{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4N7WJ5UIPGWHWXAMVJSRDYUDYI","short_pith_number":"pith:4N7WJ5UI","schema_version":"1.0","canonical_sha256":"e37f64f68879ac7b5c0caa6511e283c2194bcb6defdd7f49360d58bb5d67ad84","source":{"kind":"arxiv","id":"1704.00805","version":4},"attestation_state":"computed","paper":{"title":"On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Bolin Gao, Lacra Pavel","submitted_at":"2017-04-03T20:50:29Z","abstract_excerpt":"In this paper, we utilize results from convex analysis and monotone operator theory to derive additional properties of the softmax function that have not yet been covered in the existing literature. In particular, we show that the softmax function is the monotone gradient map of the log-sum-exp function. By exploiting this connection, we show that the inverse temperature parameter determines the Lipschitz and co-coercivity properties of the softmax function. We then demonstrate the usefulness of these properties through an application in game-theoretic reinforcement learning."},"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":"1704.00805","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-04-03T20:50:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b40e7c852386e52b890fcec7242a5ea029861692af5c4527342b566461e07b88","abstract_canon_sha256":"ea8086eeba9ae4c0e59c64c5e84e7eb2f94387f26e1886ab87449e8851fa5381"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:33.212694Z","signature_b64":"DFXRY4Qvb+EUVSoIkyh6K4fjrdb21x+bf8dr7OTWqwah6EM2Oo0M3uc3wi7jLMz0NdBFLRsI5UknEsNsmp30Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e37f64f68879ac7b5c0caa6511e283c2194bcb6defdd7f49360d58bb5d67ad84","last_reissued_at":"2026-05-18T00:07:33.212109Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:33.212109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Bolin Gao, Lacra Pavel","submitted_at":"2017-04-03T20:50:29Z","abstract_excerpt":"In this paper, we utilize results from convex analysis and monotone operator theory to derive additional properties of the softmax function that have not yet been covered in the existing literature. In particular, we show that the softmax function is the monotone gradient map of the log-sum-exp function. By exploiting this connection, we show that the inverse temperature parameter determines the Lipschitz and co-coercivity properties of the softmax function. We then demonstrate the usefulness of these properties through an application in game-theoretic reinforcement learning."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00805","kind":"arxiv","version":4},"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":"1704.00805","created_at":"2026-05-18T00:07:33.212211+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.00805v4","created_at":"2026-05-18T00:07:33.212211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00805","created_at":"2026-05-18T00:07:33.212211+00:00"},{"alias_kind":"pith_short_12","alias_value":"4N7WJ5UIPGWH","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4N7WJ5UIPGWHWXAM","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4N7WJ5UI","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2512.04745","citing_title":"Neural Policy Composition from Free Energy Minimization","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17848","citing_title":"Learning Empirical Evidence Equilibria under Weak Environmental Coupling","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15651","citing_title":"Sharp Spectral Thresholds for Logit Fixed Points","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17848","citing_title":"Learning Empirical Evidence Equilibria under Weak Environmental Coupling","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16809","citing_title":"Informative Graph Structure Learning","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2505.19525","citing_title":"Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2510.16132","citing_title":"A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08689","citing_title":"Structure-Centric Graph Foundation Model via Geometric Bases","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09813","citing_title":"Optimizing Server Placement for Vertical Federated Learning in Dynamic Edge/Fog Networks","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20551","citing_title":"On Bayesian Softmax-Gated Mixture-of-Experts Models","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14381","citing_title":"Learning Cut Distributions with Quantum Optimization","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20276","citing_title":"Rethinking Intrinsic Dimension Estimation in Neural Representations","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4N7WJ5UIPGWHWXAMVJSRDYUDYI","json":"https://pith.science/pith/4N7WJ5UIPGWHWXAMVJSRDYUDYI.json","graph_json":"https://pith.science/api/pith-number/4N7WJ5UIPGWHWXAMVJSRDYUDYI/graph.json","events_json":"https://pith.science/api/pith-number/4N7WJ5UIPGWHWXAMVJSRDYUDYI/events.json","paper":"https://pith.science/paper/4N7WJ5UI"},"agent_actions":{"view_html":"https://pith.science/pith/4N7WJ5UIPGWHWXAMVJSRDYUDYI","download_json":"https://pith.science/pith/4N7WJ5UIPGWHWXAMVJSRDYUDYI.json","view_paper":"https://pith.science/paper/4N7WJ5UI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.00805&json=true","fetch_graph":"https://pith.science/api/pith-number/4N7WJ5UIPGWHWXAMVJSRDYUDYI/graph.json","fetch_events":"https://pith.science/api/pith-number/4N7WJ5UIPGWHWXAMVJSRDYUDYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4N7WJ5UIPGWHWXAMVJSRDYUDYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4N7WJ5UIPGWHWXAMVJSRDYUDYI/action/storage_attestation","attest_author":"https://pith.science/pith/4N7WJ5UIPGWHWXAMVJSRDYUDYI/action/author_attestation","sign_citation":"https://pith.science/pith/4N7WJ5UIPGWHWXAMVJSRDYUDYI/action/citation_signature","submit_replication":"https://pith.science/pith/4N7WJ5UIPGWHWXAMVJSRDYUDYI/action/replication_record"}},"created_at":"2026-05-18T00:07:33.212211+00:00","updated_at":"2026-05-18T00:07:33.212211+00:00"}