{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:OU6HTIME2RE4GYCRDWH775XLRK","short_pith_number":"pith:OU6HTIME","schema_version":"1.0","canonical_sha256":"753c79a184d449c360511d8ffff6eb8a9186c5bea57d2ec41a007d62d79118bd","source":{"kind":"arxiv","id":"1606.00915","version":2},"attestation_state":"computed","paper":{"title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan L. Yuille, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Liang-Chieh Chen","submitted_at":"2016-06-02T21:52:21Z","abstract_excerpt":"In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or 'atrous convolution', as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of paramet"},"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":"1606.00915","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-02T21:52:21Z","cross_cats_sorted":[],"title_canon_sha256":"9e4191a8b38a5373853faf4889da5ed246da7fea17d3a8e47d3ca57872775d32","abstract_canon_sha256":"8e772f071f9da6fa4eec87dab3137d1b73eec59e4238824b8be9b9b90d874205"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:38.930645Z","signature_b64":"q+3/lUa6AFqSVgyz61JMygaIVIX0IKcNRAWupbsCUvmRvU3MMD4ZeBMx5uZtqP4hIsh+WM+rgf92f9Yw5kjeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"753c79a184d449c360511d8ffff6eb8a9186c5bea57d2ec41a007d62d79118bd","last_reissued_at":"2026-05-18T00:44:38.930137Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:38.930137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan L. Yuille, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Liang-Chieh Chen","submitted_at":"2016-06-02T21:52:21Z","abstract_excerpt":"In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or 'atrous convolution', as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00915","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":""},"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":"1606.00915","created_at":"2026-05-18T00:44:38.930205+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.00915v2","created_at":"2026-05-18T00:44:38.930205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00915","created_at":"2026-05-18T00:44:38.930205+00:00"},{"alias_kind":"pith_short_12","alias_value":"OU6HTIME2RE4","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"OU6HTIME2RE4GYCR","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"OU6HTIME","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.23024","citing_title":"InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"1706.05587","citing_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OU6HTIME2RE4GYCRDWH775XLRK","json":"https://pith.science/pith/OU6HTIME2RE4GYCRDWH775XLRK.json","graph_json":"https://pith.science/api/pith-number/OU6HTIME2RE4GYCRDWH775XLRK/graph.json","events_json":"https://pith.science/api/pith-number/OU6HTIME2RE4GYCRDWH775XLRK/events.json","paper":"https://pith.science/paper/OU6HTIME"},"agent_actions":{"view_html":"https://pith.science/pith/OU6HTIME2RE4GYCRDWH775XLRK","download_json":"https://pith.science/pith/OU6HTIME2RE4GYCRDWH775XLRK.json","view_paper":"https://pith.science/paper/OU6HTIME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.00915&json=true","fetch_graph":"https://pith.science/api/pith-number/OU6HTIME2RE4GYCRDWH775XLRK/graph.json","fetch_events":"https://pith.science/api/pith-number/OU6HTIME2RE4GYCRDWH775XLRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OU6HTIME2RE4GYCRDWH775XLRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OU6HTIME2RE4GYCRDWH775XLRK/action/storage_attestation","attest_author":"https://pith.science/pith/OU6HTIME2RE4GYCRDWH775XLRK/action/author_attestation","sign_citation":"https://pith.science/pith/OU6HTIME2RE4GYCRDWH775XLRK/action/citation_signature","submit_replication":"https://pith.science/pith/OU6HTIME2RE4GYCRDWH775XLRK/action/replication_record"}},"created_at":"2026-05-18T00:44:38.930205+00:00","updated_at":"2026-05-18T00:44:38.930205+00:00"}