{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JJDWEGZNV2AZ5HRZYDVO2QLEEW","short_pith_number":"pith:JJDWEGZN","canonical_record":{"source":{"id":"2010.13924","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T22:07:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f0935ecb3715221c429412994e933db8715b05dc12862581bd5104b81f9977dc","abstract_canon_sha256":"f8799ccfa1ed673e501947bbf8845419bcb3c0fc7d5225984b06afa9dbaaff2c"},"schema_version":"1.0"},"canonical_sha256":"4a47621b2dae819e9e39c0eaed416425bd1db4681141e0929a5842873bd62121","source":{"kind":"arxiv","id":"2010.13924","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.13924","created_at":"2026-07-05T01:46:29Z"},{"alias_kind":"arxiv_version","alias_value":"2010.13924v1","created_at":"2026-07-05T01:46:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13924","created_at":"2026-07-05T01:46:29Z"},{"alias_kind":"pith_short_12","alias_value":"JJDWEGZNV2AZ","created_at":"2026-07-05T01:46:29Z"},{"alias_kind":"pith_short_16","alias_value":"JJDWEGZNV2AZ5HRZ","created_at":"2026-07-05T01:46:29Z"},{"alias_kind":"pith_short_8","alias_value":"JJDWEGZN","created_at":"2026-07-05T01:46:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JJDWEGZNV2AZ5HRZYDVO2QLEEW","target":"record","payload":{"canonical_record":{"source":{"id":"2010.13924","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T22:07:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f0935ecb3715221c429412994e933db8715b05dc12862581bd5104b81f9977dc","abstract_canon_sha256":"f8799ccfa1ed673e501947bbf8845419bcb3c0fc7d5225984b06afa9dbaaff2c"},"schema_version":"1.0"},"canonical_sha256":"4a47621b2dae819e9e39c0eaed416425bd1db4681141e0929a5842873bd62121","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:46:29.629582Z","signature_b64":"BrBNVwL6L9d/zWZIDWxx6eIAgM1ve0dKhEEMU7b+wVxc9XFrHMJaKLTkmooO8b33XWStVf/+X4cJFeNLoKAuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a47621b2dae819e9e39c0eaed416425bd1db4681141e0929a5842873bd62121","last_reissued_at":"2026-07-05T01:46:29.629210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:46:29.629210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.13924","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":"2026-07-05T01:46:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gXNfqxYl1NP/4Zes4vypX1DWrJKGN0U4W3gv85Z33iqRcY8rSBkztLbnUosknyFfHZNzwp2iAKf5eCNA+niqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:54:51.598552Z"},"content_sha256":"2202de63cf18f2eae3813682fe90af2a9ff2ade35acdb27f8e03d46ab2e96708","schema_version":"1.0","event_id":"sha256:2202de63cf18f2eae3813682fe90af2a9ff2ade35acdb27f8e03d46ab2e96708"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JJDWEGZNV2AZ5HRZYDVO2QLEEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Deep Learning Interpretability in Time Series Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aya Abdelsalam Ismail, H\\'ector Corrada Bravo, Mohamed Gunady, Soheil Feizi","submitted_at":"2020-10-26T22:07:53Z","abstract_excerpt":"Saliency methods are used extensively to highlight the importance of input features in model predictions. These methods are mostly used in vision and language tasks, and their applications to time series data is relatively unexplored. In this paper, we set out to extensively compare the performance of various saliency-based interpretability methods across diverse neural architectures, including Recurrent Neural Network, Temporal Convolutional Networks, and Transformers in a new benchmark of synthetic time series data. We propose and report multiple metrics to empirically evaluate the performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13924","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.13924/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":"2026-07-05T01:46:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I7v1ozMZJIDrQBhOAzhtiASmVyNKY104jEnpTeVlSMyj6L4bGFGqIuP3914epfPncCCfXJoY+kt84tugqGU7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:54:51.599089Z"},"content_sha256":"36af8cb6b8dd9b18b3851bbba99c629628c92ee1c21f683170be159be9b69eb7","schema_version":"1.0","event_id":"sha256:36af8cb6b8dd9b18b3851bbba99c629628c92ee1c21f683170be159be9b69eb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJDWEGZNV2AZ5HRZYDVO2QLEEW/bundle.json","state_url":"https://pith.science/pith