{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q35GPYVJH74MFXYMFXUEGMIO5L","short_pith_number":"pith:Q35GPYVJ","schema_version":"1.0","canonical_sha256":"86fa67e2a93ff8c2df0c2de843310eeae444fa6f1fcccad7aebaff152109f807","source":{"kind":"arxiv","id":"2312.12425","version":1},"attestation_state":"computed","paper":{"title":"SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Henghui Ding, Jiajun Liu, Jun Hao Liew, Mengyu Wang, Yao Zhao, Yunchao Wei","submitted_at":"2023-12-19T18:53:47Z","abstract_excerpt":"In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by interpreting segmentation refinement as a data generation process. As a result, the refinement process can be smoothly implemented through a series of denoising diffusion steps. Specifically, SegRefiner takes coarse masks as inputs and refines them using a discrete diffusion process. By predicting the label and corresponding states-transition probabilities for each "},"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":"2312.12425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T18:53:47Z","cross_cats_sorted":[],"title_canon_sha256":"ff94465985acfb33a213d80e033c5a36f16f511e1f087fc27a383bdcc25b023b","abstract_canon_sha256":"b1ebbe2fd66e05730be2c958f597ca4779e5a3cba186c61b5d367998a1d2a2a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:03.434716Z","signature_b64":"UkzJQNE66Zy3UR2AZXsSucbQgxcAo688hk7xf0ztn2OptJZjho8wZdxWHOE01v9W3oJcMjjxqmxwIvMLj0EfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86fa67e2a93ff8c2df0c2de843310eeae444fa6f1fcccad7aebaff152109f807","last_reissued_at":"2026-07-05T07:26:03.434195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:03.434195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Henghui Ding, Jiajun Liu, Jun Hao Liew, Mengyu Wang, Yao Zhao, Yunchao Wei","submitted_at":"2023-12-19T18:53:47Z","abstract_excerpt":"In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by interpreting segmentation refinement as a data generation process. As a result, the refinement process can be smoothly implemented through a series of denoising diffusion steps. Specifically, SegRefiner takes coarse masks as inputs and refines them using a discrete diffusion process. By predicting the label and corresponding states-transition probabilities for each "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12425","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/2312.12425/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":"2312.12425","created_at":"2026-07-05T07:26:03.434263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12425v1","created_at":"2026-07-05T07:26:03.434263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12425","created_at":"2026-07-05T07:26:03.434263+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q35GPYVJH74M","created_at":"2026-07-05T07:26:03.434263+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q35GPYVJH74MFXYM","created_at":"2026-07-05T07:26:03.434263+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q35GPYVJ","created_at":"2026-07-05T07:26:03.434263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22702","citing_title":"Modular Diffusion Models for Structured Visual Recognition","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05880","citing_title":"Contour Refinement using Discrete Diffusion in Low Data Regime","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q35GPYVJH74MFXYMFXUEGMIO5L","json":"https://pith.science/pith/Q35GPYVJH74MFXYMFXUEGMIO5L.json","graph_json":"https://pith.science/api/pith-number/Q35GPYVJH74MFXYMFXUEGMIO5L/graph.json","events_json":"https://pith.science/api/pith-number/Q35GPYVJH74MFXYMFXUEGMIO5L/events.json","paper":"https://pith.science/paper/Q35GPYVJ"},"agent_actions":{"view_html":"https://pith.science/pith/Q35GPYVJH74MFXYMFXUEGMIO5L","download_json":"https://pith.science/pith/Q35GPYVJH74MFXYMFXUEGMIO5L.json","view_paper":"https://pith.science/paper/Q35GPYVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12425&json=true","fetch_graph":"https://pith.science/api/pith-number/Q35GPYVJH74MFXYMFXUEGMIO5L/graph.json","fetch_events":"https://pith.science/api/pith-number/Q35GPYVJH74MFXYMFXUEGMIO5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q35GPYVJH74MFXYMFXUEGMIO5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q35GPYVJH74MFXYMFXUEGMIO5L/action/storage_attestation","attest_author":"https://pith.science/pith/Q35GPYVJH74MFXYMFXUEGMIO5L/action/author_attestation","sign_citation":"https://pith.science/pith/Q35GPYVJH74MFXYMFXUEGMIO5L/action/citation_signature","submit_replication":"https://pith.science/pith/Q35GPYVJH74MFXYMFXUEGMIO5L/action/replication_record"}},"created_at":"2026-07-05T07:26:03.434263+00:00","updated_at":"2026-07-05T07:26:03.434263+00:00"}