{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:L3WCHMTMBQAGMQZGJLHMBCRWOI","short_pith_number":"pith:L3WCHMTM","canonical_record":{"source":{"id":"2501.14607","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T16:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"8a3071381f729804700bbec1692a88681e1b096aa7e4b033e90d32038ca79fc0","abstract_canon_sha256":"338b23eb2cd04a6f05c4a641414f2f18ca2a14b41279c7dea7ecf1c7283108b5"},"schema_version":"1.0"},"canonical_sha256":"5eec23b26c0c006643264acec08a36721a319ff9897011d0c0ae97b029054ebb","source":{"kind":"arxiv","id":"2501.14607","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14607","created_at":"2026-07-05T11:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14607v2","created_at":"2026-07-05T11:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14607","created_at":"2026-07-05T11:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"L3WCHMTMBQAG","created_at":"2026-07-05T11:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"L3WCHMTMBQAGMQZG","created_at":"2026-07-05T11:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"L3WCHMTM","created_at":"2026-07-05T11:29:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:L3WCHMTMBQAGMQZGJLHMBCRWOI","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14607","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T16:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"8a3071381f729804700bbec1692a88681e1b096aa7e4b033e90d32038ca79fc0","abstract_canon_sha256":"338b23eb2cd04a6f05c4a641414f2f18ca2a14b41279c7dea7ecf1c7283108b5"},"schema_version":"1.0"},"canonical_sha256":"5eec23b26c0c006643264acec08a36721a319ff9897011d0c0ae97b029054ebb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:05.952574Z","signature_b64":"DwPD7I0Yg65A2AD5Dx+3yka+XIytYOtCAW0b33PWRgJqozMFwRGNsfEaKwe6E4XsFChTJdVUfBpk4uEiLYKGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eec23b26c0c006643264acec08a36721a319ff9897011d0c0ae97b029054ebb","last_reissued_at":"2026-07-05T11:29:05.952093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:05.952093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14607","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:29:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z+o/BLATR6TLy1YEIppC7AFYdjS3kwJUeRiTjPPAeLHw1g1o8+dh/GCY8qUpj9gbQhB1bC3F7UrW4GtesNpWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:02:24.210685Z"},"content_sha256":"6e0820ba6108dfe3531526b6d25d1a37fe9b34efcf940728f6171fca5ca78ad7","schema_version":"1.0","event_id":"sha256:6e0820ba6108dfe3531526b6d25d1a37fe9b34efcf940728f6171fca5ca78ad7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:L3WCHMTMBQAGMQZGJLHMBCRWOI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaolei Tan, Jian-Fang Hu, Jianguo Zhang, Kun-Yu Lin, Tianming Liang, Wei-Shi Zheng","submitted_at":"2025-01-24T16:24:15Z","abstract_excerpt":"Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This is challenging as it involves deep vision-language understanding, pixel-level dense prediction and spatiotemporal reasoning. Despite notable progress in recent years, existing methods still exhibit a noticeable gap when considering all these aspects. In this work, we propose \\textbf{ReferDINO}, a strong RVOS model that inherits region-level vision-language alignment from foundational visual grounding models, and is further endowed with pixel-level dense perception and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14607","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/2501.14607/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":"2026-07-05T11:29:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d/W9n884gQBCIz9rB5tEGfc+MusyqjxM0EXDE36V7OQI+LAIwId84gOSs8eSVsjn/bZ57MrmXZczbmumk6/lDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:02:24.211287Z"},"content_sha256":"295f71b63e717731b08255364e3c4688e57a103c24c254b87148c6e62b698d46","schema_version":"1.0","event_id":"sha256:295f71b63e717731b08255364e3c4688e57a103c24c254b87148c6e62b698d46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/bundle.json","state_url":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/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":"2026-08-05T08:02:24Z","links":{"resolver":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI","bundle":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/bundle.json","state":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L3WCHMTMBQAGMQZGJLHMBCRWOI","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":"338b23eb2cd04a6f05c4a641414f2f18ca2a14b41279c7dea7ecf1c7283108b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T16:24:15Z","title_canon_sha256":"8a3071381f729804700bbec1692a88681e1b096aa7e4b033e90d32038ca79fc0"},"schema_version":"1.0","source":{"id":"2501.14607","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14607","created_at":"2026-07-05T11:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14607v2","created_at":"2026-07-05T11:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14607","created_at":"2026-07-05T11:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"L3WCHMTMBQAG","created_at":"2026-07-05T11:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"L3WCHMTMBQAGMQZG","created_at":"2026-07-05T11:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"L3WCHMTM","created_at":"2026-07-05T11:29:05Z"}],"graph_snapshots":[{"event_id":"sha256:295f71b63e717731b08255364e3c4688e57a103c24c254b87148c6e62b698d46","target":"graph","created_at":"2026-07-05T11:29:05Z","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/2501.14607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This is challenging as it involves deep vision-language understanding, pixel-level dense prediction and spatiotemporal reasoning. Despite notable progress in recent years, existing methods still exhibit a noticeable gap when considering all these aspects. In this work, we propose \\textbf{ReferDINO}, a strong RVOS model that inherits region-level vision-language alignment from foundational visual grounding models, and is further endowed with pixel-level dense perception and ","authors_text":"Chaolei Tan, Jian-Fang Hu, Jianguo Zhang, Kun-Yu Lin, Tianming Liang, Wei-Shi Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T16:24:15Z","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14607","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":"sha256:6e0820ba6108dfe3531526b6d25d1a37fe9b34efcf940728f6171fca5ca78ad7","target":"record","created_at":"2026-07-05T11:29:05Z","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":"338b23eb2cd04a6f05c4a641414f2f18ca2a14b41279c7dea7ecf1c7283108b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T16:24:15Z","title_canon_sha256":"8a3071381f729804700bbec1692a88681e1b096aa7e4b033e90d32038ca79fc0"},"schema_version":"1.0","source":{"id":"2501.14607","kind":"arxiv","version":2}},"canonical_sha256":"5eec23b26c0c006643264acec08a36721a319ff9897011d0c0ae97b029054ebb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5eec23b26c0c006643264acec08a36721a319ff9897011d0c0ae97b029054ebb","first_computed_at":"2026-07-05T11:29:05.952093Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:05.952093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DwPD7I0Yg65A2AD5Dx+3yka+XIytYOtCAW0b33PWRgJqozMFwRGNsfEaKwe6E4XsFChTJdVUfBpk4uEiLYKGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:05.952574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14607","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e0820ba6108dfe3531526b6d25d1a37fe9b34efcf940728f6171fca5ca78ad7","sha256:295f71b63e717731b08255364e3c4688e57a103c24c254b87148c6e62b698d46"],"state_sha256":"d2e0f6e303f99ecf9d93e347b303de0ac0e9df2244ba88ca20ddcd912385570a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zc3o3aE5vl7mPCYn+PoxBqnYq4qA4UTUXBroA8WBBCMqZ0M1i4IW0ACN7A9zNDav+BBX2Dhd3P1lIy4OFGkABA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:02:24.214990Z","bundle_sha256":"bc59e2070dcdfb6e185294eb13235bf17df2933cf415873d7b2031a3b484cb1f"}}