{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6FNBEXZBXRJ4AS2J4MQB6HH6US","short_pith_number":"pith:6FNBEXZB","canonical_record":{"source":{"id":"1709.09118","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-26T16:32:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e6521b76e6d0043e8933952e26f62d9921374d47e646d0b389db7febd05a38c6","abstract_canon_sha256":"fe71c9aac04e779f4c4831751b2ac73d6c6ee7ec78b09ab919939435a24e1271"},"schema_version":"1.0"},"canonical_sha256":"f15a125f21bc53c04b49e3201f1cfea4862786d833ae14b740e737ca8a5580f7","source":{"kind":"arxiv","id":"1709.09118","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.09118","created_at":"2026-05-18T00:27:52Z"},{"alias_kind":"arxiv_version","alias_value":"1709.09118v5","created_at":"2026-05-18T00:27:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.09118","created_at":"2026-05-18T00:27:52Z"},{"alias_kind":"pith_short_12","alias_value":"6FNBEXZBXRJ4","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6FNBEXZBXRJ4AS2J","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6FNBEXZB","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6FNBEXZBXRJ4AS2J4MQB6HH6US","target":"record","payload":{"canonical_record":{"source":{"id":"1709.09118","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-26T16:32:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e6521b76e6d0043e8933952e26f62d9921374d47e646d0b389db7febd05a38c6","abstract_canon_sha256":"fe71c9aac04e779f4c4831751b2ac73d6c6ee7ec78b09ab919939435a24e1271"},"schema_version":"1.0"},"canonical_sha256":"f15a125f21bc53c04b49e3201f1cfea4862786d833ae14b740e737ca8a5580f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:52.145434Z","signature_b64":"PueUN4Wsir9/ePuLf1IgoxqgJsbQNn5qDJxv3yV+Ltk/jIFhlDbVFN4V0azFHhi1fANPe4jN1kXxLpqiOFlVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f15a125f21bc53c04b49e3201f1cfea4862786d833ae14b740e737ca8a5580f7","last_reissued_at":"2026-05-18T00:27:52.144788Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:52.144788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.09118","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:27:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qXpMAwEshOjayN/CTeqXPYcDjTQ+2X6GWZMMdwn3IryooSZzTof5guRywMupM/RlO/vM1Nr2YK32Tk/dYHzBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:56:22.965432Z"},"content_sha256":"163f0f39710924405d0e7153612b9c9dbfa4618af2c866df1f96c0384622d342","schema_version":"1.0","event_id":"sha256:163f0f39710924405d0e7153612b9c9dbfa4618af2c866df1f96c0384622d342"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6FNBEXZBXRJ4AS2J4MQB6HH6US","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tensor Product Generation Networks for Deep NLP Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dapeng Wu, Li Deng, Paul Smolensky, Qiuyuan Huang, Xiaodong He","submitted_at":"2017-09-26T16:32:20Z","abstract_excerpt":"We present a new approach to the design of deep networks for natural language processing (NLP), based on the general technique of Tensor Product Representations (TPRs) for encoding and processing symbol structures in distributed neural networks. A network architecture --- the Tensor Product Generation Network (TPGN) --- is proposed which is capable in principle of carrying out TPR computation, but which uses unconstrained deep learning to design its internal representations. Instantiated in a model for image-caption generation, TPGN outperforms LSTM baselines when evaluated on the COCO dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.09118","kind":"arxiv","version":5},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:27:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+cQgLxg2C+lKtGLalqPuvZRgaLrc0oxvG/IQ+IoqdEtMLa8vRf4nm5Deslgir8wVx1Kp6mv5zB5D3/DdwWEsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:56:22.965785Z"},"content_sha256":"8320610ff7340381593a61396c6a157e1d9d5aa2c981baabff1cc6154e64027f","schema_version":"1.0","event_id":"sha256:8320610ff7340381593a61396c6a157e1d9d5aa2c981baabff1cc6154e64027f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6FNBEXZBXRJ4AS2J4MQB6HH6US/bundle.json","state_url":"https://