{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3FZL4CBTGIJY5F7KIPFLEZ7V45","short_pith_number":"pith:3FZL4CBT","schema_version":"1.0","canonical_sha256":"d972be083332138e97ea43cab267f5e773dd725176f60e905bdf3f71c76c9a62","source":{"kind":"arxiv","id":"2104.06751","version":2},"attestation_state":"computed","paper":{"title":"Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Juanzi Li, Lei Hou, Xin Lv, Yichi Zhang, Yixin Cao, Zelin Dai, Zhiyuan Liu","submitted_at":"2021-04-14T10:12:05Z","abstract_excerpt":"Multi-hop reasoning has been widely studied in recent years to obtain more interpretable link prediction. However, we find in experiments that many paths given by these models are actually unreasonable, while little works have been done on interpretability evaluation for them. In this paper, we propose a unified framework to quantitatively evaluate the interpretability of multi-hop reasoning models so as to advance their development. In specific, we define three metrics including path recall, local interpretability, and global interpretability for evaluation, and design an approximate strategy"},"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":"2104.06751","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2021-04-14T10:12:05Z","cross_cats_sorted":[],"title_canon_sha256":"16e40e50e500147beabdddbf2c5f3ca2f0b821e1e8cd87b263a0af4ebc379cb1","abstract_canon_sha256":"a9e151220853cf19e8aa082655b846e03d425e978ad5a60d1905e04ca8fe2c52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:48.078086Z","signature_b64":"No1PftZ+7d7l0I2PjmbZsGPgo0LQB1HL7cYBQaw7p9U+i3AIFwImHp1cdXKnPixKWFXAzTcXM2HhleU0vkgPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d972be083332138e97ea43cab267f5e773dd725176f60e905bdf3f71c76c9a62","last_reissued_at":"2026-07-05T03:12:48.077639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:48.077639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Juanzi Li, Lei Hou, Xin Lv, Yichi Zhang, Yixin Cao, Zelin Dai, Zhiyuan Liu","submitted_at":"2021-04-14T10:12:05Z","abstract_excerpt":"Multi-hop reasoning has been widely studied in recent years to obtain more interpretable link prediction. However, we find in experiments that many paths given by these models are actually unreasonable, while little works have been done on interpretability evaluation for them. In this paper, we propose a unified framework to quantitatively evaluate the interpretability of multi-hop reasoning models so as to advance their development. In specific, we define three metrics including path recall, local interpretability, and global interpretability for evaluation, and design an approximate strategy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06751","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/2104.06751/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2104.06751","created_at":"2026-07-05T03:12:48.077707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06751v2","created_at":"2026-07-05T03:12:48.077707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06751","created_at":"2026-07-05T03:12:48.077707+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FZL4CBTGIJY","created_at":"2026-07-05T03:12:48.077707+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FZL4CBTGIJY5F7K","created_at":"2026-07-05T03:12:48.077707+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FZL4CBT","created_at":"2026-07-05T03:12:48.077707+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/3FZL4CBTGIJY5F7KIPFLEZ7V45","json":"https://pith.science/pith/3FZL4CBTGIJY5F7KIPFLEZ7V45.json","graph_json":"https://pith.science/api/pith-number/3FZL4CBTGIJY5F7KIPFLEZ7V45/graph.json","events_json":"https://pith.science/api/pith-number/3FZL4CBTGIJY5F7KIPFLEZ7V45/events.json","paper":"https://pith.science/paper/3FZL4CBT"},"agent_actions":{"view_html":"https://pith.science/pith/3FZL4CBTGIJY5F7KIPFLEZ7V45","download_json":"https://pith.science/pith/3FZL4CBTGIJY5F7KIPFLEZ7V45.json","view_paper":"https://pith.science/paper/3FZL4CBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06751&json=true","fetch_graph":"https://pith.science/api/pith-number/3FZL4CBTGIJY5F7KIPFLEZ7V45/graph.json","fetch_events":"https://pith.science/api/pith-number/3FZL4CBTGIJY5F7KIPFLEZ7V45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FZL4CBTGIJY5F7KIPFLEZ7V45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FZL4CBTGIJY5F7KIPFLEZ7V45/action/storage_attestation","attest_author":"https://pith.science/pith/3FZL4CBTGIJY5F7KIPFLEZ7V45/action/author_attestation","sign_citation":"https://pith.science/pith/3FZL4CBTGIJY5F7KIPFLEZ7V45/action/citation_signature","submit_replication":"https://pith.science/pith/3FZL4CBTGIJY5F7KIPFLEZ7V45/action/replication_record"}},"created_at":"2026-07-05T03:12:48.077707+00:00","updated_at":"2026-07-05T03:12:48.077707+00:00"}