{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ULGIYH7RMEG772J3DK2QI2JIO7","short_pith_number":"pith:ULGIYH7R","canonical_record":{"source":{"id":"1711.00146","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-31T23:59:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7e86a21bd6f9ce5bc23e0a08446bd79bff5f53a914b3912fc67bbc7487df42f2","abstract_canon_sha256":"cd2356849be6cf0fdafb84ab066300c8cb583519f51f2052be60a4fdcf679969"},"schema_version":"1.0"},"canonical_sha256":"a2cc8c1ff1610dffe93b1ab504692877cfca8f82a72cfcbe65363fe04c5bb375","source":{"kind":"arxiv","id":"1711.00146","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00146","created_at":"2026-05-18T00:31:35Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00146v1","created_at":"2026-05-18T00:31:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00146","created_at":"2026-05-18T00:31:35Z"},{"alias_kind":"pith_short_12","alias_value":"ULGIYH7RMEG7","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"ULGIYH7RMEG772J3","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"ULGIYH7R","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ULGIYH7RMEG772J3DK2QI2JIO7","target":"record","payload":{"canonical_record":{"source":{"id":"1711.00146","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-31T23:59:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7e86a21bd6f9ce5bc23e0a08446bd79bff5f53a914b3912fc67bbc7487df42f2","abstract_canon_sha256":"cd2356849be6cf0fdafb84ab066300c8cb583519f51f2052be60a4fdcf679969"},"schema_version":"1.0"},"canonical_sha256":"a2cc8c1ff1610dffe93b1ab504692877cfca8f82a72cfcbe65363fe04c5bb375","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:35.084663Z","signature_b64":"o7XcKUD7L0gakAdHFBFyze7uRjrLM964WXfAjw1ajFc0qNflrqstGxFXA9e6jkGCph1kAvxBQdp60WdP6PPwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2cc8c1ff1610dffe93b1ab504692877cfca8f82a72cfcbe65363fe04c5bb375","last_reissued_at":"2026-05-18T00:31:35.083460Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:35.083460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.00146","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MR2MpAcKs/PndGmRA9LRqBFIypNYLC0JT5wC/YdQoFwApwUyy4NEdT11Ye+QzM56hTtt9YGLhHYt6M0Nue8FDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:43:00.342038Z"},"content_sha256":"b34366384241ee1a1ac442f044e5e9aebb9fcc2a736ef20295feaeae5bca78c9","schema_version":"1.0","event_id":"sha256:b34366384241ee1a1ac442f044e5e9aebb9fcc2a736ef20295feaeae5bca78c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ULGIYH7RMEG772J3DK2QI2JIO7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A multitask deep learning model for real-time deployment in embedded systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Atsuto Maki, Miquel Mart\\'i","submitted_at":"2017-10-31T23:59:23Z","abstract_excerpt":"We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We develop a multitask model for both Object Detection and Semantic Segmentation and analyze the challenges that appear during its training. Our multitask network is 1.6x faster, lighter and uses less memory than deploying the single-task models in parallel. We conclude that MTL has the potential to give superior performance in exchange of a more complex training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00146","kind":"arxiv","version":1},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J5K+/pxM4Ff7Vsuv5gXP/K8mO45P8gL9Fzc/Ub2/uWgRbgCRTMHFLsuU440K+kskXPNriZBd2YhXEfJN4GMmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:43:00.342738Z"},"content_sha256":"fb9a8fe5a0628aa8570d8d4579b1c97ba104e6bbd9f277a8661c7e2d686e78b6","schema_version":"1.0","event_id":"sha256:fb9a8fe5a0628aa8570d8d4579b1c97ba104e6bbd9f277a8661c7e2d686e78b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULGIYH7RMEG772J3DK2QI2JIO7/bundle.json","state_url":"https://pith.science/pith/ULGIYH7RMEG772J3DK2QI2JIO7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULGIYH7RMEG772J3DK2QI2JIO7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T21:43:00Z","links":{"resolver":"https://pith.science/pith/ULGIYH7RMEG772J3DK2QI2JIO7","bundle":"https://pith.science/pith/ULGIYH7RMEG772J3DK2QI2JIO7/bundle.json","state":"https://pith.science/pith/ULGIYH7RMEG772J3DK2QI2JIO7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULGIYH7RMEG772J3DK2QI2JIO7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ULGIYH7RMEG772J3DK2QI2JIO7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cd2356849be6cf0fdafb84ab066300c8cb583519f51f2052be60a4fdcf679969","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-31T23:59:23Z","title_canon_sha256":"7e86a21bd6f9ce5bc23e0a08446bd79bff5f53a914b3912fc67bbc7487df42f2"},"schema_version":"1.0","source":{"id":"1711.00146","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00146","created_at":"2026-05-18T00:31:35Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00146v1","created_at":"2026-05-18T00:31:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00146","created_at":"2026-05-18T00:31:35Z"},{"alias_kind":"pith_short_12","alias_value":"ULGIYH7RMEG7","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"ULGIYH7RMEG772J3","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"ULGIYH7R","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:fb9a8fe5a0628aa8570d8d4579b1c97ba104e6bbd9f277a8661c7e2d686e78b6","target":"graph","created_at":"2026-05-18T00:31:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We develop a multitask model for both Object Detection and Semantic Segmentation and analyze the challenges that appear during its training. Our multitask network is 1.6x faster, lighter and uses less memory than deploying the single-task models in parallel. We conclude that MTL has the potential to give superior performance in exchange of a more complex training","authors_text":"Atsuto Maki, Miquel Mart\\'i","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-31T23:59:23Z","title":"A multitask deep learning model for real-time deployment in embedded systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00146","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b34366384241ee1a1ac442f044e5e9aebb9fcc2a736ef20295feaeae5bca78c9","target":"record","created_at":"2026-05-18T00:31:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cd2356849be6cf0fdafb84ab066300c8cb583519f51f2052be60a4fdcf679969","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-31T23:59:23Z","title_canon_sha256":"7e86a21bd6f9ce5bc23e0a08446bd79bff5f53a914b3912fc67bbc7487df42f2"},"schema_version":"1.0","source":{"id":"1711.00146","kind":"arxiv","version":1}},"canonical_sha256":"a2cc8c1ff1610dffe93b1ab504692877cfca8f82a72cfcbe65363fe04c5bb375","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2cc8c1ff1610dffe93b1ab504692877cfca8f82a72cfcbe65363fe04c5bb375","first_computed_at":"2026-05-18T00:31:35.083460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:35.083460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o7XcKUD7L0gakAdHFBFyze7uRjrLM964WXfAjw1ajFc0qNflrqstGxFXA9e6jkGCph1kAvxBQdp60WdP6PPwAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:35.084663Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.00146","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b34366384241ee1a1ac442f044e5e9aebb9fcc2a736ef20295feaeae5bca78c9","sha256:fb9a8fe5a0628aa8570d8d4579b1c97ba104e6bbd9f277a8661c7e2d686e78b6"],"state_sha256":"0a8489f3bc5e6f255dc2e2960961ce2aef786c5d6fdbc8366a3cb66ef23fbc9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OYaBBGe27i9aGQYpJTn45DmS/LmxWCzjiPUkA60ol9f55omKb1d7CgfbIhp+VOWmvr3nlLi8U3Q8g3D9GFwzCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T21:43:00.346104Z","bundle_sha256":"1e313aadb122f7700bfecd65ec50612f0c60c203eca7bdf5dcd95816f31e3ae4"}}