{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3COBNVJTYXNUFBTSK4IWJ4IUAU","short_pith_number":"pith:3COBNVJT","canonical_record":{"source":{"id":"2508.21809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T17:43:58Z","cross_cats_sorted":[],"title_canon_sha256":"5b26ce9448ead9fca7a49f3db635381b4e0231e5ed0c2cee4c764d8557f70ce0","abstract_canon_sha256":"aa30a2537c96f58c636a78224c2727408709f8d0006bb53c2369aabe44c2ec87"},"schema_version":"1.0"},"canonical_sha256":"d89c16d533c5db428672571164f1140538df11ba05488fd589e1aa699c664d01","source":{"kind":"arxiv","id":"2508.21809","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21809","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21809v1","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21809","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"3COBNVJTYXNU","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"3COBNVJTYXNUFBTS","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"3COBNVJT","created_at":"2026-07-05T12:01:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3COBNVJTYXNUFBTSK4IWJ4IUAU","target":"record","payload":{"canonical_record":{"source":{"id":"2508.21809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T17:43:58Z","cross_cats_sorted":[],"title_canon_sha256":"5b26ce9448ead9fca7a49f3db635381b4e0231e5ed0c2cee4c764d8557f70ce0","abstract_canon_sha256":"aa30a2537c96f58c636a78224c2727408709f8d0006bb53c2369aabe44c2ec87"},"schema_version":"1.0"},"canonical_sha256":"d89c16d533c5db428672571164f1140538df11ba05488fd589e1aa699c664d01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:50.001416Z","signature_b64":"oSx1N18hzU8t5g/PSZ5KQYHlT71SklLn2bmgGGvJc55DkXd1AjIYal0U7CwsCl/jFjoMqGago3sICcvgur1SDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d89c16d533c5db428672571164f1140538df11ba05488fd589e1aa699c664d01","last_reissued_at":"2026-07-05T12:01:50.000938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:50.000938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.21809","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Za72SqKypY7skYuG4yVslEyPiJrSuqOpuzWfEOXU1JEUYfvujl4W2/ynLxNQPz03APjxTqF5AhzS8Flsgw7sAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T02:58:34.058988Z"},"content_sha256":"9fa6e9638d5b2f93975850785627a102b2177c100b940d07b10f391fa4d0314c","schema_version":"1.0","event_id":"sha256:9fa6e9638d5b2f93975850785627a102b2177c100b940d07b10f391fa4d0314c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3COBNVJTYXNUFBTSK4IWJ4IUAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoCap: Video Object Captioning and Segmentation from Any Prompt","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alireza Fathi, Anurag Arnab, Arsha Nagrani, Cordelia Schmid, David Ross, Jasper Uijlings, Xingyi Zhou, Xiuye Gu","submitted_at":"2025-08-29T17:43:58Z","abstract_excerpt":"Understanding objects in videos in terms of fine-grained localization masks and detailed semantic properties is a fundamental task in video understanding. In this paper, we propose VoCap, a flexible video model that consumes a video and a prompt of various modalities (text, box or mask), and produces a spatio-temporal masklet with a corresponding object-centric caption. As such our model addresses simultaneously the tasks of promptable video object segmentation, referring expression segmentation, and object captioning. Since obtaining data for this task is tedious and expensive, we propose to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21809","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/2508.21809/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sfclvzWuYOxtZrIn4WekbJShgj8fC2DHhzrUrUl9zWeFJpmoL1eWEtFY9cB1ejsSEZnCYqb0Dm9WWIvYkeMPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T02:58:34.059499Z"},"content_sha256":"9ed3c1707d71e994e577fc86d5f83f99e92c1453ff775b6dad8bd2114cceaebb","schema_version":"1.0","event_id":"sha256:9ed3c1707d71e994e577fc86d5f83f99e92c1453ff775b6dad8bd2114cceaebb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3COBNVJTYXNUFBTSK4IWJ4IUAU/bundle.json","state_url":"https://pith.science/pith/3COBNVJTYXNUFBTSK4IWJ4IUAