{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:54V4MPRRBJPI7DRBLARLF7XOAX","short_pith_number":"pith:54V4MPRR","canonical_record":{"source":{"id":"2109.05779","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T08:58:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4d29770343721e9faccd86203eac0202c742ffef2f1de7907ad6428aaf95a95","abstract_canon_sha256":"eb0e9a67bc25501e28e72e37d6adc070b17f5eff8545385295a515836171693e"},"schema_version":"1.0"},"canonical_sha256":"ef2bc63e310a5e8f8e215822b2feee05facd01c6b9a2496be32a08e72bf72625","source":{"kind":"arxiv","id":"2109.05779","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05779","created_at":"2026-07-05T03:28:25Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05779v2","created_at":"2026-07-05T03:28:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05779","created_at":"2026-07-05T03:28:25Z"},{"alias_kind":"pith_short_12","alias_value":"54V4MPRRBJPI","created_at":"2026-07-05T03:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"54V4MPRRBJPI7DRB","created_at":"2026-07-05T03:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"54V4MPRR","created_at":"2026-07-05T03:28:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:54V4MPRRBJPI7DRBLARLF7XOAX","target":"record","payload":{"canonical_record":{"source":{"id":"2109.05779","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T08:58:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4d29770343721e9faccd86203eac0202c742ffef2f1de7907ad6428aaf95a95","abstract_canon_sha256":"eb0e9a67bc25501e28e72e37d6adc070b17f5eff8545385295a515836171693e"},"schema_version":"1.0"},"canonical_sha256":"ef2bc63e310a5e8f8e215822b2feee05facd01c6b9a2496be32a08e72bf72625","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:25.378475Z","signature_b64":"ltxiddX2TVMdsVbSiNxkUN6V7pIESMN+QRvNVnzST3PJeFGhlxm4q+GiMUpz6euZBArPJ+n8zryeYkEzYP5NBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef2bc63e310a5e8f8e215822b2feee05facd01c6b9a2496be32a08e72bf72625","last_reissued_at":"2026-07-05T03:28:25.378063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:25.378063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.05779","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:28:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IcLv95j5UPfs8LXijyTS6Uviz5w4Yr39YnMaSnT+8CXkAFFVSA7t9Zrkha2B1pXCmAinGrcbOynfeKBMvptcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:14:55.571039Z"},"content_sha256":"31a9b85ff1a7c1ce09b9f4d4b4d74545424811b77aed113e95127aaa1e716cb2","schema_version":"1.0","event_id":"sha256:31a9b85ff1a7c1ce09b9f4d4b4d74545424811b77aed113e95127aaa1e716cb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:54V4MPRRBJPI7DRBLARLF7XOAX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Joint Source-Channel Coding for Multi-Task Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiahui Li, Mengyang Wang, Mengyao Ma, Xiaopeng Fan, Zhicong Zhang","submitted_at":"2021-09-13T08:58:02Z","abstract_excerpt":"Multi-task learning (MTL) is an efficient way to improve the performance of related tasks by sharing knowledge. However, most existing MTL networks run on a single end and are not suitable for collaborative intelligence (CI) scenarios. In this work, we propose an MTL network with a deep joint source-channel coding (JSCC) framework, which allows operating under CI scenarios. We first propose a feature fusion based MTL network (FFMNet) for joint object detection and semantic segmentation. Compared with other MTL networks, FFMNet gets higher performance with fewer parameters. Then FFMNet is split"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05779","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.05779/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:28:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ymm3XNWYzao04WkGQNRitFPr41iJaKGZ9WcEX1dLfuIzsriDsAdR50SaYvuSOSNEQGCJYW4qfMzY8NTFBX3MDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:14:55.571436Z"},"content_sha256":"294732f95a1808a4d1cdd3b21032bfa54512e6021df54f0bf17a3fb4456d9cb2","schema_version":"1.0","event_id":"sha256:294732f95a1808a4d1cdd3b21032bfa54512e6021df54f0bf17a3fb4456d9cb2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX/bundle.json","state_url":