{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:G4XRBRVMM3RT4MWH2ZEH7TZEYX","short_pith_number":"pith:G4XRBRVM","canonical_record":{"source":{"id":"2412.09329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-12-12T14:53:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b3593d0e3df43bec67c1dac2e0ba95ffcffbc3a9e2b17a08b1b6b0d3a0d0a2c","abstract_canon_sha256":"e917f981c78cc7f4ff511864072525fb97b6fd138b85f8209c0b461af75569ac"},"schema_version":"1.0"},"canonical_sha256":"372f10c6ac66e33e32c7d6487fcf24c5ce782fc1f25d32e5d345117a5e721590","source":{"kind":"arxiv","id":"2412.09329","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09329","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09329v1","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09329","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_12","alias_value":"G4XRBRVMM3RT","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_16","alias_value":"G4XRBRVMM3RT4MWH","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_8","alias_value":"G4XRBRVM","created_at":"2026-07-05T09:48:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:G4XRBRVMM3RT4MWH2ZEH7TZEYX","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-12-12T14:53:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b3593d0e3df43bec67c1dac2e0ba95ffcffbc3a9e2b17a08b1b6b0d3a0d0a2c","abstract_canon_sha256":"e917f981c78cc7f4ff511864072525fb97b6fd138b85f8209c0b461af75569ac"},"schema_version":"1.0"},"canonical_sha256":"372f10c6ac66e33e32c7d6487fcf24c5ce782fc1f25d32e5d345117a5e721590","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:23.303002Z","signature_b64":"E4d+9UxdLPYpVGip7FFUNOIOrevZz9nsnRKjazmNB6++RfamTScWeUufclmej3WOU8TiXRzyJXTs8H/fwB8yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"372f10c6ac66e33e32c7d6487fcf24c5ce782fc1f25d32e5d345117a5e721590","last_reissued_at":"2026-07-05T09:48:23.302209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:23.302209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09329","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":"2026-07-05T09:48:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QoEQirCrtYxcDBZr6HJB/uB8ujBffogn2WygnXZvV3cDpk59ntWvL3Jlr1YsKvYsUNQTnoW9JMRpg/Iw7DgLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:33:42.691830Z"},"content_sha256":"6cd7ff95dd50b3f6c6a7a6802f32f02fc9edd40e0150d54c624200ec27d97778","schema_version":"1.0","event_id":"sha256:6cd7ff95dd50b3f6c6a7a6802f32f02fc9edd40e0150d54c624200ec27d97778"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:G4XRBRVMM3RT4MWH2ZEH7TZEYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Open-Vocabulary Video Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MM","authors_text":"Ce Zhu, Guolei Sun, Le Zhang, Min Wu, Xinhao Li, Yun Liu","submitted_at":"2024-12-12T14:53:16Z","abstract_excerpt":"Semantic segmentation in videos has been a focal point of recent research. However, existing models encounter challenges when faced with unfamiliar categories. To address this, we introduce the Open Vocabulary Video Semantic Segmentation (OV-VSS) task, designed to accurately segment every pixel across a wide range of open-vocabulary categories, including those that are novel or previously unexplored. To enhance OV-VSS performance, we propose a robust baseline, OV2VSS, which integrates a spatial-temporal fusion module, allowing the model to utilize temporal relationships across consecutive fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09329","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/2412.09329/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":"2026-07-05T09:48:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PpVWCGmTSY47vC539WeP52yO5mejWAvtT9kkqKIA4lyD17m6mrRa5xCm9qsTISRH7njnLfZKz+mvebJt3OGmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:33:42.692567Z"},"content_sha256":"9eae67910e7c993bfb0c6852d804fdabce741d452f4f7f5f2297e31556000554","schema_version":"1.0","event_id":"sha256:9eae67910e7c993bfb0c6852d804fdabce741d452f4f7f5f2297e31556000554"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4XRBRVMM3RT4MWH2ZEH7TZEYX/bundle.json","state_url":"https://pith.science/pith/G4XRBRVMM3