{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4W5Q324PYZ5SKP6QAWGEZKDPW2","short_pith_number":"pith:4W5Q324P","canonical_record":{"source":{"id":"1810.04038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-07T21:24:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"aede95fa5eec9fc4280aead34d450aa964d70b60f8ff8caeaeb79ab4de01977f","abstract_canon_sha256":"cfe0c80269dfdd0ac98efe901a63a1fc82de8826542da4b84d2b3f4f44603848"},"schema_version":"1.0"},"canonical_sha256":"e5bb0deb8fc67b253fd0058c4ca86fb6a678a74c8b983439c6cc8f290c1a6289","source":{"kind":"arxiv","id":"1810.04038","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04038","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04038v1","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04038","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"4W5Q324PYZ5S","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4W5Q324PYZ5SKP6Q","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4W5Q324P","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4W5Q324PYZ5SKP6QAWGEZKDPW2","target":"record","payload":{"canonical_record":{"source":{"id":"1810.04038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-07T21:24:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"aede95fa5eec9fc4280aead34d450aa964d70b60f8ff8caeaeb79ab4de01977f","abstract_canon_sha256":"cfe0c80269dfdd0ac98efe901a63a1fc82de8826542da4b84d2b3f4f44603848"},"schema_version":"1.0"},"canonical_sha256":"e5bb0deb8fc67b253fd0058c4ca86fb6a678a74c8b983439c6cc8f290c1a6289","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:44.025146Z","signature_b64":"2oNogSsAoyLDCAdeKvFIFjSL3qUD02t61DELdphpa70VZQSPtodJwWbvvQ51rWloedH39yZEQU4dYny476H0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5bb0deb8fc67b253fd0058c4ca86fb6a678a74c8b983439c6cc8f290c1a6289","last_reissued_at":"2026-05-18T00:03:44.024703Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:44.024703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.04038","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":"2026-05-18T00:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C9TllNiSA0MBeYqrG3+bV1TPn7AMX8uosg4GCjdboyDc2/2pLVxgPWRE44wcYKF6eQo7dQLPz3mZIPnB130DCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T11:12:53.285376Z"},"content_sha256":"0351c42a481cca1e038569659cb552ddfd8338e058c9b4a12be21ce4c34a794f","schema_version":"1.0","event_id":"sha256:0351c42a481cca1e038569659cb552ddfd8338e058c9b4a12be21ce4c34a794f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4W5Q324PYZ5SKP6QAWGEZKDPW2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoxiang Gao, Helge Langseth, Ian Lane, Ming Zeng, Ole J. Mengshoel, Tong Yu, Xiaobing Liu","submitted_at":"2018-10-07T21:24:19Z","abstract_excerpt":"Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant sensor modalities, etc.). Besides, it is difficult to interpret the recurrent networks to gain insight into the models' behavior. To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention. These two mechanisms adaptively focus on important signals and sensor modalities. To furt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04038","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":"2026-05-18T00:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GQmTt6v2oDqnhgyvDG8PnSNUIYI/pTWuRl5TkiKWP3YNvUIr9SacKiBxaMq0Uil3GKuaDMO/c8CLcdgyzASfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T11:12:53.285705Z"},"content_sha256":"8cbd0d9a5810a4ce9533891f729b3c08e714be8364603c013046b8613bf92c50","schema_version":"1.0","event_id":"sha256:8cbd0d9a5810a4ce9533891f729b3c08e714be8364603c013046b8613bf92c50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4W5Q324PYZ5SKP6QAWGEZKDPW2/bundle.json","state_url":"https://pith.science/pith/4W5Q324PYZ5SKP6QAWGEZKDPW2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4W5Q324PYZ5SKP6QAWGEZKDPW2/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":"2026-06-09T11:12:53Z","links":{"resolver":"https://pith.science/pith/4W5Q324PYZ5SKP6QAWGEZKDPW2","bundle":"https://pith.science/pith/4W5Q324PYZ5SKP6QAWGEZKDPW2/bundle.json","state":"https://pith.science/pith/4W5Q324PYZ5SKP6QAWGEZKDPW2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4W5Q324PYZ5SKP6QAWGEZKDPW2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4W5Q324PYZ5SKP6QAWGEZKDPW2","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":"cfe0c80269dfdd0ac98efe901a63a1fc82de8826542da4b84d2b3f4f44603848","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-07T21:24:19Z","title_canon_sha256":"aede95fa5eec9fc4280aead34d450aa964d70b60f8ff8caeaeb79ab4de01977f"},"schema_version":"1.0","source":{"id":"1810.04038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04038","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04038v1","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04038","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"4W5Q324PYZ5S","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4W5Q324PYZ5SKP6Q","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4W5Q324P","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:8cbd0d9a5810a4ce9533891f729b3c08e714be8364603c013046b8613bf92c50","target":"graph","created_at":"2026-05-18T00:03:44Z","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":"Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant sensor modalities, etc.). Besides, it is difficult to interpret the recurrent networks to gain insight into the models' behavior. To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention. These two mechanisms adaptively focus on important signals and sensor modalities. To furt","authors_text":"Haoxiang Gao, Helge Langseth, Ian Lane, Ming Zeng, Ole J. Mengshoel, Tong Yu, Xiaobing Liu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-07T21:24:19Z","title":"Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04038","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":"sha256:0351c42a481cca1e038569659cb552ddfd8338e058c9b4a12be21ce4c34a794f","target":"record","created_at":"2026-05-18T00:03:44Z","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":"cfe0c80269dfdd0ac98efe901a63a1fc82de8826542da4b84d2b3f4f44603848","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-07T21:24:19Z","title_canon_sha256":"aede95fa5eec9fc4280aead34d450aa964d70b60f8ff8caeaeb79ab4de01977f"},"schema_version":"1.0","source":{"id":"1810.04038","kind":"arxiv","version":1}},"canonical_sha256":"e5bb0deb8fc67b253fd0058c4ca86fb6a678a74c8b983439c6cc8f290c1a6289","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5bb0deb8fc67b253fd0058c4ca86fb6a678a74c8b983439c6cc8f290c1a6289","first_computed_at":"2026-05-18T00:03:44.024703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:44.024703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2oNogSsAoyLDCAdeKvFIFjSL3qUD02t61DELdphpa70VZQSPtodJwWbvvQ51rWloedH39yZEQU4dYny476H0DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:44.025146Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.04038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0351c42a481cca1e038569659cb552ddfd8338e058c9b4a12be21ce4c34a794f","sha256:8cbd0d9a5810a4ce9533891f729b3c08e714be8364603c013046b8613bf92c50"],"state_sha256":"73fef985c35e9b5d8ab8cf8b6204ed258ce967cd73fb6d1fa053b26726f3ec4c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E7MqcowxW45EE3KoaOno6wBloBLAEXX4RbU4+J3XhqijL5U9mnlXsyYzDaT7yF5Hf2417kJda8X1/RT26OztBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T11:12:53.287415Z","bundle_sha256":"1b4f534eebca0c49dbb1d043a62b6de8cd2ff0246347e14b56012f82f1006321"}}