{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VCALEJWR2UOLDTD4YPLUAJT7BJ","short_pith_number":"pith:VCALEJWR","schema_version":"1.0","canonical_sha256":"a880b226d1d51cb1cc7cc3d740267f0a4c4f7e51fa6dd431e91499818ad592cd","source":{"kind":"arxiv","id":"2412.11890","version":2},"attestation_state":"computed","paper":{"title":"SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Meng Lou, Yizhou Yu, Yunxiang Fu","submitted_at":"2024-12-16T15:38:25Z","abstract_excerpt":"High-quality semantic segmentation relies on three key capabilities: global context modeling, local detail encoding, and multi-scale feature extraction. However, recent methods struggle to possess all these capabilities simultaneously. Hence, we aim to empower segmentation networks to simultaneously carry out efficient global context modeling, high-quality local detail encoding, and rich multi-scale feature representation for varying input resolutions. In this paper, we introduce SegMAN, a novel linear-time model comprising a hybrid feature encoder dubbed SegMAN Encoder, and a decoder based on"},"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":"2412.11890","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T15:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"61bf897082dda049ddfad40f27ae42c34c11e19c8a06003d055bacb27b966f6c","abstract_canon_sha256":"707a31beb3c5f7660a07bcee8bf96d0f56ed97eeaebadb03afd6a1fd40ae4d46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:15.407284Z","signature_b64":"ATUCAihRVunumgdvxsezjMBggjc8hvKv3wXLVuPX63E6AaQOVZXo+7vOqI7LycDkc5I8j4Bh1MZCk90bYrY/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a880b226d1d51cb1cc7cc3d740267f0a4c4f7e51fa6dd431e91499818ad592cd","last_reissued_at":"2026-07-05T10:40:15.406704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:15.406704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Meng Lou, Yizhou Yu, Yunxiang Fu","submitted_at":"2024-12-16T15:38:25Z","abstract_excerpt":"High-quality semantic segmentation relies on three key capabilities: global context modeling, local detail encoding, and multi-scale feature extraction. However, recent methods struggle to possess all these capabilities simultaneously. Hence, we aim to empower segmentation networks to simultaneously carry out efficient global context modeling, high-quality local detail encoding, and rich multi-scale feature representation for varying input resolutions. In this paper, we introduce SegMAN, a novel linear-time model comprising a hybrid feature encoder dubbed SegMAN Encoder, and a decoder based on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11890","kind":"arxiv","version":2},"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/2412.11890/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":"2412.11890","created_at":"2026-07-05T10:40:15.406765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11890v2","created_at":"2026-07-05T10:40:15.406765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11890","created_at":"2026-07-05T10:40:15.406765+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCALEJWR2UOL","created_at":"2026-07-05T10:40:15.406765+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCALEJWR2UOLDTD4","created_at":"2026-07-05T10:40:15.406765+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCALEJWR","created_at":"2026-07-05T10:40:15.406765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12640","citing_title":"MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VCALEJWR2UOLDTD4YPLUAJT7BJ","json":"https://pith.science/pith/VCALEJWR2UOLDTD4YPLUAJT7BJ.json","graph_json":"https://pith.science/api/pith-number/VCALEJWR2UOLDTD4YPLUAJT7BJ/graph.json","events_json":"https://pith.science/api/pith-number/VCALEJWR2UOLDTD4YPLUAJT7BJ/events.json","paper":"https://pith.science/paper/VCALEJWR"},"agent_actions":{"view_html":"https://pith.science/pith/VCALEJWR2UOLDTD4YPLUAJT7BJ","download_json":"https://pith.science/pith/VCALEJWR2UOLDTD4YPLUAJT7BJ.json","view_paper":"https://pith.science/paper/VCALEJWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11890&json=true","fetch_graph":"https://pith.science/api/pith-number/VCALEJWR2UOLDTD4YPLUAJT7BJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VCALEJWR2UOLDTD4YPLUAJT7BJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCALEJWR2UOLDTD4YPLUAJT7BJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCALEJWR2UOLDTD4YPLUAJT7BJ/action/storage_attestation","attest_author":"https://pith.science/pith/VCALEJWR2UOLDTD4YPLUAJT7BJ/action/author_attestation","sign_citation":"https://pith.science/pith/VCALEJWR2UOLDTD4YPLUAJT7BJ/action/citation_signature","submit_replication":"https://pith.science/pith/VCALEJWR2UOLDTD4YPLUAJT7BJ/action/replication_record"}},"created_at":"2026-07-05T10:40:15.406765+00:00","updated_at":"2026-07-05T10:40:15.406765+00:00"}