{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AHB4ES2UMFL7IRIW23AK5JMPEF","short_pith_number":"pith:AHB4ES2U","schema_version":"1.0","canonical_sha256":"01c3c24b546157f44516d6c0aea58f2144213f5c705a72d9e6c1bc748a0c70b7","source":{"kind":"arxiv","id":"2007.12298","version":1},"attestation_state":"computed","paper":{"title":"Evaluation metrics for behaviour modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Jiwoong Im, Iljung Kwak, Kristin Branson","submitted_at":"2020-07-23T23:47:24Z","abstract_excerpt":"A primary difficulty with unsupervised discovery of structure in large data sets is a lack of quantitative evaluation criteria. In this work, we propose and investigate several metrics for evaluating and comparing generative models of behavior learned using imitation learning. Compared to the commonly-used model log-likelihood, these criteria look at longer temporal relationships in behavior, are relevant if behavior has some properties that are inherently unpredictable, and highlight biases in the overall distribution of behaviors produced by the model. Pointwise metrics compare real to model"},"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":"2007.12298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-23T23:47:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9dc3fac675d9105e4f1f4c984dc659d8e551a81d6538d6e446afdac8cf043501","abstract_canon_sha256":"a3cd6a5733fa2f5bb8852f1025d8b431d2f0d8f622d323bc704704bab152270c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:51.026087Z","signature_b64":"aOhD11bVqfapfa6JUdrVeYFFWSYIYvVdjLzzpL509g1VNlRXawGsrG447igJrU25d88A36Jmshh6NHbmO9f9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01c3c24b546157f44516d6c0aea58f2144213f5c705a72d9e6c1bc748a0c70b7","last_reissued_at":"2026-07-05T01:21:51.025731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:51.025731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation metrics for behaviour modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Jiwoong Im, Iljung Kwak, Kristin Branson","submitted_at":"2020-07-23T23:47:24Z","abstract_excerpt":"A primary difficulty with unsupervised discovery of structure in large data sets is a lack of quantitative evaluation criteria. In this work, we propose and investigate several metrics for evaluating and comparing generative models of behavior learned using imitation learning. Compared to the commonly-used model log-likelihood, these criteria look at longer temporal relationships in behavior, are relevant if behavior has some properties that are inherently unpredictable, and highlight biases in the overall distribution of behaviors produced by the model. Pointwise metrics compare real to model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12298","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/2007.12298/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":"2007.12298","created_at":"2026-07-05T01:21:51.025785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.12298v1","created_at":"2026-07-05T01:21:51.025785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12298","created_at":"2026-07-05T01:21:51.025785+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHB4ES2UMFL7","created_at":"2026-07-05T01:21:51.025785+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHB4ES2UMFL7IRIW","created_at":"2026-07-05T01:21:51.025785+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHB4ES2U","created_at":"2026-07-05T01:21:51.025785+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/AHB4ES2UMFL7IRIW23AK5JMPEF","json":"https://pith.science/pith/AHB4ES2UMFL7IRIW23AK5JMPEF.json","graph_json":"https://pith.science/api/pith-number/AHB4ES2UMFL7IRIW23AK5JMPEF/graph.json","events_json":"https://pith.science/api/pith-number/AHB4ES2UMFL7IRIW23AK5JMPEF/events.json","paper":"https://pith.science/paper/AHB4ES2U"},"agent_actions":{"view_html":"https://pith.science/pith/AHB4ES2UMFL7IRIW23AK5JMPEF","download_json":"https://pith.science/pith/AHB4ES2UMFL7IRIW23AK5JMPEF.json","view_paper":"https://pith.science/paper/AHB4ES2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.12298&json=true","fetch_graph":"https://pith.science/api/pith-number/AHB4ES2UMFL7IRIW23AK5JMPEF/graph.json","fetch_events":"https://pith.science/api/pith-number/AHB4ES2UMFL7IRIW23AK5JMPEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHB4ES2UMFL7IRIW23AK5JMPEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHB4ES2UMFL7IRIW23AK5JMPEF/action/storage_attestation","attest_author":"https://pith.science/pith/AHB4ES2UMFL7IRIW23AK5JMPEF/action/author_attestation","sign_citation":"https://pith.science/pith/AHB4ES2UMFL7IRIW23AK5JMPEF/action/citation_signature","submit_replication":"https://pith.science/pith/AHB4ES2UMFL7IRIW23AK5JMPEF/action/replication_record"}},"created_at":"2026-07-05T01:21:51.025785+00:00","updated_at":"2026-07-05T01:21:51.025785+00:00"}