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3COBNVJTYXNUFBTSK4IWJ4IUAU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T02:58:34Z","links":{"resolver":"https://pith.science/pith/3COBNVJTYXNUFBTSK4IWJ4IUAU","bundle":"https://pith.science/pith/3COBNVJTYXNUFBTSK4IWJ4IUAU/bundle.json","state":"https://pith.science/pith/3COBNVJTYXNUFBTSK4IWJ4IUAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3COBNVJTYXNUFBTSK4IWJ4IUAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3COBNVJTYXNUFBTSK4IWJ4IUAU","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":"aa30a2537c96f58c636a78224c2727408709f8d0006bb53c2369aabe44c2ec87","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T17:43:58Z","title_canon_sha256":"5b26ce9448ead9fca7a49f3db635381b4e0231e5ed0c2cee4c764d8557f70ce0"},"schema_version":"1.0","source":{"id":"2508.21809","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21809","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21809v1","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21809","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"3COBNVJTYXNU","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"3COBNVJTYXNUFBTS","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"3COBNVJT","created_at":"2026-07-05T12:01:50Z"}],"graph_snapshots":[{"event_id":"sha256:9ed3c1707d71e994e577fc86d5f83f99e92c1453ff775b6dad8bd2114cceaebb","target":"graph","created_at":"2026-07-05T12:01:50Z","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/2508.21809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding objects in videos in terms of fine-grained localization masks and detailed semantic properties is a fundamental task in video understanding. In this paper, we propose VoCap, a flexible video model that consumes a video and a prompt of various modalities (text, box or mask), and produces a spatio-temporal masklet with a corresponding object-centric caption. As such our model addresses simultaneously the tasks of promptable video object segmentation, referring expression segmentation, and object captioning. Since obtaining data for this task is tedious and expensive, we propose to ","authors_text":"Alireza Fathi, Anurag Arnab, Arsha Nagrani, Cordelia Schmid, David Ross, Jasper Uijlings, Xingyi Zhou, Xiuye Gu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T17:43:58Z","title":"VoCap: Video Object Captioning and Segmentation from Any Prompt"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21809","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":"sha256:9fa6e9638d5b2f93975850785627a102b2177c100b940d07b10f391fa4d0314c","target":"record","created_at":"2026-07-05T12:01:50Z","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":"aa30a2537c96f58c636a78224c2727408709f8d0006bb53c2369aabe44c2ec87","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T17:43:58Z","title_canon_sha256":"5b26ce9448ead9fca7a49f3db635381b4e0231e5ed0c2cee4c764d8557f70ce0"},"schema_version":"1.0","source":{"id":"2508.21809","kind":"arxiv","version":1}},"canonical_sha256":"d89c16d533c5db428672571164f1140538df11ba05488fd589e1aa699c664d01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d89c16d533c5db428672571164f1140538df11ba05488fd589e1aa699c664d01","first_computed_at":"2026-07-05T12:01:50.000938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:50.000938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oSx1N18hzU8t5g/PSZ5KQYHlT71SklLn2bmgGGvJc55DkXd1AjIYal0U7CwsCl/jFjoMqGago3sICcvgur1SDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:50.001416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21809","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fa6e9638d5b2f93975850785627a102b2177c100b940d07b10f391fa4d0314c","sha256:9ed3c1707d71e994e577fc86d5f83f99e92c1453ff775b6dad8bd2114cceaebb"],"state_sha256":"3ef9d2d06d95ac983114635544628d5568a17775e0768ec54188d67373689d51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/HpZE8SsBMzLzoz25YsBoy+gHGjGA+4S75N4ud7Q3tSSEHYNBp62IlTFS8X8Bmt0WXgxASi1FCUjd7s0rHApCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T02:58:34.064601Z","bundle_sha256":"d434a5d13d0c8c3544343b079096505228c14139384e5d1f1fccc68c7c6046ad"}}