{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:MDQ3Z2CTASLEMZ7VQBMKD53WJM","short_pith_number":"pith:MDQ3Z2CT","canonical_record":{"source":{"id":"1611.01587","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-05T01:59:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1cdb0e65aad8b43062a481bf160396e6b23bc868744de5e25efdc277f10f342b","abstract_canon_sha256":"7a16429af9e23e23a75514015dd262262e946a49f68a71eb99e7e445c3cf3baf"},"schema_version":"1.0"},"canonical_sha256":"60e1bce85304964667f58058a1f7764b32f894b68dd749320b8396dbf174c424","source":{"kind":"arxiv","id":"1611.01587","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01587","created_at":"2026-05-18T00:39:47Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01587v5","created_at":"2026-05-18T00:39:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01587","created_at":"2026-05-18T00:39:47Z"},{"alias_kind":"pith_short_12","alias_value":"MDQ3Z2CTASLE","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MDQ3Z2CTASLEMZ7V","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MDQ3Z2CT","created_at":"2026-05-18T12:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:MDQ3Z2CTASLEMZ7VQBMKD53WJM","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01587","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-05T01:59:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1cdb0e65aad8b43062a481bf160396e6b23bc868744de5e25efdc277f10f342b","abstract_canon_sha256":"7a16429af9e23e23a75514015dd262262e946a49f68a71eb99e7e445c3cf3baf"},"schema_version":"1.0"},"canonical_sha256":"60e1bce85304964667f58058a1f7764b32f894b68dd749320b8396dbf174c424","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:47.222396Z","signature_b64":"RA4P8F+0vN3hcxAGfr2b2LafSiDhTNlqyNWK2EXik9DYZ3HmH99NyncfQbiBgERS593wU/RIhjhEUcPVJGp/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60e1bce85304964667f58058a1f7764b32f894b68dd749320b8396dbf174c424","last_reissued_at":"2026-05-18T00:39:47.221668Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:47.221668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01587","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":"2026-05-18T00:39:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8jM+U9sfZTPI2vM6nXOHp3RyEr+fD9wyS+AzoPERRs8V99TwV66uRIpnvlEgJWcTGOa4lvdWXksJ35v9doPYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T12:21:17.540894Z"},"content_sha256":"0e1e4738ca51562d849a9d95294bb1db9eac532df8fe3f0669f985717263cb1c","schema_version":"1.0","event_id":"sha256:0e1e4738ca51562d849a9d95294bb1db9eac532df8fe3f0669f985717263cb1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:MDQ3Z2CTASLEMZ7VQBMKD53WJM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Kazuma Hashimoto, Richard Socher, Yoshimasa Tsuruoka","submitted_at":"2016-11-05T01:59:29Z","abstract_excerpt":"Transfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks. Ideally, the linguistic levels of morphology, syntax and semantics would benefit each other by being trained in a single model. We introduce a joint many-task model together with a strategy for successively growing its depth to solve increasingly complex tasks. Higher layers include shortcut connections to lower-level task predictions to reflect linguistic hierarchies. We use a simple regularization term to allow for optimizing all model weights to improve one task's lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01587","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":"2026-05-18T00:39:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLlPBBSJIUbBYDM/q1uwct7ShWYk202pK5AunViRDFw8D62MoLTHSfx29x4gRtn3VrorSI6OUZ1+IgtET3/nAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T12:21:17.541555Z"},"content_sha256":"723567a2b8583762d0d83f31d0e086f5752953ee5fa18aa975c59e8921b9bf22","schema_version":"1.0","event_id":"sha256:723567a2b8583762d0d83f31d0e086f5752953ee5fa18aa975c59e8921b9bf22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MDQ3Z2CTASLEMZ7VQBMKD53WJM/bundle.json","state_url":"https://pith.science/pith/MDQ3Z2CTASLEMZ7VQBMKD53WJM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MDQ3Z2CTASLEMZ7VQBMKD53WJM/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":"2026-05-27T12:21:17Z","links":{"resolver":"https://pith.science/pith/MDQ3Z2CTASLEMZ7VQBMKD53WJM","bundle":"https://pith.science/pith/MDQ3Z2CTASLEMZ7VQBMKD53WJM/bundle.json","state":"https://pith.science/pith/MDQ3Z2CTASLEMZ7VQBMKD53WJM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MDQ3Z2CTASLEMZ7VQBMKD53WJM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:MDQ3Z2CTASLEMZ7VQBMKD53WJM","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":"7a16429af9e23e23a75514015dd262262e946a49f68a71eb99e7e445c3cf3baf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-05T01:59:29Z","title_canon_sha256":"1cdb0e65aad8b43062a481bf160396e6b23bc868744de5e25efdc277f10f342b"},"schema_version":"1.0","source":{"id":"1611.01587","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01587","created_at":"2026-05-18T00:39:47Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01587v5","created_at":"2026-05-18T00:39:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01587","created_at":"2026-05-18T00:39:47Z"},{"alias_kind":"pith_short_12","alias_value":"MDQ3Z2CTASLE","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MDQ3Z2CTASLEMZ7V","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MDQ3Z2CT","created_at":"2026-05-18T12:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:723567a2b8583762d0d83f31d0e086f5752953ee5fa18aa975c59e8921b9bf22","target":"graph","created_at":"2026-05-18T00:39:47Z","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":"Transfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks. Ideally, the linguistic levels of morphology, syntax and semantics would benefit each other by being trained in a single model. We introduce a joint many-task model together with a strategy for successively growing its depth to solve increasingly complex tasks. Higher layers include shortcut connections to lower-level task predictions to reflect linguistic hierarchies. We use a simple regularization term to allow for optimizing all model weights to improve one task's lo","authors_text":"Caiming Xiong, Kazuma Hashimoto, Richard Socher, Yoshimasa Tsuruoka","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-05T01:59:29Z","title":"A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01587","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":"sha256:0e1e4738ca51562d849a9d95294bb1db9eac532df8fe3f0669f985717263cb1c","target":"record","created_at":"2026-05-18T00:39:47Z","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":"7a16429af9e23e23a75514015dd262262e946a49f68a71eb99e7e445c3cf3baf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-05T01:59:29Z","title_canon_sha256":"1cdb0e65aad8b43062a481bf160396e6b23bc868744de5e25efdc277f10f342b"},"schema_version":"1.0","source":{"id":"1611.01587","kind":"arxiv","version":5}},"canonical_sha256":"60e1bce85304964667f58058a1f7764b32f894b68dd749320b8396dbf174c424","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60e1bce85304964667f58058a1f7764b32f894b68dd749320b8396dbf174c424","first_computed_at":"2026-05-18T00:39:47.221668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:47.221668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RA4P8F+0vN3hcxAGfr2b2LafSiDhTNlqyNWK2EXik9DYZ3HmH99NyncfQbiBgERS593wU/RIhjhEUcPVJGp/CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:47.222396Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01587","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e1e4738ca51562d849a9d95294bb1db9eac532df8fe3f0669f985717263cb1c","sha256:723567a2b8583762d0d83f31d0e086f5752953ee5fa18aa975c59e8921b9bf22"],"state_sha256":"1393b6b474f0767108c5727cc0fe299ee8d6cddc8adf6f95a14fa7993b2913b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"inKWCF5FYt7nA32c9V8GGhN5xW69vqPRbZq6wb2apS0ERAC64FzX1i/XcpFjWMVv6FhFH5Za2mwbFOI/4DNXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T12:21:17.545337Z","bundle_sha256":"846ab5851ba605e9ac1f6c3416a4d7836f69a72089fa949fdb3117c48ed9ecf9"}}