{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:24XALYP5DWWTKE2THOTOM5GUHR","short_pith_number":"pith:24XALYP5","schema_version":"1.0","canonical_sha256":"d72e05e1fd1dad3513533ba6e674d43c51933f42b6b788236305e742a296e3f2","source":{"kind":"arxiv","id":"1606.01735","version":2},"attestation_state":"computed","paper":{"title":"Integrated perception with recurrent multi-task neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrea Vedaldi, Hakan Bilen","submitted_at":"2016-06-06T13:27:25Z","abstract_excerpt":"Modern discriminative predictors have been shown to match natural intelligences in specific perceptual tasks in image classification, object and part detection, boundary extraction, etc. However, a major advantage that natural intelligences still have is that they work well for \"all\" perceptual problems together, solving them efficiently and coherently in an \"integrated manner\". In order to capture some of these advantages in machine perception, we ask two questions: whether deep neural networks can learn universal image representations, useful not only for a single task but for all of them, a"},"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":"1606.01735","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-06T13:27:25Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"f09813f770b120e07a277e3060d724879a8a4390c0eb4fbee519ac5cbd8eda35","abstract_canon_sha256":"df68f0c34b9b59e59fcfcc46c94e93337c377da38a48cd39f754de7cc4f9a84c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:20.365291Z","signature_b64":"jWfzgntkg0CE/ig7BglQnq6FnM65YcMSKygIoVObQc+PZYvmOenuY1l7PT/3XrFxDbk2w+j/d8v6HdKjTgcGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d72e05e1fd1dad3513533ba6e674d43c51933f42b6b788236305e742a296e3f2","last_reissued_at":"2026-05-18T00:56:20.364473Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:20.364473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrated perception with recurrent multi-task neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrea Vedaldi, Hakan Bilen","submitted_at":"2016-06-06T13:27:25Z","abstract_excerpt":"Modern discriminative predictors have been shown to match natural intelligences in specific perceptual tasks in image classification, object and part detection, boundary extraction, etc. However, a major advantage that natural intelligences still have is that they work well for \"all\" perceptual problems together, solving them efficiently and coherently in an \"integrated manner\". In order to capture some of these advantages in machine perception, we ask two questions: whether deep neural networks can learn universal image representations, useful not only for a single task but for all of them, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.01735","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":"1606.01735","created_at":"2026-05-18T00:56:20.364611+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.01735v2","created_at":"2026-05-18T00:56:20.364611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.01735","created_at":"2026-05-18T00:56:20.364611+00:00"},{"alias_kind":"pith_short_12","alias_value":"24XALYP5DWWT","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"24XALYP5DWWTKE2T","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"24XALYP5","created_at":"2026-05-18T12:29:52.810259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24XALYP5DWWTKE2THOTOM5GUHR","json":"https://pith.science/pith/24XALYP5DWWTKE2THOTOM5GUHR.json","graph_json":"https://pith.science/api/pith-number/24XALYP5DWWTKE2THOTOM5GUHR/graph.json","events_json":"https://pith.science/api/pith-number/24XALYP5DWWTKE2THOTOM5GUHR/events.json","paper":"https://pith.science/paper/24XALYP5"},"agent_actions":{"view_html":"https://pith.science/pith/24XALYP5DWWTKE2THOTOM5GUHR","download_json":"https://pith.science/pith/24XALYP5DWWTKE2THOTOM5GUHR.json","view_paper":"https://pith.science/paper/24XALYP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.01735&json=true","fetch_graph":"https://pith.science/api/pith-number/24XALYP5DWWTKE2THOTOM5GUHR/graph.json","fetch_events":"https://pith.science/api/pith-number/24XALYP5DWWTKE2THOTOM5GUHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24XALYP5DWWTKE2THOTOM5GUHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24XALYP5DWWTKE2THOTOM5GUHR/action/storage_attestation","attest_author":"https://pith.science/pith/24XALYP5DWWTKE2THOTOM5GUHR/action/author_attestation","sign_citation":"https://pith.science/pith/24XALYP5DWWTKE2THOTOM5GUHR/action/citation_signature","submit_replication":"https://pith.science/pith/24XALYP5DWWTKE2THOTOM5GUHR/action/replication_record"}},"created_at":"2026-05-18T00:56:20.364611+00:00","updated_at":"2026-05-18T00:56:20.364611+00:00"}