pith.science/pith/6FNBEXZBXRJ4AS2J4MQB6HH6US/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6FNBEXZBXRJ4AS2J4MQB6HH6US/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T22:56:22Z","links":{"resolver":"https://pith.science/pith/6FNBEXZBXRJ4AS2J4MQB6HH6US","bundle":"https://pith.science/pith/6FNBEXZBXRJ4AS2J4MQB6HH6US/bundle.json","state":"https://pith.science/pith/6FNBEXZBXRJ4AS2J4MQB6HH6US/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6FNBEXZBXRJ4AS2J4MQB6HH6US/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6FNBEXZBXRJ4AS2J4MQB6HH6US","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fe71c9aac04e779f4c4831751b2ac73d6c6ee7ec78b09ab919939435a24e1271","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-26T16:32:20Z","title_canon_sha256":"e6521b76e6d0043e8933952e26f62d9921374d47e646d0b389db7febd05a38c6"},"schema_version":"1.0","source":{"id":"1709.09118","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.09118","created_at":"2026-05-18T00:27:52Z"},{"alias_kind":"arxiv_version","alias_value":"1709.09118v5","created_at":"2026-05-18T00:27:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.09118","created_at":"2026-05-18T00:27:52Z"},{"alias_kind":"pith_short_12","alias_value":"6FNBEXZBXRJ4","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6FNBEXZBXRJ4AS2J","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6FNBEXZB","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:8320610ff7340381593a61396c6a157e1d9d5aa2c981baabff1cc6154e64027f","target":"graph","created_at":"2026-05-18T00:27:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We present a new approach to the design of deep networks for natural language processing (NLP), based on the general technique of Tensor Product Representations (TPRs) for encoding and processing symbol structures in distributed neural networks. A network architecture --- the Tensor Product Generation Network (TPGN) --- is proposed which is capable in principle of carrying out TPR computation, but which uses unconstrained deep learning to design its internal representations. Instantiated in a model for image-caption generation, TPGN outperforms LSTM baselines when evaluated on the COCO dataset","authors_text":"Dapeng Wu, Li Deng, Paul Smolensky, Qiuyuan Huang, Xiaodong He","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-26T16:32:20Z","title":"Tensor Product Generation Networks for Deep NLP Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.09118","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:163f0f39710924405d0e7153612b9c9dbfa4618af2c866df1f96c0384622d342","target":"record","created_at":"2026-05-18T00:27:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fe71c9aac04e779f4c4831751b2ac73d6c6ee7ec78b09ab919939435a24e1271","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-26T16:32:20Z","title_canon_sha256":"e6521b76e6d0043e8933952e26f62d9921374d47e646d0b389db7febd05a38c6"},"schema_version":"1.0","source":{"id":"1709.09118","kind":"arxiv","version":5}},"canonical_sha256":"f15a125f21bc53c04b49e3201f1cfea4862786d833ae14b740e737ca8a5580f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f15a125f21bc53c04b49e3201f1cfea4862786d833ae14b740e737ca8a5580f7","first_computed_at":"2026-05-18T00:27:52.144788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:52.144788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PueUN4Wsir9/ePuLf1IgoxqgJsbQNn5qDJxv3yV+Ltk/jIFhlDbVFN4V0azFHhi1fANPe4jN1kXxLpqiOFlVDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:52.145434Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.09118","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:163f0f39710924405d0e7153612b9c9dbfa4618af2c866df1f96c0384622d342","sha256:8320610ff7340381593a61396c6a157e1d9d5aa2c981baabff1cc6154e64027f"],"state_sha256":"70b9702970bbf761d28c5f5cc81d84b8c38ca84181335430a9b436865f18c350"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N75NE6kWoSgdVai9umrvuV5tDgv4Vx4kv2Ui6gsBInfJ9tRyNehH3KE/JB576srlqZlf1eKAIuA8OwZI/DboCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:56:22.968209Z","bundle_sha256":"5a8a37f26b28710e4ccf9ef54ab23e0d72b70371757a6992dcdb40105564f480"}}