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54V4MPRRBJPI7DRBLARLF7XOAX/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":"2026-07-06T14:14:55Z","links":{"resolver":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX","bundle":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX/bundle.json","state":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54V4MPRRBJPI7DRBLARLF7XOAX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:54V4MPRRBJPI7DRBLARLF7XOAX","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":"eb0e9a67bc25501e28e72e37d6adc070b17f5eff8545385295a515836171693e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T08:58:02Z","title_canon_sha256":"c4d29770343721e9faccd86203eac0202c742ffef2f1de7907ad6428aaf95a95"},"schema_version":"1.0","source":{"id":"2109.05779","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05779","created_at":"2026-07-05T03:28:25Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05779v2","created_at":"2026-07-05T03:28:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05779","created_at":"2026-07-05T03:28:25Z"},{"alias_kind":"pith_short_12","alias_value":"54V4MPRRBJPI","created_at":"2026-07-05T03:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"54V4MPRRBJPI7DRB","created_at":"2026-07-05T03:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"54V4MPRR","created_at":"2026-07-05T03:28:25Z"}],"graph_snapshots":[{"event_id":"sha256:294732f95a1808a4d1cdd3b21032bfa54512e6021df54f0bf17a3fb4456d9cb2","target":"graph","created_at":"2026-07-05T03:28:25Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.05779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task learning (MTL) is an efficient way to improve the performance of related tasks by sharing knowledge. However, most existing MTL networks run on a single end and are not suitable for collaborative intelligence (CI) scenarios. In this work, we propose an MTL network with a deep joint source-channel coding (JSCC) framework, which allows operating under CI scenarios. We first propose a feature fusion based MTL network (FFMNet) for joint object detection and semantic segmentation. Compared with other MTL networks, FFMNet gets higher performance with fewer parameters. Then FFMNet is split","authors_text":"Jiahui Li, Mengyang Wang, Mengyao Ma, Xiaopeng Fan, Zhicong Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T08:58:02Z","title":"Deep Joint Source-Channel Coding for Multi-Task Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05779","kind":"arxiv","version":2},"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":"sha256:31a9b85ff1a7c1ce09b9f4d4b4d74545424811b77aed113e95127aaa1e716cb2","target":"record","created_at":"2026-07-05T03:28:25Z","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":"eb0e9a67bc25501e28e72e37d6adc070b17f5eff8545385295a515836171693e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T08:58:02Z","title_canon_sha256":"c4d29770343721e9faccd86203eac0202c742ffef2f1de7907ad6428aaf95a95"},"schema_version":"1.0","source":{"id":"2109.05779","kind":"arxiv","version":2}},"canonical_sha256":"ef2bc63e310a5e8f8e215822b2feee05facd01c6b9a2496be32a08e72bf72625","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef2bc63e310a5e8f8e215822b2feee05facd01c6b9a2496be32a08e72bf72625","first_computed_at":"2026-07-05T03:28:25.378063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:28:25.378063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ltxiddX2TVMdsVbSiNxkUN6V7pIESMN+QRvNVnzST3PJeFGhlxm4q+GiMUpz6euZBArPJ+n8zryeYkEzYP5NBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:28:25.378475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.05779","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31a9b85ff1a7c1ce09b9f4d4b4d74545424811b77aed113e95127aaa1e716cb2","sha256:294732f95a1808a4d1cdd3b21032bfa54512e6021df54f0bf17a3fb4456d9cb2"],"state_sha256":"c3862d2dfd11461d9d7dd141fae7b2ca89d3f36b2b5bf31b38e918b16d7f24a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RBsYYxpebGKLJN79o3WR2H/9i/+2b46DYW4yh/cDipngSoU96OQ1KPeLoDcKk356mIPoZYHVWac6Wnu/oFRoBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T14:14:55.573439Z","bundle_sha256":"3bc0acf2630cdf066ba4ea2e4f7e56de3a66838399e6676ff252b62a8e183f40"}}