{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VNYU7SF3Y6SOOVDPG2YZELWZDZ","short_pith_number":"pith:VNYU7SF3","schema_version":"1.0","canonical_sha256":"ab714fc8bbc7a4e7546f36b1922ed91e686731cd915540c25f963b168e588f34","source":{"kind":"arxiv","id":"1711.06778","version":3},"attestation_state":"computed","paper":{"title":"Excitation Backprop for RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Zunino, Donghyun Kim, Jianming Zhang, Sarah Adel Bargal, Stan Sclaroff, Vittorio Murino","submitted_at":"2017-11-18T00:22:17Z","abstract_excerpt":"Deep models are state-of-the-art for many vision tasks including video action recognition and video captioning. Models are trained to caption or classify activity in videos, but little is known about the evidence used to make such decisions. Grounding decisions made by deep networks has been studied in spatial visual content, giving more insight into model predictions for images. However, such studies are relatively lacking for models of spatiotemporal visual content - videos. In this work, we devise a formulation that simultaneously grounds evidence in space and time, in a single pass, using "},"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":"1711.06778","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-18T00:22:17Z","cross_cats_sorted":[],"title_canon_sha256":"054ad9f68094dbcb76dec5f58e853da94ef54105d9638eaf0d261a2a244ecd73","abstract_canon_sha256":"8056fea55af8464b9877e468c13ce779b021f6674abbe2850f3a94a7ac6300d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:45.914840Z","signature_b64":"DtQwhtaJDL+rq3+3fM6p18x5NGMjACF85p+HrZ97Wxxdqlu6W0e4O2Vl5nXkoZKqGbz4Q8MBFJ+G1T57EL2GDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab714fc8bbc7a4e7546f36b1922ed91e686731cd915540c25f963b168e588f34","last_reissued_at":"2026-05-18T00:21:45.914311Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:45.914311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Excitation Backprop for RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Zunino, Donghyun Kim, Jianming Zhang, Sarah Adel Bargal, Stan Sclaroff, Vittorio Murino","submitted_at":"2017-11-18T00:22:17Z","abstract_excerpt":"Deep models are state-of-the-art for many vision tasks including video action recognition and video captioning. Models are trained to caption or classify activity in videos, but little is known about the evidence used to make such decisions. Grounding decisions made by deep networks has been studied in spatial visual content, giving more insight into model predictions for images. However, such studies are relatively lacking for models of spatiotemporal visual content - videos. In this work, we devise a formulation that simultaneously grounds evidence in space and time, in a single pass, using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06778","kind":"arxiv","version":3},"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":"1711.06778","created_at":"2026-05-18T00:21:45.914408+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.06778v3","created_at":"2026-05-18T00:21:45.914408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06778","created_at":"2026-05-18T00:21:45.914408+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNYU7SF3Y6SO","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNYU7SF3Y6SOOVDP","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNYU7SF3","created_at":"2026-05-18T12:31:49.984773+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/VNYU7SF3Y6SOOVDPG2YZELWZDZ","json":"https://pith.science/pith/VNYU7SF3Y6SOOVDPG2YZELWZDZ.json","graph_json":"https://pith.science/api/pith-number/VNYU7SF3Y6SOOVDPG2YZELWZDZ/graph.json","events_json":"https://pith.science/api/pith-number/VNYU7SF3Y6SOOVDPG2YZELWZDZ/events.json","paper":"https://pith.science/paper/VNYU7SF3"},"agent_actions":{"view_html":"https://pith.science/pith/VNYU7SF3Y6SOOVDPG2YZELWZDZ","download_json":"https://pith.science/pith/VNYU7SF3Y6SOOVDPG2YZELWZDZ.json","view_paper":"https://pith.science/paper/VNYU7SF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.06778&json=true","fetch_graph":"https://pith.science/api/pith-number/VNYU7SF3Y6SOOVDPG2YZELWZDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VNYU7SF3Y6SOOVDPG2YZELWZDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNYU7SF3Y6SOOVDPG2YZELWZDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNYU7SF3Y6SOOVDPG2YZELWZDZ/action/storage_attestation","attest_author":"https://pith.science/pith/VNYU7SF3Y6SOOVDPG2YZELWZDZ/action/author_attestation","sign_citation":"https://pith.science/pith/VNYU7SF3Y6SOOVDPG2YZELWZDZ/action/citation_signature","submit_replication":"https://pith.science/pith/VNYU7SF3Y6SOOVDPG2YZELWZDZ/action/replication_record"}},"created_at":"2026-05-18T00:21:45.914408+00:00","updated_at":"2026-05-18T00:21:45.914408+00:00"}