{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:6KMBPTECNNUWIGATTBV4QJ7PQP","short_pith_number":"pith:6KMBPTEC","schema_version":"1.0","canonical_sha256":"f29817cc826b69641813986bc827ef83c1c4ff748645bddeaebe3e3a69713e51","source":{"kind":"arxiv","id":"1511.06391","version":4},"attestation_state":"computed","paper":{"title":"Order Matters: Sequence to sequence for sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Manjunath Kudlur, Oriol Vinyals, Samy Bengio","submitted_at":"2015-11-19T21:31:26Z","abstract_excerpt":"Sequences have become first class citizens in supervised learning thanks to the resurgence of recurrent neural networks. Many complex tasks that require mapping from or to a sequence of observations can now be formulated with the sequence-to-sequence (seq2seq) framework which employs the chain rule to efficiently represent the joint probability of sequences. In many cases, however, variable sized inputs and/or outputs might not be naturally expressed as sequences. For instance, it is not clear how to input a set of numbers into a model where the task is to sort them; similarly, we do not know "},"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":"1511.06391","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-11-19T21:31:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"f8c75e63daeafe3a45aa994e1f02aed350af7c7c33c9eb13cbce95eb7a9ca997","abstract_canon_sha256":"9735bdbeabadfcb33a06e5808853803e663df26cd0306bcb0ce7236e4a174690"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:06.357570Z","signature_b64":"bzKK3pAhnJ8gh6YhbGRcgPlRqHRNkdJCU7d8yCJFIhDXsm5eARiJkmFacBgMNWkNo5mT7syxs45S6KG8pTkqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f29817cc826b69641813986bc827ef83c1c4ff748645bddeaebe3e3a69713e51","last_reissued_at":"2026-05-18T01:20:06.356931Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:06.356931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Order Matters: Sequence to sequence for sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Manjunath Kudlur, Oriol Vinyals, Samy Bengio","submitted_at":"2015-11-19T21:31:26Z","abstract_excerpt":"Sequences have become first class citizens in supervised learning thanks to the resurgence of recurrent neural networks. Many complex tasks that require mapping from or to a sequence of observations can now be formulated with the sequence-to-sequence (seq2seq) framework which employs the chain rule to efficiently represent the joint probability of sequences. In many cases, however, variable sized inputs and/or outputs might not be naturally expressed as sequences. For instance, it is not clear how to input a set of numbers into a model where the task is to sort them; similarly, we do not know "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06391","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":"1511.06391","created_at":"2026-05-18T01:20:06.357044+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06391v4","created_at":"2026-05-18T01:20:06.357044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06391","created_at":"2026-05-18T01:20:06.357044+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KMBPTECNNUW","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KMBPTECNNUWIGAT","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KMBPTEC","created_at":"2026-05-18T12:29:07.941421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2210.15304","citing_title":"Explaining the Explainers in Graph Neural Networks: a Comparative Study","ref_index":106,"is_internal_anchor":true},{"citing_arxiv_id":"2406.11452","citing_title":"Attention-Based Deep Reinforcement Learning for Qubit Allocation in Modular Quantum Architectures","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2410.19541","citing_title":"The product structure of MPS-under-permutations","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2505.04018","citing_title":"Modal Decomposition and Identification for a Population of Structures Using Physics-Informed Graph Neural Networks and Transformers","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2601.01123","citing_title":"Learning from Historical Activations in Graph Neural Networks","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04087","citing_title":"ArrowFlow: Hierarchical Machine Learning in the Space of Permutations","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"1603.08983","citing_title":"Adaptive Computation Time for Recurrent Neural Networks","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"1605.08803","citing_title":"Density estimation using Real NVP","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":279,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08037","citing_title":"Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14613","citing_title":"Uncertainty-aware Generative Learning Path Recommendation with Cognition-Adaptive Diffusion","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KMBPTECNNUWIGATTBV4QJ7PQP","json":"https://pith.science/pith/6KMBPTECNNUWIGATTBV4QJ7PQP.json","graph_json":"https://pith.science/api/pith-number/6KMBPTECNNUWIGATTBV4QJ7PQP/graph.json","events_json":"https://pith.science/api/pith-number/6KMBPTECNNUWIGATTBV4QJ7PQP/events.json","paper":"https://pith.science/paper/6KMBPTEC"},"agent_actions":{"view_html":"https://pith.science/pith/6KMBPTECNNUWIGATTBV4QJ7PQP","download_json":"https://pith.science/pith/6KMBPTECNNUWIGATTBV4QJ7PQP.json","view_paper":"https://pith.science/paper/6KMBPTEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06391&json=true","fetch_graph":"https://pith.science/api/pith-number/6KMBPTECNNUWIGATTBV4QJ7PQP/graph.json","fetch_events":"https://pith.science/api/pith-number/6KMBPTECNNUWIGATTBV4QJ7PQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KMBPTECNNUWIGATTBV4QJ7PQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KMBPTECNNUWIGATTBV4QJ7PQP/action/storage_attestation","attest_author":"https://pith.science/pith/6KMBPTECNNUWIGATTBV4QJ7PQP/action/author_attestation","sign_citation":"https://pith.science/pith/6KMBPTECNNUWIGATTBV4QJ7PQP/action/citation_signature","submit_replication":"https://pith.science/pith/6KMBPTECNNUWIGATTBV4QJ7PQP/action/replication_record"}},"created_at":"2026-05-18T01:20:06.357044+00:00","updated_at":"2026-05-18T01:20:06.357044+00:00"}