/JJDWEGZNV2AZ5HRZYDVO2QLEEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJDWEGZNV2AZ5HRZYDVO2QLEEW/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":"2026-08-13T19:54:51Z","links":{"resolver":"https://pith.science/pith/JJDWEGZNV2AZ5HRZYDVO2QLEEW","bundle":"https://pith.science/pith/JJDWEGZNV2AZ5HRZYDVO2QLEEW/bundle.json","state":"https://pith.science/pith/JJDWEGZNV2AZ5HRZYDVO2QLEEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJDWEGZNV2AZ5HRZYDVO2QLEEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JJDWEGZNV2AZ5HRZYDVO2QLEEW","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":"f8799ccfa1ed673e501947bbf8845419bcb3c0fc7d5225984b06afa9dbaaff2c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T22:07:53Z","title_canon_sha256":"f0935ecb3715221c429412994e933db8715b05dc12862581bd5104b81f9977dc"},"schema_version":"1.0","source":{"id":"2010.13924","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.13924","created_at":"2026-07-05T01:46:29Z"},{"alias_kind":"arxiv_version","alias_value":"2010.13924v1","created_at":"2026-07-05T01:46:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13924","created_at":"2026-07-05T01:46:29Z"},{"alias_kind":"pith_short_12","alias_value":"JJDWEGZNV2AZ","created_at":"2026-07-05T01:46:29Z"},{"alias_kind":"pith_short_16","alias_value":"JJDWEGZNV2AZ5HRZ","created_at":"2026-07-05T01:46:29Z"},{"alias_kind":"pith_short_8","alias_value":"JJDWEGZN","created_at":"2026-07-05T01:46:29Z"}],"graph_snapshots":[{"event_id":"sha256:36af8cb6b8dd9b18b3851bbba99c629628c92ee1c21f683170be159be9b69eb7","target":"graph","created_at":"2026-07-05T01:46:29Z","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/2010.13924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Saliency methods are used extensively to highlight the importance of input features in model predictions. These methods are mostly used in vision and language tasks, and their applications to time series data is relatively unexplored. In this paper, we set out to extensively compare the performance of various saliency-based interpretability methods across diverse neural architectures, including Recurrent Neural Network, Temporal Convolutional Networks, and Transformers in a new benchmark of synthetic time series data. We propose and report multiple metrics to empirically evaluate the performan","authors_text":"Aya Abdelsalam Ismail, H\\'ector Corrada Bravo, Mohamed Gunady, Soheil Feizi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T22:07:53Z","title":"Benchmarking Deep Learning Interpretability in Time Series Predictions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13924","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":"sha256:2202de63cf18f2eae3813682fe90af2a9ff2ade35acdb27f8e03d46ab2e96708","target":"record","created_at":"2026-07-05T01:46:29Z","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":"f8799ccfa1ed673e501947bbf8845419bcb3c0fc7d5225984b06afa9dbaaff2c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T22:07:53Z","title_canon_sha256":"f0935ecb3715221c429412994e933db8715b05dc12862581bd5104b81f9977dc"},"schema_version":"1.0","source":{"id":"2010.13924","kind":"arxiv","version":1}},"canonical_sha256":"4a47621b2dae819e9e39c0eaed416425bd1db4681141e0929a5842873bd62121","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a47621b2dae819e9e39c0eaed416425bd1db4681141e0929a5842873bd62121","first_computed_at":"2026-07-05T01:46:29.629210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:46:29.629210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BrBNVwL6L9d/zWZIDWxx6eIAgM1ve0dKhEEMU7b+wVxc9XFrHMJaKLTkmooO8b33XWStVf/+X4cJFeNLoKAuDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:46:29.629582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.13924","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2202de63cf18f2eae3813682fe90af2a9ff2ade35acdb27f8e03d46ab2e96708","sha256:36af8cb6b8dd9b18b3851bbba99c629628c92ee1c21f683170be159be9b69eb7"],"state_sha256":"6529acd71d6c0354a75c3b44dfd9877c2ded85921d5072f3a8bc847bb570673e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ibuNlPzekXToNSeFdK0PXFkBE5lgseV2v0XH10PDlYg5Oz07niukZ6j3Gg09z8J7vfMShSqe5k4dVrToolCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T19:54:51.605494Z","bundle_sha256":"0d970dfa8dd6474b93e5dd498b3f78f547f76ea5e0b72b4b46201b044f131e3f"}}