{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UVA4IMWCXYSKTOR2MHMQCDML7N","short_pith_number":"pith:UVA4IMWC","schema_version":"1.0","canonical_sha256":"a541c432c2be24a9ba3a61d9010d8bfb5f69b0d8f64ddc8b0b4157c5c5c0da51","source":{"kind":"arxiv","id":"2211.06560","version":3},"attestation_state":"computed","paper":{"title":"PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaopeng Shen, Daniel Kifer, Savinay Nagendra","submitted_at":"2022-11-12T03:49:22Z","abstract_excerpt":"The purpose of binary segmentation models is to determine which pixels belong to an object of interest (e.g., which pixels in an image are part of roads). The models assign a logit score (i.e., probability) to each pixel and these are converted into predictions by thresholding (i.e., each pixel with logit score $\\geq \\tau$ is predicted to be part of a road). However, a common phenomenon in current and former state-of-the-art segmentation models is spatial bias -- in some patches, the logit scores are consistently biased upwards and in others they are consistently biased downwards. These biases"},"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":"2211.06560","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-12T03:49:22Z","cross_cats_sorted":[],"title_canon_sha256":"99a9fbe966b34a9abf499468225542add01e0865d68fd5760b814adb449f76fb","abstract_canon_sha256":"efe9ce7c230402d91ae9b0161b22164eca2288b53124943b34de441d685b861f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:58.056704Z","signature_b64":"lb1tpXCVMD7M1q/BHN74nLSjoBGrRml1Ytnb/kuskZ6GvJZ+Fbi/OJ1LntrHmGjErFJ5PbQ1Ju1B2kpaJF/hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a541c432c2be24a9ba3a61d9010d8bfb5f69b0d8f64ddc8b0b4157c5c5c0da51","last_reissued_at":"2026-07-05T06:49:58.056283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:58.056283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaopeng Shen, Daniel Kifer, Savinay Nagendra","submitted_at":"2022-11-12T03:49:22Z","abstract_excerpt":"The purpose of binary segmentation models is to determine which pixels belong to an object of interest (e.g., which pixels in an image are part of roads). The models assign a logit score (i.e., probability) to each pixel and these are converted into predictions by thresholding (i.e., each pixel with logit score $\\geq \\tau$ is predicted to be part of a road). However, a common phenomenon in current and former state-of-the-art segmentation models is spatial bias -- in some patches, the logit scores are consistently biased upwards and in others they are consistently biased downwards. These biases"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06560","kind":"arxiv","version":3},"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/2211.06560/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":"2211.06560","created_at":"2026-07-05T06:49:58.056344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.06560v3","created_at":"2026-07-05T06:49:58.056344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06560","created_at":"2026-07-05T06:49:58.056344+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVA4IMWCXYSK","created_at":"2026-07-05T06:49:58.056344+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVA4IMWCXYSKTOR2","created_at":"2026-07-05T06:49:58.056344+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVA4IMWC","created_at":"2026-07-05T06:49:58.056344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11998","citing_title":"SAMIC: Segment Anything with In-Context Spatial Prompt Engineering","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UVA4IMWCXYSKTOR2MHMQCDML7N","json":"https://pith.science/pith/UVA4IMWCXYSKTOR2MHMQCDML7N.json","graph_json":"https://pith.science/api/pith-number/UVA4IMWCXYSKTOR2MHMQCDML7N/graph.json","events_json":"https://pith.science/api/pith-number/UVA4IMWCXYSKTOR2MHMQCDML7N/events.json","paper":"https://pith.science/paper/UVA4IMWC"},"agent_actions":{"view_html":"https://pith.science/pith/UVA4IMWCXYSKTOR2MHMQCDML7N","download_json":"https://pith.science/pith/UVA4IMWCXYSKTOR2MHMQCDML7N.json","view_paper":"https://pith.science/paper/UVA4IMWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.06560&json=true","fetch_graph":"https://pith.science/api/pith-number/UVA4IMWCXYSKTOR2MHMQCDML7N/graph.json","fetch_events":"https://pith.science/api/pith-number/UVA4IMWCXYSKTOR2MHMQCDML7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVA4IMWCXYSKTOR2MHMQCDML7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVA4IMWCXYSKTOR2MHMQCDML7N/action/storage_attestation","attest_author":"https://pith.science/pith/UVA4IMWCXYSKTOR2MHMQCDML7N/action/author_attestation","sign_citation":"https://pith.science/pith/UVA4IMWCXYSKTOR2MHMQCDML7N/action/citation_signature","submit_replication":"https://pith.science/pith/UVA4IMWCXYSKTOR2MHMQCDML7N/action/replication_record"}},"created_at":"2026-07-05T06:49:58.056344+00:00","updated_at":"2026-07-05T06:49:58.056344+00:00"}