{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SAMFDBIY4LCCC2O2WFNYTXQUBU","short_pith_number":"pith:SAMFDBIY","schema_version":"1.0","canonical_sha256":"9018518518e2c42169dab15b89de140d2f6c7e5ad9836f91ba9be4a63c068de0","source":{"kind":"arxiv","id":"2403.09065","version":3},"attestation_state":"computed","paper":{"title":"When Semantic Segmentation Meets Frequency Aliasing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lin Gu, Linwei Chen, Ying Fu","submitted_at":"2024-03-14T03:12:02Z","abstract_excerpt":"Despite recent advancements in semantic segmentation, where and what pixels are hard to segment remains largely unexplored. Existing research only separates an image into easy and hard regions and empirically observes the latter are associated with object boundaries. In this paper, we conduct a comprehensive analysis of hard pixel errors, categorizing them into three types: false responses, merging mistakes, and displacements. Our findings reveal a quantitative association between hard pixels and aliasing, which is distortion caused by the overlapping of frequency components in the Fourier dom"},"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":"2403.09065","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T03:12:02Z","cross_cats_sorted":[],"title_canon_sha256":"bdb38bcce4308ec858d36648e1089b1227b1968103f6f5ac092fbf151f86f55a","abstract_canon_sha256":"f0c78b940af4d80571dcd602818d5776305be6a9ac97df36ddb0d7a341eb599e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:03.651053Z","signature_b64":"BmqAat+UzEjNsQ5dEnYqx8eqVQC1HJkytXVRSHbLYkNeNWUsHjW572FyNLp9VxlwSjn+Qz+EGxJv7mCIPaKuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9018518518e2c42169dab15b89de140d2f6c7e5ad9836f91ba9be4a63c068de0","last_reissued_at":"2026-07-05T08:00:03.650560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:03.650560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Semantic Segmentation Meets Frequency Aliasing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lin Gu, Linwei Chen, Ying Fu","submitted_at":"2024-03-14T03:12:02Z","abstract_excerpt":"Despite recent advancements in semantic segmentation, where and what pixels are hard to segment remains largely unexplored. Existing research only separates an image into easy and hard regions and empirically observes the latter are associated with object boundaries. In this paper, we conduct a comprehensive analysis of hard pixel errors, categorizing them into three types: false responses, merging mistakes, and displacements. Our findings reveal a quantitative association between hard pixels and aliasing, which is distortion caused by the overlapping of frequency components in the Fourier dom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09065","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/2403.09065/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":"2403.09065","created_at":"2026-07-05T08:00:03.650621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09065v3","created_at":"2026-07-05T08:00:03.650621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09065","created_at":"2026-07-05T08:00:03.650621+00:00"},{"alias_kind":"pith_short_12","alias_value":"SAMFDBIY4LCC","created_at":"2026-07-05T08:00:03.650621+00:00"},{"alias_kind":"pith_short_16","alias_value":"SAMFDBIY4LCCC2O2","created_at":"2026-07-05T08:00:03.650621+00:00"},{"alias_kind":"pith_short_8","alias_value":"SAMFDBIY","created_at":"2026-07-05T08:00:03.650621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14526","citing_title":"FreqTrack: Frequency Learning based Vision Transformer for RGB-Event Object Tracking","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SAMFDBIY4LCCC2O2WFNYTXQUBU","json":"https://pith.science/pith/SAMFDBIY4LCCC2O2WFNYTXQUBU.json","graph_json":"https://pith.science/api/pith-number/SAMFDBIY4LCCC2O2WFNYTXQUBU/graph.json","events_json":"https://pith.science/api/pith-number/SAMFDBIY4LCCC2O2WFNYTXQUBU/events.json","paper":"https://pith.science/paper/SAMFDBIY"},"agent_actions":{"view_html":"https://pith.science/pith/SAMFDBIY4LCCC2O2WFNYTXQUBU","download_json":"https://pith.science/pith/SAMFDBIY4LCCC2O2WFNYTXQUBU.json","view_paper":"https://pith.science/paper/SAMFDBIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09065&json=true","fetch_graph":"https://pith.science/api/pith-number/SAMFDBIY4LCCC2O2WFNYTXQUBU/graph.json","fetch_events":"https://pith.science/api/pith-number/SAMFDBIY4LCCC2O2WFNYTXQUBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SAMFDBIY4LCCC2O2WFNYTXQUBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SAMFDBIY4LCCC2O2WFNYTXQUBU/action/storage_attestation","attest_author":"https://pith.science/pith/SAMFDBIY4LCCC2O2WFNYTXQUBU/action/author_attestation","sign_citation":"https://pith.science/pith/SAMFDBIY4LCCC2O2WFNYTXQUBU/action/citation_signature","submit_replication":"https://pith.science/pith/SAMFDBIY4LCCC2O2WFNYTXQUBU/action/replication_record"}},"created_at":"2026-07-05T08:00:03.650621+00:00","updated_at":"2026-07-05T08:00:03.650621+00:00"}