{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZK5BKQUGSZJOX3B7ISPGH3ZAKY","short_pith_number":"pith:ZK5BKQUG","canonical_record":{"source":{"id":"2311.04414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-08T00:56:31Z","cross_cats_sorted":[],"title_canon_sha256":"b0a898959f541fc353e494dc2e07ec91312b8771c3617bf3b61c991465aabe1b","abstract_canon_sha256":"e837804247e8d714cde0781d3b892e799991244a954e92436227e6e82596ba7e"},"schema_version":"1.0"},"canonical_sha256":"caba1542869652ebec3f449e63ef20562d9c732e36250ecf3f7e9e6db8ce848f","source":{"kind":"arxiv","id":"2311.04414","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04414","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04414v2","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04414","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZK5BKQUGSZJO","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZK5BKQUGSZJOX3B7","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZK5BKQUG","created_at":"2026-07-05T07:11:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZK5BKQUGSZJOX3B7ISPGH3ZAKY","target":"record","payload":{"canonical_record":{"source":{"id":"2311.04414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-08T00:56:31Z","cross_cats_sorted":[],"title_canon_sha256":"b0a898959f541fc353e494dc2e07ec91312b8771c3617bf3b61c991465aabe1b","abstract_canon_sha256":"e837804247e8d714cde0781d3b892e799991244a954e92436227e6e82596ba7e"},"schema_version":"1.0"},"canonical_sha256":"caba1542869652ebec3f449e63ef20562d9c732e36250ecf3f7e9e6db8ce848f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:37.503239Z","signature_b64":"mIFywNp8gEWnDxeINixe6u/IECjSL5/ok2JPzOjciG4tkEEkbU952xQAto+jruuaXvBEkMWUKr+V47mxCFlVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caba1542869652ebec3f449e63ef20562d9c732e36250ecf3f7e9e6db8ce848f","last_reissued_at":"2026-07-05T07:11:37.502711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:37.502711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.04414","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":"2026-07-05T07:11:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+QoYj2jTLis7CiXC/ZgZzm1euMrFS6u0Q7NEXBYLjzauj9wkXuB5IVxLqcex22FRPV6CJrIcw66Zz03zGFdGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:02:46.091992Z"},"content_sha256":"4508633b240efd26b9e5dc2825cc7c4d5d2470f930e057975690a419228b8f67","schema_version":"1.0","event_id":"sha256:4508633b240efd26b9e5dc2825cc7c4d5d2470f930e057975690a419228b8f67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZK5BKQUGSZJOX3B7ISPGH3ZAKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning the What and How of Annotation in Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dim P. Papadopoulos, Thanos Delatolas, Vicky Kalogeiton","submitted_at":"2023-11-08T00:56:31Z","abstract_excerpt":"Video Object Segmentation (VOS) is crucial for several applications, from video editing to video data generation. Training a VOS model requires an abundance of manually labeled training videos. The de-facto traditional way of annotating objects requires humans to draw detailed segmentation masks on the target objects at each video frame. This annotation process, however, is tedious and time-consuming. To reduce this annotation cost, in this paper, we propose EVA-VOS, a human-in-the-loop annotation framework for video object segmentation. Unlike the traditional approach, we introduce an agent t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04414","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/2311.04414/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":"2026-07-05T07:11:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3zGLe7TBj5dtX68EdJ7TaVtg1MF3oO8hf9lGE8Wzt2TLL0edwp/j6NPcot7CxVftS2EE0n0meGGpeBEK4DQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:02:46.092534Z"},"content_sha256":"83d93e39a4649bc4e77f424a3af5ff0abe3d286534ea27430a7dfb134f7f5422","schema_version":"1.0","event_id":"sha256:83d93e39a4649bc4e77f424a3af5ff0abe3d286534ea27430a7dfb134f7f5422"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZK5BKQUGSZJOX3B7ISPGH3ZAKY/bundle.json","state_url":"https://pith.science/pith/ZK5BKQUGSZJOX3B7ISPGH3ZAKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZK5BKQUGSZJOX3B7ISPGH3ZAKY/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":"2026-08-17T20:02:46Z","links":{"resolver":"https://pith.science/pith/ZK5BKQUGSZJOX3B7ISPGH3ZAKY","bundle":"https://pith.science/pith/ZK5BKQUGSZJOX3B7ISPGH3ZAKY/bundle.json","state":"https://pith.science/pith/ZK5BKQUGSZJOX3B7ISPGH3ZAKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZK5BKQUGSZJOX3B7ISPGH3ZAKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZK5BKQUGSZJOX3B7ISPGH3ZAKY","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":"e837804247e8d714cde0781d3b892e799991244a954e92436227e6e82596ba7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-08T00:56:31Z","title_canon_sha256":"b0a898959f541fc353e494dc2e07ec91312b8771c3617bf3b61c991465aabe1b"},"schema_version":"1.0","source":{"id":"2311.04414","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04414","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04414v2","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04414","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZK5BKQUGSZJO","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZK5BKQUGSZJOX3B7","created_at":"2026-07-05T07:11:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZK5BKQUG","created_at":"2026-07-05T07:11:37Z"}],"graph_snapshots":[{"event_id":"sha256:83d93e39a4649bc4e77f424a3af5ff0abe3d286534ea27430a7dfb134f7f5422","target":"graph","created_at":"2026-07-05T07:11:37Z","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/2311.04414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Object Segmentation (VOS) is crucial for several applications, from video editing to video data generation. Training a VOS model requires an abundance of manually labeled training videos. The de-facto traditional way of annotating objects requires humans to draw detailed segmentation masks on the target objects at each video frame. This annotation process, however, is tedious and time-consuming. To reduce this annotation cost, in this paper, we propose EVA-VOS, a human-in-the-loop annotation framework for video object segmentation. Unlike the traditional approach, we introduce an agent t","authors_text":"Dim P. Papadopoulos, Thanos Delatolas, Vicky Kalogeiton","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-08T00:56:31Z","title":"Learning the What and How of Annotation in Video Object Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04414","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":"sha256:4508633b240efd26b9e5dc2825cc7c4d5d2470f930e057975690a419228b8f67","target":"record","created_at":"2026-07-05T07:11:37Z","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":"e837804247e8d714cde0781d3b892e799991244a954e92436227e6e82596ba7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-08T00:56:31Z","title_canon_sha256":"b0a898959f541fc353e494dc2e07ec91312b8771c3617bf3b61c991465aabe1b"},"schema_version":"1.0","source":{"id":"2311.04414","kind":"arxiv","version":2}},"canonical_sha256":"caba1542869652ebec3f449e63ef20562d9c732e36250ecf3f7e9e6db8ce848f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caba1542869652ebec3f449e63ef20562d9c732e36250ecf3f7e9e6db8ce848f","first_computed_at":"2026-07-05T07:11:37.502711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:37.502711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mIFywNp8gEWnDxeINixe6u/IECjSL5/ok2JPzOjciG4tkEEkbU952xQAto+jruuaXvBEkMWUKr+V47mxCFlVDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:37.503239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.04414","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4508633b240efd26b9e5dc2825cc7c4d5d2470f930e057975690a419228b8f67","sha256:83d93e39a4649bc4e77f424a3af5ff0abe3d286534ea27430a7dfb134f7f5422"],"state_sha256":"a093763569f00997378548a9a1f775f6233b288ce39fe2b0c04711e7d0b916a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f5lFnqLUPjhSaluYB056NiPKi2Zq6hbQqIUFPijoIic91B6ZNhWUDYSYG+tpwcB6684umL0d8mxu9Qp481y0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:02:46.097922Z","bundle_sha256":"e82cb4944def60ecf9d57e3c43982357051f49a838b6fdc27db94d6af458ec92"}}