e165fe42bdadd3bcb71b80856e05e95e7d06a12898","target":"graph","created_at":"2026-07-05T10:39:23Z","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/2412.02071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While image captioning provides isolated descriptions for individual images, and video captioning offers one single narrative for an entire video clip, our work explores an important middle ground: progress-aware video captioning at the frame level. This novel task aims to generate temporally fine-grained captions that not only accurately describe each frame but also capture the subtle progression of actions throughout a video sequence. Despite the strong capabilities of existing leading vision language models, they often struggle to discern the nuances of frame-wise differences. To address th","authors_text":"Joungbin An, Kristen Grauman, Xitong Yang, Zihui Xue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T01:21:28Z","title":"Progress-Aware Video Frame Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02071","kind":"arxiv","version":2},"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:d46032766954cb8e11707c56c34824193ce86f25c3d11fd63f46e20ad184bfbe","target":"record","created_at":"2026-07-05T10:39:23Z","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":"5f0e41aa2839e37db40ab3bbae9eabeaa0bc3008f6088ba8e41b6bf649baf68e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T01:21:28Z","title_canon_sha256":"a547bc0041c6f73db79adbcd3c19fd2433265df92014576df45cac6000daa9e8"},"schema_version":"1.0","source":{"id":"2412.02071","kind":"arxiv","version":2}},"canonical_sha256":"69b01adad1c88831655de0b13e18a8eb52234a55cf43bb701318e5cbceb61044","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69b01adad1c88831655de0b13e18a8eb52234a55cf43bb701318e5cbceb61044","first_computed_at":"2026-07-05T10:39:23.782561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:23.782561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AJgrFLZ9n6yNTJinzb3qEC3qNF3iIiAQvn4THvzCgwMEaph0J7vCPnALagzp7E2rvaVS5KCps+dmDmS9YE6TDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:23.783051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02071","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d46032766954cb8e11707c56c34824193ce86f25c3d11fd63f46e20ad184bfbe","sha256:f7ef881deaf05d7c2c4401e165fe42bdadd3bcb71b80856e05e95e7d06a12898"],"state_sha256":"96ccb5102a40a0ee18e4146bb5bdd317047ce58de446e27799a0b5501e51d7aa"}