{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S2OHMORZCE7TNMLZSP3IWV67G7","short_pith_number":"pith:S2OHMORZ","schema_version":"1.0","canonical_sha256":"969c763a39113f36b17993f68b57df37c70478b8baa26965de886465037d2393","source":{"kind":"arxiv","id":"2406.17098","version":2},"attestation_state":"computed","paper":{"title":"Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anca Dragan, Benjamin Eysenbach, Chongyi Zheng, Sergey Levine, Vivek Myers","submitted_at":"2024-06-24T19:36:45Z","abstract_excerpt":"Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such temporal distances in stochastic settings have been stymied by an important limitation: these prior approaches do not satisfy the triangle inequality. This is not merely a definitional concern, but translates to an inability to generalize and find shortest paths. In this paper, we build on prior work in contrastive learning and quasimetrics to show how successor "},"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":"2406.17098","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T19:36:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34e2a84613a06dcefc93597f4277e56daf517a94628f45e913e156c5d680876d","abstract_canon_sha256":"186aa0ce6df6940f212d605b992632f7387e961a47bc15b989626e23520bbeb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:11.701918Z","signature_b64":"P+RiqqLbkTEp4w3LCF6UhbIpHyGE7mgR8G53wuIbBRcERab1RrW4YPVpnHhetrxG0Ms7KBFe/ZHlAunQXmWFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"969c763a39113f36b17993f68b57df37c70478b8baa26965de886465037d2393","last_reissued_at":"2026-07-05T10:27:11.700866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:11.700866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anca Dragan, Benjamin Eysenbach, Chongyi Zheng, Sergey Levine, Vivek Myers","submitted_at":"2024-06-24T19:36:45Z","abstract_excerpt":"Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such temporal distances in stochastic settings have been stymied by an important limitation: these prior approaches do not satisfy the triangle inequality. This is not merely a definitional concern, but translates to an inability to generalize and find shortest paths. In this paper, we build on prior work in contrastive learning and quasimetrics to show how successor "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17098","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/2406.17098/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":"2406.17098","created_at":"2026-07-05T10:27:11.701026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17098v2","created_at":"2026-07-05T10:27:11.701026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17098","created_at":"2026-07-05T10:27:11.701026+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2OHMORZCE7T","created_at":"2026-07-05T10:27:11.701026+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2OHMORZCE7TNMLZ","created_at":"2026-07-05T10:27:11.701026+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2OHMORZ","created_at":"2026-07-05T10:27:11.701026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04188","citing_title":"Dual Advantage Fields","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08960","citing_title":"Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01865","citing_title":"Quality-Aware Exploration Budget Allocation for Cooperative Multi-Agent Reinforcement Learning","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2OHMORZCE7TNMLZSP3IWV67G7","json":"https://pith.science/pith/S2OHMORZCE7TNMLZSP3IWV67G7.json","graph_json":"https://pith.science/api/pith-number/S2OHMORZCE7TNMLZSP3IWV67G7/graph.json","events_json":"https://pith.science/api/pith-number/S2OHMORZCE7TNMLZSP3IWV67G7/events.json","paper":"https://pith.science/paper/S2OHMORZ"},"agent_actions":{"view_html":"https://pith.science/pith/S2OHMORZCE7TNMLZSP3IWV67G7","download_json":"https://pith.science/pith/S2OHMORZCE7TNMLZSP3IWV67G7.json","view_paper":"https://pith.science/paper/S2OHMORZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17098&json=true","fetch_graph":"https://pith.science/api/pith-number/S2OHMORZCE7TNMLZSP3IWV67G7/graph.json","fetch_events":"https://pith.science/api/pith-number/S2OHMORZCE7TNMLZSP3IWV67G7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2OHMORZCE7TNMLZSP3IWV67G7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2OHMORZCE7TNMLZSP3IWV67G7/action/storage_attestation","attest_author":"https://pith.science/pith/S2OHMORZCE7TNMLZSP3IWV67G7/action/author_attestation","sign_citation":"https://pith.science/pith/S2OHMORZCE7TNMLZSP3IWV67G7/action/citation_signature","submit_replication":"https://pith.science/pith/S2OHMORZCE7TNMLZSP3IWV67G7/action/replication_record"}},"created_at":"2026-07-05T10:27:11.701026+00:00","updated_at":"2026-07-05T10:27:11.701026+00:00"}