{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NGYBVWWRZCEDCZK54CYT4GFI5N","short_pith_number":"pith:NGYBVWWR","schema_version":"1.0","canonical_sha256":"69b01adad1c88831655de0b13e18a8eb52234a55cf43bb701318e5cbceb61044","source":{"kind":"arxiv","id":"2412.02071","version":2},"attestation_state":"computed","paper":{"title":"Progress-Aware Video Frame Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joungbin An, Kristen Grauman, Xitong Yang, Zihui Xue","submitted_at":"2024-12-03T01:21:28Z","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"},"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":"2412.02071","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T01:21:28Z","cross_cats_sorted":[],"title_canon_sha256":"a547bc0041c6f73db79adbcd3c19fd2433265df92014576df45cac6000daa9e8","abstract_canon_sha256":"5f0e41aa2839e37db40ab3bbae9eabeaa0bc3008f6088ba8e41b6bf649baf68e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:23.783051Z","signature_b64":"AJgrFLZ9n6yNTJinzb3qEC3qNF3iIiAQvn4THvzCgwMEaph0J7vCPnALagzp7E2rvaVS5KCps+dmDmS9YE6TDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69b01adad1c88831655de0b13e18a8eb52234a55cf43bb701318e5cbceb61044","last_reissued_at":"2026-07-05T10:39:23.782561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:23.782561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progress-Aware Video Frame Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joungbin An, Kristen Grauman, Xitong Yang, Zihui Xue","submitted_at":"2024-12-03T01:21:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02071","kind":"arxiv","version":2},"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/2412.02071/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":"2412.02071","created_at":"2026-07-05T10:39:23.782619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02071v2","created_at":"2026-07-05T10:39:23.782619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02071","created_at":"2026-07-05T10:39:23.782619+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGYBVWWRZCED","created_at":"2026-07-05T10:39:23.782619+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGYBVWWRZCEDCZK5","created_at":"2026-07-05T10:39:23.782619+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGYBVWWR","created_at":"2026-07-05T10:39:23.782619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09693","citing_title":"ExpStar: Towards Automatic Commentary Generation for Multi-discipline Scientific Experiments","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGYBVWWRZCEDCZK54CYT4GFI5N","json":"https://pith.science/pith/NGYBVWWRZCEDCZK54CYT4GFI5N.json","graph_json":"https://pith.science/api/pith-number/NGYBVWWRZCEDCZK54CYT4GFI5N/graph.json","events_json":"https://pith.science/api/pith-number/NGYBVWWRZCEDCZK54CYT4GFI5N/events.json","paper":"https://pith.science/paper/NGYBVWWR"},"agent_actions":{"view_html":"https://pith.science/pith/NGYBVWWRZCEDCZK54CYT4GFI5N","download_json":"https://pith.science/pith/NGYBVWWRZCEDCZK54CYT4GFI5N.json","view_paper":"https://pith.science/paper/NGYBVWWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02071&json=true","fetch_graph":"https://pith.science/api/pith-number/NGYBVWWRZCEDCZK54CYT4GFI5N/graph.json","fetch_events":"https://pith.science/api/pith-number/NGYBVWWRZCEDCZK54CYT4GFI5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGYBVWWRZCEDCZK54CYT4GFI5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGYBVWWRZCEDCZK54CYT4GFI5N/action/storage_attestation","attest_author":"https://pith.science/pith/NGYBVWWRZCEDCZK54CYT4GFI5N/action/author_attestation","sign_citation":"https://pith.science/pith/NGYBVWWRZCEDCZK54CYT4GFI5N/action/citation_signature","submit_replication":"https://pith.science/pith/NGYBVWWRZCEDCZK54CYT4GFI5N/action/replication_record"}},"created_at":"2026-07-05T10:39:23.782619+00:00","updated_at":"2026-07-05T10:39:23.782619+00:00"}