RT4MWH2ZEH7TZEYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4XRBRVMM3RT4MWH2ZEH7TZEYX/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":"2026-08-17T12:33:42Z","links":{"resolver":"https://pith.science/pith/G4XRBRVMM3RT4MWH2ZEH7TZEYX","bundle":"https://pith.science/pith/G4XRBRVMM3RT4MWH2ZEH7TZEYX/bundle.json","state":"https://pith.science/pith/G4XRBRVMM3RT4MWH2ZEH7TZEYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4XRBRVMM3RT4MWH2ZEH7TZEYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G4XRBRVMM3RT4MWH2ZEH7TZEYX","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":"e917f981c78cc7f4ff511864072525fb97b6fd138b85f8209c0b461af75569ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-12-12T14:53:16Z","title_canon_sha256":"8b3593d0e3df43bec67c1dac2e0ba95ffcffbc3a9e2b17a08b1b6b0d3a0d0a2c"},"schema_version":"1.0","source":{"id":"2412.09329","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09329","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09329v1","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09329","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_12","alias_value":"G4XRBRVMM3RT","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_16","alias_value":"G4XRBRVMM3RT4MWH","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_8","alias_value":"G4XRBRVM","created_at":"2026-07-05T09:48:23Z"}],"graph_snapshots":[{"event_id":"sha256:9eae67910e7c993bfb0c6852d804fdabce741d452f4f7f5f2297e31556000554","target":"graph","created_at":"2026-07-05T09:48:23Z","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/2412.09329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic segmentation in videos has been a focal point of recent research. However, existing models encounter challenges when faced with unfamiliar categories. To address this, we introduce the Open Vocabulary Video Semantic Segmentation (OV-VSS) task, designed to accurately segment every pixel across a wide range of open-vocabulary categories, including those that are novel or previously unexplored. To enhance OV-VSS performance, we propose a robust baseline, OV2VSS, which integrates a spatial-temporal fusion module, allowing the model to utilize temporal relationships across consecutive fram","authors_text":"Ce Zhu, Guolei Sun, Le Zhang, Min Wu, Xinhao Li, Yun Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-12-12T14:53:16Z","title":"Towards Open-Vocabulary Video Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09329","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":"sha256:6cd7ff95dd50b3f6c6a7a6802f32f02fc9edd40e0150d54c624200ec27d97778","target":"record","created_at":"2026-07-05T09:48:23Z","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":"e917f981c78cc7f4ff511864072525fb97b6fd138b85f8209c0b461af75569ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-12-12T14:53:16Z","title_canon_sha256":"8b3593d0e3df43bec67c1dac2e0ba95ffcffbc3a9e2b17a08b1b6b0d3a0d0a2c"},"schema_version":"1.0","source":{"id":"2412.09329","kind":"arxiv","version":1}},"canonical_sha256":"372f10c6ac66e33e32c7d6487fcf24c5ce782fc1f25d32e5d345117a5e721590","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"372f10c6ac66e33e32c7d6487fcf24c5ce782fc1f25d32e5d345117a5e721590","first_computed_at":"2026-07-05T09:48:23.302209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:23.302209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E4d+9UxdLPYpVGip7FFUNOIOrevZz9nsnRKjazmNB6++RfamTScWeUufclmej3WOU8TiXRzyJXTs8H/fwB8yCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:23.303002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09329","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cd7ff95dd50b3f6c6a7a6802f32f02fc9edd40e0150d54c624200ec27d97778","sha256:9eae67910e7c993bfb0c6852d804fdabce741d452f4f7f5f2297e31556000554"],"state_sha256":"3beeec375c9942f5e1bd139fb67c921c43bff32ab53330ef9cf52f5c769033ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4kSPLpCrS0XM7wYRCpoqSDS6IQTpXMB/nD9t4L58ZiOA+FpDDyw6/C4GnCF1Ysn4yF8otpWj437mleMbPjt+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:33:42.699208Z","bundle_sha256":"34ca4a2054d3c269b6a7685d1dbcc012e204bf9e13f10c36b0ecbed738b8e4f6"}}