{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Y3X45B4Q4IABMW37VMDIQLSO45","short_pith_number":"pith:Y3X45B4Q","schema_version":"1.0","canonical_sha256":"c6efce8790e200165b7fab06882e4ee758c879e48bbe07207bbe6c5c5d3ebd96","source":{"kind":"arxiv","id":"1603.08358","version":4},"attestation_state":"computed","paper":{"title":"Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Iasonas Kokkinos, Siddhartha Chandra","submitted_at":"2016-03-28T10:55:20Z","abstract_excerpt":"In this work we propose a structured prediction technique that combines the virtues of Gaussian Conditional Random Fields (G-CRF) with Deep Learning: (a) our structured prediction task has a unique global optimum that is obtained exactly from the solution of a linear system (b) the gradients of our model parameters are analytically computed using closed form expressions, in contrast to the memory-demanding contemporary deep structured prediction approaches that rely on back-propagation-through-time, (c) our pairwise terms do not have to be simple hand-crafted expressions, as in the line of wor"},"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":"1603.08358","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-28T10:55:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"544e1ca9cb375f6e4f0b2f125c878295c5aa7dea7de77e146cf8ad5c849a7968","abstract_canon_sha256":"dd3a48c235076752c2b7610d45c38ed0d639c1a4d9de61ef3341fb912d5801bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:20.814799Z","signature_b64":"lLT+HnNtgk6JM8tyzerlNYePuYqEEPIpqMzmKKrbnuUAlb/oJP7ps7sufpmw539yPxg42ZM14q0H9uGPSRuVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6efce8790e200165b7fab06882e4ee758c879e48bbe07207bbe6c5c5d3ebd96","last_reissued_at":"2026-05-18T00:56:20.814071Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:20.814071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Iasonas Kokkinos, Siddhartha Chandra","submitted_at":"2016-03-28T10:55:20Z","abstract_excerpt":"In this work we propose a structured prediction technique that combines the virtues of Gaussian Conditional Random Fields (G-CRF) with Deep Learning: (a) our structured prediction task has a unique global optimum that is obtained exactly from the solution of a linear system (b) the gradients of our model parameters are analytically computed using closed form expressions, in contrast to the memory-demanding contemporary deep structured prediction approaches that rely on back-propagation-through-time, (c) our pairwise terms do not have to be simple hand-crafted expressions, as in the line of wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.08358","kind":"arxiv","version":4},"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":"1603.08358","created_at":"2026-05-18T00:56:20.814195+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.08358v4","created_at":"2026-05-18T00:56:20.814195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.08358","created_at":"2026-05-18T00:56:20.814195+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3X45B4Q4IAB","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3X45B4Q4IABMW37","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3X45B4Q","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1706.05587","citing_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3X45B4Q4IABMW37VMDIQLSO45","json":"https://pith.science/pith/Y3X45B4Q4IABMW37VMDIQLSO45.json","graph_json":"https://pith.science/api/pith-number/Y3X45B4Q4IABMW37VMDIQLSO45/graph.json","events_json":"https://pith.science/api/pith-number/Y3X45B4Q4IABMW37VMDIQLSO45/events.json","paper":"https://pith.science/paper/Y3X45B4Q"},"agent_actions":{"view_html":"https://pith.science/pith/Y3X45B4Q4IABMW37VMDIQLSO45","download_json":"https://pith.science/pith/Y3X45B4Q4IABMW37VMDIQLSO45.json","view_paper":"https://pith.science/paper/Y3X45B4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.08358&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3X45B4Q4IABMW37VMDIQLSO45/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3X45B4Q4IABMW37VMDIQLSO45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3X45B4Q4IABMW37VMDIQLSO45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3X45B4Q4IABMW37VMDIQLSO45/action/storage_attestation","attest_author":"https://pith.science/pith/Y3X45B4Q4IABMW37VMDIQLSO45/action/author_attestation","sign_citation":"https://pith.science/pith/Y3X45B4Q4IABMW37VMDIQLSO45/action/citation_signature","submit_replication":"https://pith.science/pith/Y3X45B4Q4IABMW37VMDIQLSO45/action/replication_record"}},"created_at":"2026-05-18T00:56:20.814195+00:00","updated_at":"2026-05-18T00:56:20.814195+00:00"}