{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LVXAD2AIX6IQF7UFQ5EDCRIJ75","short_pith_number":"pith:LVXAD2AI","schema_version":"1.0","canonical_sha256":"5d6e01e808bf9102fe858748314509ff627f8d6a848619cd9417470dd3cbeac4","source":{"kind":"arxiv","id":"2504.19506","version":1},"attestation_state":"computed","paper":{"title":"SynergyAmodal: Deocclude Anything with Text Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Yi, Jiawei Lai, Liujuan Cao, Mingbao Lin, Shengchuan Zhang, Xinyang Li, Yansong Qu","submitted_at":"2025-04-28T06:04:17Z","abstract_excerpt":"Image deocclusion (or amodal completion) aims to recover the invisible regions (\\ie, shape and appearance) of occluded instances in images. Despite recent advances, the scarcity of high-quality data that balances diversity, plausibility, and fidelity remains a major obstacle. To address this challenge, we identify three critical elements: leveraging in-the-wild image data for diversity, incorporating human expertise for plausibility, and utilizing generative priors for fidelity. We propose SynergyAmodal, a novel framework for co-synthesizing in-the-wild amodal datasets with comprehensive shape"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.19506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T06:04:17Z","cross_cats_sorted":[],"title_canon_sha256":"4ed869411f527329a6e63df69c30f1de2ccaf46da6803ee020a1ae764e98e3da","abstract_canon_sha256":"1b7d9d218b6fcf0e3194a38d110e5f9f31c4c7436f89fe5ae2c0da8f26281999"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:58.501632Z","signature_b64":"7NT/YdDlQk7280ebqdCOx7QpvinBjHzM4eflTvvCo1El+QcB6RpHAihwm7ekp/97I+/U6QUU4VWhcMkJ7aIgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d6e01e808bf9102fe858748314509ff627f8d6a848619cd9417470dd3cbeac4","last_reissued_at":"2026-07-05T10:54:58.501135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:58.501135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynergyAmodal: Deocclude Anything with Text Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Yi, Jiawei Lai, Liujuan Cao, Mingbao Lin, Shengchuan Zhang, Xinyang Li, Yansong Qu","submitted_at":"2025-04-28T06:04:17Z","abstract_excerpt":"Image deocclusion (or amodal completion) aims to recover the invisible regions (\\ie, shape and appearance) of occluded instances in images. Despite recent advances, the scarcity of high-quality data that balances diversity, plausibility, and fidelity remains a major obstacle. To address this challenge, we identify three critical elements: leveraging in-the-wild image data for diversity, incorporating human expertise for plausibility, and utilizing generative priors for fidelity. We propose SynergyAmodal, a novel framework for co-synthesizing in-the-wild amodal datasets with comprehensive shape"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19506","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/2504.19506/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.19506","created_at":"2026-07-05T10:54:58.501197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.19506v1","created_at":"2026-07-05T10:54:58.501197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19506","created_at":"2026-07-05T10:54:58.501197+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVXAD2AIX6IQ","created_at":"2026-07-05T10:54:58.501197+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVXAD2AIX6IQF7UF","created_at":"2026-07-05T10:54:58.501197+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVXAD2AI","created_at":"2026-07-05T10:54:58.501197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09619","citing_title":"Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LVXAD2AIX6IQF7UFQ5EDCRIJ75","json":"https://pith.science/pith/LVXAD2AIX6IQF7UFQ5EDCRIJ75.json","graph_json":"https://pith.science/api/pith-number/LVXAD2AIX6IQF7UFQ5EDCRIJ75/graph.json","events_json":"https://pith.science/api/pith-number/LVXAD2AIX6IQF7UFQ5EDCRIJ75/events.json","paper":"https://pith.science/paper/LVXAD2AI"},"agent_actions":{"view_html":"https://pith.science/pith/LVXAD2AIX6IQF7UFQ5EDCRIJ75","download_json":"https://pith.science/pith/LVXAD2AIX6IQF7UFQ5EDCRIJ75.json","view_paper":"https://pith.science/paper/LVXAD2AI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.19506&json=true","fetch_graph":"https://pith.science/api/pith-number/LVXAD2AIX6IQF7UFQ5EDCRIJ75/graph.json","fetch_events":"https://pith.science/api/pith-number/LVXAD2AIX6IQF7UFQ5EDCRIJ75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVXAD2AIX6IQF7UFQ5EDCRIJ75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVXAD2AIX6IQF7UFQ5EDCRIJ75/action/storage_attestation","attest_author":"https://pith.science/pith/LVXAD2AIX6IQF7UFQ5EDCRIJ75/action/author_attestation","sign_citation":"https://pith.science/pith/LVXAD2AIX6IQF7UFQ5EDCRIJ75/action/citation_signature","submit_replication":"https://pith.science/pith/LVXAD2AIX6IQF7UFQ5EDCRIJ75/action/replication_record"}},"created_at":"2026-07-05T10:54:58.501197+00:00","updated_at":"2026-07-05T10:54:58.501197+00:00"}