{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4EHNOXAFN7EXKC2BTTG75735RV","short_pith_number":"pith:4EHNOXAF","canonical_record":{"source":{"id":"2407.11325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T02:29:29Z","cross_cats_sorted":[],"title_canon_sha256":"1bbc036fb990f7698911c24c298b0b1de25a0182f80205188b4168fc85fc4bf1","abstract_canon_sha256":"c59e97cdcbf63d1135837fcb16f0109f4561bcccd06a677769ce8eaf4b4a1b24"},"schema_version":"1.0"},"canonical_sha256":"e10ed75c056fc9750b419ccdfeff7d8d5529549d3bf4fd7e75de7f5493673e38","source":{"kind":"arxiv","id":"2407.11325","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11325","created_at":"2026-07-05T08:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11325v1","created_at":"2026-07-05T08:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11325","created_at":"2026-07-05T08:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"4EHNOXAFN7EX","created_at":"2026-07-05T08:44:22Z"},{"alias_kind":"pith_short_16","alias_value":"4EHNOXAFN7EXKC2B","created_at":"2026-07-05T08:44:22Z"},{"alias_kind":"pith_short_8","alias_value":"4EHNOXAF","created_at":"2026-07-05T08:44:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4EHNOXAFN7EXKC2BTTG75735RV","target":"record","payload":{"canonical_record":{"source":{"id":"2407.11325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T02:29:29Z","cross_cats_sorted":[],"title_canon_sha256":"1bbc036fb990f7698911c24c298b0b1de25a0182f80205188b4168fc85fc4bf1","abstract_canon_sha256":"c59e97cdcbf63d1135837fcb16f0109f4561bcccd06a677769ce8eaf4b4a1b24"},"schema_version":"1.0"},"canonical_sha256":"e10ed75c056fc9750b419ccdfeff7d8d5529549d3bf4fd7e75de7f5493673e38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:22.369512Z","signature_b64":"W3JIKPi5wKF4vR5V0q6fmoUpSm2cC4HeOrTt2hIhh+USdDQoDe6kXdq29hLI7Ym0tEzlXjP6YkIPGr/GpBu2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e10ed75c056fc9750b419ccdfeff7d8d5529549d3bf4fd7e75de7f5493673e38","last_reissued_at":"2026-07-05T08:44:22.368938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:22.368938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.11325","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":"2026-07-05T08:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wG7u6Jazs7RAIS7tiUmb4LmKketlWm+WlQ4NCwvukQD4PNx99kDeQj8o3bwig/q86JNy1NiwfefqiB2KSLWwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:51:37.247954Z"},"content_sha256":"aec06636aaa5951d3e79c904d84d2240787e873ffaae73eb0f8ce8ccd568609e","schema_version":"1.0","event_id":"sha256:aec06636aaa5951d3e79c904d84d2240787e873ffaae73eb0f8ce8ccd568609e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4EHNOXAFN7EXKC2BTTG75735RV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VISA: Reasoning Video Object Segmentation via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cilin Yan, Efstratios Gavves, Guoliang Kang, Haochen Wang, Shilin Yan, Weidi Xie, Xiaolong Jiang, Yao Hu","submitted_at":"2024-07-16T02:29:29Z","abstract_excerpt":"Existing Video Object Segmentation (VOS) relies on explicit user instructions, such as categories, masks, or short phrases, restricting their ability to perform complex video segmentation requiring reasoning with world knowledge. In this paper, we introduce a new task, Reasoning Video Object Segmentation (ReasonVOS). This task aims to generate a sequence of segmentation masks in response to implicit text queries that require complex reasoning abilities based on world knowledge and video contexts, which is crucial for structured environment understanding and object-centric interactions, pivotal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11325","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/2407.11325/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":"2026-07-05T08:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0U1fhUb9r1AAjUOJ44m1nn2m7XR+SBu3G1e/+r61kiO2uecnnfjH90d1D0ZAUOH05SqDIfo02z3dxZgQN/ZdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:51:37.248439Z"},"content_sha256":"c31cdacd1c1911a6f03ac27367f0a023a819c5f525018ed88d293f03eb7ad967","schema_version":"1.0","event_id":"sha256:c31cdacd1c1911a6f03ac27367f0a023a819c5f525018ed88d293f03eb7ad967"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4EHNOXAFN7EXKC2BTTG75735RV/bundle.json","state_url":"https://pith