{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FAEAO2BXSR3KHTPB2BWH7RY77H","short_pith_number":"pith:FAEAO2BX","canonical_record":{"source":{"id":"2404.03645","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:58:21Z","cross_cats_sorted":[],"title_canon_sha256":"417bfab0a3cd8695ada7112ba23ab7baac93df346a4b5697fcfb83ce5dffa2b3","abstract_canon_sha256":"a69725f2221309e2e6a305221e6e24347642a9f0870db320357508da905c96e5"},"schema_version":"1.0"},"canonical_sha256":"28080768379476a3cde1d06c7fc71ff9d90bc4912f6c1589e6f937c19524baa5","source":{"kind":"arxiv","id":"2404.03645","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03645","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03645v1","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03645","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"FAEAO2BXSR3K","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"FAEAO2BXSR3KHTPB","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"FAEAO2BX","created_at":"2026-07-05T08:04:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FAEAO2BXSR3KHTPB2BWH7RY77H","target":"record","payload":{"canonical_record":{"source":{"id":"2404.03645","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:58:21Z","cross_cats_sorted":[],"title_canon_sha256":"417bfab0a3cd8695ada7112ba23ab7baac93df346a4b5697fcfb83ce5dffa2b3","abstract_canon_sha256":"a69725f2221309e2e6a305221e6e24347642a9f0870db320357508da905c96e5"},"schema_version":"1.0"},"canonical_sha256":"28080768379476a3cde1d06c7fc71ff9d90bc4912f6c1589e6f937c19524baa5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:28.699509Z","signature_b64":"ctXHsWwz8UXymWg2csIkCGYpe0JbsfnH81lIII87HLIUsGTzfYC94DT/B23fhZzaMBAbywnQSLc++cl+q42/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28080768379476a3cde1d06c7fc71ff9d90bc4912f6c1589e6f937c19524baa5","last_reissued_at":"2026-07-05T08:04:28.698988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:28.698988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.03645","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":"2026-07-05T08:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0dXQuYUqovnicEqmDeVmg5lc1+ikw6/zaj4VTNrdtjMdsXZyXJvG+Sx7P3JPJlYeMK9IRritttAMubzyTV52BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:45:31.486784Z"},"content_sha256":"73705448dcc180cd72d160a1d35b066ec7e314b9dfa4cabfb8a842e368d7fa90","schema_version":"1.0","event_id":"sha256:73705448dcc180cd72d160a1d35b066ec7e314b9dfa4cabfb8a842e368d7fa90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FAEAO2BXSR3KHTPB2BWH7RY77H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Henghui Ding, Shuting He","submitted_at":"2024-04-04T17:58:21Z","abstract_excerpt":"Referring video segmentation relies on natural language expressions to identify and segment objects, often emphasizing motion clues. Previous works treat a sentence as a whole and directly perform identification at the video-level, mixing up static image-level cues with temporal motion cues. However, image-level features cannot well comprehend motion cues in sentences, and static cues are not crucial for temporal perception. In fact, static cues can sometimes interfere with temporal perception by overshadowing motion cues. In this work, we propose to decouple video-level referring expression u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03645","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/2404.03645/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":"2026-07-05T08:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R9jEV8RkLmPFlibUDn4/9yxtIFckv8yB3e59pJX2w9JN9UyM3gIJTtO3+2N0N5Fc1hoVU1SncbdDUqvKSl4TCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:45:31.487281Z"},"content_sha256":"bec5b77c152d302edc71abea5d14d14f5798eefc7dbb0c6f8cbe5b53d321c233","schema_version":"1.0","event_id":"sha256:bec5b77c152d302edc71abea5d14d14f5798eefc7dbb0c6f8cbe5b53d321c233"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAEAO2BXSR3KHTPB2BWH7RY77H/bundle.json","state_url":"https://pith.science/pith/FAEAO2BXSR3KHTPB2BWH7RY77H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAEAO2BXSR3KHTPB2BWH7RY77H/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":"2026-08-08T18:45:31Z","links":{"resolver":"https://pith.science/pith/FAEAO2BXSR3KHTPB2BWH7RY77H","bundle":"https://pith.science/pith/FAEAO2BXSR3KHTPB2BWH7RY77H/bundle.json","state":"https://pith.science/pith/FAEAO2BXSR3KHTPB2BWH7RY77H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAEAO2BXSR3KHTPB2BWH7RY77H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FAEAO2BXSR3KHTPB2BWH7RY77H","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":"a69725f2221309e2e6a305221e6e24347642a9f0870db320357508da905c96e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:58:21Z","title_canon_sha256":"417bfab0a3cd8695ada7112ba23ab7baac93df346a4b5697fcfb83ce5dffa2b3"},"schema_version":"1.0","source":{"id":"2404.03645","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03645","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03645v1","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03645","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"FAEAO2BXSR3K","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"FAEAO2BXSR3KHTPB","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"FAEAO2BX","created_at":"2026-07-05T08:04:28Z"}],"graph_snapshots":[{"event_id":"sha256:bec5b77c152d302edc71abea5d14d14f5798eefc7dbb0c6f8cbe5b53d321c233","target":"graph","created_at":"2026-07-05T08:04:28Z","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/2404.03645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring video segmentation relies on natural language expressions to identify and segment objects, often emphasizing motion clues. Previous works treat a sentence as a whole and directly perform identification at the video-level, mixing up static image-level cues with temporal motion cues. However, image-level features cannot well comprehend motion cues in sentences, and static cues are not crucial for temporal perception. In fact, static cues can sometimes interfere with temporal perception by overshadowing motion cues. In this work, we propose to decouple video-level referring expression u","authors_text":"Henghui Ding, Shuting He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:58:21Z","title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03645","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":"sha256:73705448dcc180cd72d160a1d35b066ec7e314b9dfa4cabfb8a842e368d7fa90","target":"record","created_at":"2026-07-05T08:04:28Z","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":"a69725f2221309e2e6a305221e6e24347642a9f0870db320357508da905c96e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:58:21Z","title_canon_sha256":"417bfab0a3cd8695ada7112ba23ab7baac93df346a4b5697fcfb83ce5dffa2b3"},"schema_version":"1.0","source":{"id":"2404.03645","kind":"arxiv","version":1}},"canonical_sha256":"28080768379476a3cde1d06c7fc71ff9d90bc4912f6c1589e6f937c19524baa5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28080768379476a3cde1d06c7fc71ff9d90bc4912f6c1589e6f937c19524baa5","first_computed_at":"2026-07-05T08:04:28.698988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:28.698988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ctXHsWwz8UXymWg2csIkCGYpe0JbsfnH81lIII87HLIUsGTzfYC94DT/B23fhZzaMBAbywnQSLc++cl+q42/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:28.699509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03645","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73705448dcc180cd72d160a1d35b066ec7e314b9dfa4cabfb8a842e368d7fa90","sha256:bec5b77c152d302edc71abea5d14d14f5798eefc7dbb0c6f8cbe5b53d321c233"],"state_sha256":"a761e9e33c064f1532e5e1fb8984aaff462d0c6aca6525f93de86b823ba42791"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xINBGfKHs4R1yv/kdcvhS4ruJzpySnE+I8JO5BjRhwn6LD22g857dLOwSlif31QMRK7HThdDySuoZ4JMB+RWDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:45:31.491970Z","bundle_sha256":"28caf276016a621493449031cd7fd9dfd37064e0e0065e9ed873c7a6df017937"}}