{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OTZXCOTPPFBPVDPAXBWRI74DMV","short_pith_number":"pith:OTZXCOTP","schema_version":"1.0","canonical_sha256":"74f3713a6f7942fa8de0b86d147f836566502fbd1109f6595eadb8ac42ddc51f","source":{"kind":"arxiv","id":"1705.07420","version":3},"attestation_state":"computed","paper":{"title":"Large-Scale Classification of Structured Objects using a CRF with Deep Class Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eran Goldman, Jacob Goldberger","submitted_at":"2017-05-21T09:44:17Z","abstract_excerpt":"This paper presents a novel deep learning architecture to classify structured objects in datasets with a large number of visually similar categories. We model sequences of images as linear-chain CRFs, and jointly learn the parameters from both local-visual features and neighboring classes. The visual features are computed by convolutional layers, and the class embeddings are learned by factorizing the CRF pairwise potential matrix. This forms a highly nonlinear objective function which is trained by optimizing a local likelihood approximation with batch-normalization. This model overcomes the "},"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":"1705.07420","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-21T09:44:17Z","cross_cats_sorted":[],"title_canon_sha256":"ebeb596dc07f59a04ef00a821c0df8bd9a1f63a0363d811ee625f3c1303ac771","abstract_canon_sha256":"a60320a5b1355e7d90f7ab6c2d53912f58ee4ce30a58e0a1906dcd9f12bf7d1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:27.687052Z","signature_b64":"Rj9nmIEBsYT9GaK2P1+ZGXGryquzSm9os9wRpU+L4yj4NeO1lFaR6Kd1e8ZXpfOubXcEIchecI2ySI8iRiduCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74f3713a6f7942fa8de0b86d147f836566502fbd1109f6595eadb8ac42ddc51f","last_reissued_at":"2026-07-05T00:19:27.686629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:27.686629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Classification of Structured Objects using a CRF with Deep Class Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eran Goldman, Jacob Goldberger","submitted_at":"2017-05-21T09:44:17Z","abstract_excerpt":"This paper presents a novel deep learning architecture to classify structured objects in datasets with a large number of visually similar categories. We model sequences of images as linear-chain CRFs, and jointly learn the parameters from both local-visual features and neighboring classes. The visual features are computed by convolutional layers, and the class embeddings are learned by factorizing the CRF pairwise potential matrix. This forms a highly nonlinear objective function which is trained by optimizing a local likelihood approximation with batch-normalization. This model overcomes the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07420","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/1705.07420/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":"1705.07420","created_at":"2026-07-05T00:19:27.686688+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07420v3","created_at":"2026-07-05T00:19:27.686688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07420","created_at":"2026-07-05T00:19:27.686688+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTZXCOTPPFBP","created_at":"2026-07-05T00:19:27.686688+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTZXCOTPPFBPVDPA","created_at":"2026-07-05T00:19:27.686688+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTZXCOTP","created_at":"2026-07-05T00:19:27.686688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.11658","citing_title":"Autoregressive Text Generation Beyond Feedback Loops","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTZXCOTPPFBPVDPAXBWRI74DMV","json":"https://pith.science/pith/OTZXCOTPPFBPVDPAXBWRI74DMV.json","graph_json":"https://pith.science/api/pith-number/OTZXCOTPPFBPVDPAXBWRI74DMV/graph.json","events_json":"https://pith.science/api/pith-number/OTZXCOTPPFBPVDPAXBWRI74DMV/events.json","paper":"https://pith.science/paper/OTZXCOTP"},"agent_actions":{"view_html":"https://pith.science/pith/OTZXCOTPPFBPVDPAXBWRI74DMV","download_json":"https://pith.science/pith/OTZXCOTPPFBPVDPAXBWRI74DMV.json","view_paper":"https://pith.science/paper/OTZXCOTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07420&json=true","fetch_graph":"https://pith.science/api/pith-number/OTZXCOTPPFBPVDPAXBWRI74DMV/graph.json","fetch_events":"https://pith.science/api/pith-number/OTZXCOTPPFBPVDPAXBWRI74DMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTZXCOTPPFBPVDPAXBWRI74DMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTZXCOTPPFBPVDPAXBWRI74DMV/action/storage_attestation","attest_author":"https://pith.science/pith/OTZXCOTPPFBPVDPAXBWRI74DMV/action/author_attestation","sign_citation":"https://pith.science/pith/OTZXCOTPPFBPVDPAXBWRI74DMV/action/citation_signature","submit_replication":"https://pith.science/pith/OTZXCOTPPFBPVDPAXBWRI74DMV/action/replication_record"}},"created_at":"2026-07-05T00:19:27.686688+00:00","updated_at":"2026-07-05T00:19:27.686688+00:00"}