{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QQNQTWPE4TK65LWNX4RDIJC73G","short_pith_number":"pith:QQNQTWPE","schema_version":"1.0","canonical_sha256":"841b09d9e4e4d5eeaecdbf2234245fd9ae9e7a72920474b14b5a3d3f29656dc6","source":{"kind":"arxiv","id":"1705.07136","version":3},"attestation_state":"computed","paper":{"title":"Softmax Q-Distribution Estimation for Structured Prediction: A Theoretical Interpretation for RAML","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eduard Hovy, Graham Neubig, Jingzhou Liu, Pengcheng Yin, Xuezhe Ma","submitted_at":"2017-05-19T18:17:00Z","abstract_excerpt":"Reward augmented maximum likelihood (RAML), a simple and effective learning framework to directly optimize towards the reward function in structured prediction tasks, has led to a number of impressive empirical successes. RAML incorporates task-specific reward by performing maximum-likelihood updates on candidate outputs sampled according to an exponentiated payoff distribution, which gives higher probabilities to candidates that are close to the reference output. While RAML is notable for its simplicity, efficiency, and its impressive empirical successes, the theoretical properties of RAML, e"},"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":"1705.07136","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-19T18:17:00Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"5c23684559a23ffefd665fcc75be0ee15e4c5d4d08325d7cb45d625bbc64ce82","abstract_canon_sha256":"779494d114939c8f5a0f7e4610a5ba375e39905390036e0e9f09516004d7ffe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:51.102121Z","signature_b64":"GLtNlzX3KN40/qk1QyFjFYkdcHqXoPyrXHaKAqOvTQbOZfG1BUVhgG6M7Dhh0NdzJQXQhqksNShi4hn4CdtDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"841b09d9e4e4d5eeaecdbf2234245fd9ae9e7a72920474b14b5a3d3f29656dc6","last_reissued_at":"2026-05-18T00:31:51.101525Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:51.101525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Softmax Q-Distribution Estimation for Structured Prediction: A Theoretical Interpretation for RAML","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eduard Hovy, Graham Neubig, Jingzhou Liu, Pengcheng Yin, Xuezhe Ma","submitted_at":"2017-05-19T18:17:00Z","abstract_excerpt":"Reward augmented maximum likelihood (RAML), a simple and effective learning framework to directly optimize towards the reward function in structured prediction tasks, has led to a number of impressive empirical successes. RAML incorporates task-specific reward by performing maximum-likelihood updates on candidate outputs sampled according to an exponentiated payoff distribution, which gives higher probabilities to candidates that are close to the reference output. While RAML is notable for its simplicity, efficiency, and its impressive empirical successes, the theoretical properties of RAML, e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07136","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":"1705.07136","created_at":"2026-05-18T00:31:51.101623+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07136v3","created_at":"2026-05-18T00:31:51.101623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07136","created_at":"2026-05-18T00:31:51.101623+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQNQTWPE4TK6","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQNQTWPE4TK65LWN","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQNQTWPE","created_at":"2026-05-18T12:31:39.905425+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/QQNQTWPE4TK65LWNX4RDIJC73G","json":"https://pith.science/pith/QQNQTWPE4TK65LWNX4RDIJC73G.json","graph_json":"https://pith.science/api/pith-number/QQNQTWPE4TK65LWNX4RDIJC73G/graph.json","events_json":"https://pith.science/api/pith-number/QQNQTWPE4TK65LWNX4RDIJC73G/events.json","paper":"https://pith.science/paper/QQNQTWPE"},"agent_actions":{"view_html":"https://pith.science/pith/QQNQTWPE4TK65LWNX4RDIJC73G","download_json":"https://pith.science/pith/QQNQTWPE4TK65LWNX4RDIJC73G.json","view_paper":"https://pith.science/paper/QQNQTWPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07136&json=true","fetch_graph":"https://pith.science/api/pith-number/QQNQTWPE4TK65LWNX4RDIJC73G/graph.json","fetch_events":"https://pith.science/api/pith-number/QQNQTWPE4TK65LWNX4RDIJC73G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQNQTWPE4TK65LWNX4RDIJC73G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQNQTWPE4TK65LWNX4RDIJC73G/action/storage_attestation","attest_author":"https://pith.science/pith/QQNQTWPE4TK65LWNX4RDIJC73G/action/author_attestation","sign_citation":"https://pith.science/pith/QQNQTWPE4TK65LWNX4RDIJC73G/action/citation_signature","submit_replication":"https://pith.science/pith/QQNQTWPE4TK65LWNX4RDIJC73G/action/replication_record"}},"created_at":"2026-05-18T00:31:51.101623+00:00","updated_at":"2026-05-18T00:31:51.101623+00:00"}