.science/pith/4EHNOXAFN7EXKC2BTTG75735RV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4EHNOXAFN7EXKC2BTTG75735RV/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":"2026-08-09T20:51:37Z","links":{"resolver":"https://pith.science/pith/4EHNOXAFN7EXKC2BTTG75735RV","bundle":"https://pith.science/pith/4EHNOXAFN7EXKC2BTTG75735RV/bundle.json","state":"https://pith.science/pith/4EHNOXAFN7EXKC2BTTG75735RV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4EHNOXAFN7EXKC2BTTG75735RV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4EHNOXAFN7EXKC2BTTG75735RV","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":"c59e97cdcbf63d1135837fcb16f0109f4561bcccd06a677769ce8eaf4b4a1b24","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T02:29:29Z","title_canon_sha256":"1bbc036fb990f7698911c24c298b0b1de25a0182f80205188b4168fc85fc4bf1"},"schema_version":"1.0","source":{"id":"2407.11325","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11325","created_at":"2026-07-05T08:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11325v1","created_at":"2026-07-05T08:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11325","created_at":"2026-07-05T08:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"4EHNOXAFN7EX","created_at":"2026-07-05T08:44:22Z"},{"alias_kind":"pith_short_16","alias_value":"4EHNOXAFN7EXKC2B","created_at":"2026-07-05T08:44:22Z"},{"alias_kind":"pith_short_8","alias_value":"4EHNOXAF","created_at":"2026-07-05T08:44:22Z"}],"graph_snapshots":[{"event_id":"sha256:c31cdacd1c1911a6f03ac27367f0a023a819c5f525018ed88d293f03eb7ad967","target":"graph","created_at":"2026-07-05T08:44:22Z","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/2407.11325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Video Object Segmentation (VOS) relies on explicit user instructions, such as categories, masks, or short phrases, restricting their ability to perform complex video segmentation requiring reasoning with world knowledge. In this paper, we introduce a new task, Reasoning Video Object Segmentation (ReasonVOS). This task aims to generate a sequence of segmentation masks in response to implicit text queries that require complex reasoning abilities based on world knowledge and video contexts, which is crucial for structured environment understanding and object-centric interactions, pivotal","authors_text":"Cilin Yan, Efstratios Gavves, Guoliang Kang, Haochen Wang, Shilin Yan, Weidi Xie, Xiaolong Jiang, Yao Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T02:29:29Z","title":"VISA: Reasoning Video Object Segmentation via Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11325","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:aec06636aaa5951d3e79c904d84d2240787e873ffaae73eb0f8ce8ccd568609e","target":"record","created_at":"2026-07-05T08:44:22Z","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":"c59e97cdcbf63d1135837fcb16f0109f4561bcccd06a677769ce8eaf4b4a1b24","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T02:29:29Z","title_canon_sha256":"1bbc036fb990f7698911c24c298b0b1de25a0182f80205188b4168fc85fc4bf1"},"schema_version":"1.0","source":{"id":"2407.11325","kind":"arxiv","version":1}},"canonical_sha256":"e10ed75c056fc9750b419ccdfeff7d8d5529549d3bf4fd7e75de7f5493673e38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e10ed75c056fc9750b419ccdfeff7d8d5529549d3bf4fd7e75de7f5493673e38","first_computed_at":"2026-07-05T08:44:22.368938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:22.368938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W3JIKPi5wKF4vR5V0q6fmoUpSm2cC4HeOrTt2hIhh+USdDQoDe6kXdq29hLI7Ym0tEzlXjP6YkIPGr/GpBu2Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:22.369512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11325","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aec06636aaa5951d3e79c904d84d2240787e873ffaae73eb0f8ce8ccd568609e","sha256:c31cdacd1c1911a6f03ac27367f0a023a819c5f525018ed88d293f03eb7ad967"],"state_sha256":"fd8a2f1bf1ad6017adbe1051db17f59e10361b2bea97f9933bf464132900b05f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/FHPQTtVKZJn6u75/i2jTEE6Vjzx7RMHkkS0g/+6LEwYkc/VCsscPVNLe3I+YHbgfQgEB8lfXP3Hp2d5muqVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:51:37.252076Z","bundle_sha256":"06b54708db5ccb0ae31ff803fcf0751069d49a4a4808198fba0a06334cb74353"}}