{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RAU5CRANQ4XRR6CI3TLWZAAUIR","short_pith_number":"pith:RAU5CRAN","canonical_record":{"source":{"id":"1910.05728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-10-13T10:49:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"763db8de3d13544412b3d23265ed61d1bdfeef15a41ac9b73f11d4e3ce9bf489","abstract_canon_sha256":"3f6492172c7ac7b22ffc0e19d2d771519d0c30ab1e18de9c9200fd20d6776a4e"},"schema_version":"1.0"},"canonical_sha256":"8829d1440d872f18f848dcd76c8014445808c7f93bd2a9228c245f5d30114eb1","source":{"kind":"arxiv","id":"1910.05728","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05728","created_at":"2026-07-05T00:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05728v1","created_at":"2026-07-05T00:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05728","created_at":"2026-07-05T00:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"RAU5CRANQ4XR","created_at":"2026-07-05T00:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"RAU5CRANQ4XRR6CI","created_at":"2026-07-05T00:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"RAU5CRAN","created_at":"2026-07-05T00:11:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RAU5CRANQ4XRR6CI3TLWZAAUIR","target":"record","payload":{"canonical_record":{"source":{"id":"1910.05728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-10-13T10:49:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"763db8de3d13544412b3d23265ed61d1bdfeef15a41ac9b73f11d4e3ce9bf489","abstract_canon_sha256":"3f6492172c7ac7b22ffc0e19d2d771519d0c30ab1e18de9c9200fd20d6776a4e"},"schema_version":"1.0"},"canonical_sha256":"8829d1440d872f18f848dcd76c8014445808c7f93bd2a9228c245f5d30114eb1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:41.222614Z","signature_b64":"S5BOMy2oULnOStX9c9NdqlSotZIGTUkTUirfLzy3ZAIORCWMeiGUTvVdXtzlJ2BJ8fixdw0pqwO8ohqwVFSPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8829d1440d872f18f848dcd76c8014445808c7f93bd2a9228c245f5d30114eb1","last_reissued_at":"2026-07-05T00:11:41.222211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:41.222211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.05728","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dbgzV+dCfrgTkcTUUuzAEqGTG7rNPb/A9rjlrxgrFSAxtJgXB4Iom2qRVqCKXmfJJx3gW6nWCn739NOWcoUkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:29:48.125073Z"},"content_sha256":"1c32e9ab3853b1c47f276fd295e8dc4b6334deac1ceefc500f613359a12fa97e","schema_version":"1.0","event_id":"sha256:1c32e9ab3853b1c47f276fd295e8dc4b6334deac1ceefc500f613359a12fa97e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RAU5CRANQ4XRR6CI3TLWZAAUIR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Granular Multimodal Attention Networks for Visual Dialog","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Badri N. Patro, Shivansh Patel, Vinay P. Namboodiri","submitted_at":"2019-10-13T10:49:41Z","abstract_excerpt":"Vision and language tasks have benefited from attention. There have been a number of different attention models proposed. However, the scale at which attention needs to be applied has not been well examined. Particularly, in this work, we propose a new method Granular Multi-modal Attention, where we aim to particularly address the question of the right granularity at which one needs to attend while solving the Visual Dialog task. The proposed method shows improvement in both image and text attention networks. We then propose a granular Multi-modal Attention network that jointly attends on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05728","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.05728/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ic8nFKDayXN1tovDRLqplDdgTIb96//dwRzJqAdYYWjcFk4i7DY5qJl1khVy6ewcx13NVjIuRIM7Ojxel9YsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:29:48.125568Z"},"content_sha256":"ccdefaca6f13e14a0d6b8381c2eed9a0494de2ae18c4a5d57419cda6ab84b482","schema_version":"1.0","event_id":"sha256:ccdefaca6f13e14a0d6b8381c2eed9a0494de2ae18c4a5d57419cda6ab84b482"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RAU5CRANQ4XRR6CI3TLWZAAUIR/bundle.json","state_url":"https://pith.science/pith/RAU5CRANQ4XRR6CI3TLWZAAUIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RAU5CRANQ4XRR6CI3TLWZAAUIR/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":"2026-08-23T06:29:48Z","links":{"resolver":"https://pith.science/pith/RAU5CRANQ4XRR6CI3TLWZAAUIR","bundle":"https://pith.science/pith/RAU5CRANQ4XRR6CI3TLWZAAUIR/bundle.json","state":"https://pith.science/pith/RAU5CRANQ4XRR6CI3TLWZAAUIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RAU5CRANQ4XRR6CI3TLWZAAUIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RAU5CRANQ4XRR6CI3TLWZAAUIR","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":"3f6492172c7ac7b22ffc0e19d2d771519d0c30ab1e18de9c9200fd20d6776a4e","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-10-13T10:49:41Z","title_canon_sha256":"763db8de3d13544412b3d23265ed61d1bdfeef15a41ac9b73f11d4e3ce9bf489"},"schema_version":"1.0","source":{"id":"1910.05728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05728","created_at":"2026-07-05T00:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05728v1","created_at":"2026-07-05T00:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05728","created_at":"2026-07-05T00:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"RAU5CRANQ4XR","created_at":"2026-07-05T00:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"RAU5CRANQ4XRR6CI","created_at":"2026-07-05T00:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"RAU5CRAN","created_at":"2026-07-05T00:11:41Z"}],"graph_snapshots":[{"event_id":"sha256:ccdefaca6f13e14a0d6b8381c2eed9a0494de2ae18c4a5d57419cda6ab84b482","target":"graph","created_at":"2026-07-05T00:11:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1910.05728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision and language tasks have benefited from attention. There have been a number of different attention models proposed. However, the scale at which attention needs to be applied has not been well examined. Particularly, in this work, we propose a new method Granular Multi-modal Attention, where we aim to particularly address the question of the right granularity at which one needs to attend while solving the Visual Dialog task. The proposed method shows improvement in both image and text attention networks. We then propose a granular Multi-modal Attention network that jointly attends on the ","authors_text":"Badri N. Patro, Shivansh Patel, Vinay P. Namboodiri","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-10-13T10:49:41Z","title":"Granular Multimodal Attention Networks for Visual Dialog"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05728","kind":"arxiv","version":1},"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":"sha256:1c32e9ab3853b1c47f276fd295e8dc4b6334deac1ceefc500f613359a12fa97e","target":"record","created_at":"2026-07-05T00:11:41Z","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":"3f6492172c7ac7b22ffc0e19d2d771519d0c30ab1e18de9c9200fd20d6776a4e","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-10-13T10:49:41Z","title_canon_sha256":"763db8de3d13544412b3d23265ed61d1bdfeef15a41ac9b73f11d4e3ce9bf489"},"schema_version":"1.0","source":{"id":"1910.05728","kind":"arxiv","version":1}},"canonical_sha256":"8829d1440d872f18f848dcd76c8014445808c7f93bd2a9228c245f5d30114eb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8829d1440d872f18f848dcd76c8014445808c7f93bd2a9228c245f5d30114eb1","first_computed_at":"2026-07-05T00:11:41.222211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:11:41.222211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S5BOMy2oULnOStX9c9NdqlSotZIGTUkTUirfLzy3ZAIORCWMeiGUTvVdXtzlJ2BJ8fixdw0pqwO8ohqwVFSPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:11:41.222614Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.05728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c32e9ab3853b1c47f276fd295e8dc4b6334deac1ceefc500f613359a12fa97e","sha256:ccdefaca6f13e14a0d6b8381c2eed9a0494de2ae18c4a5d57419cda6ab84b482"],"state_sha256":"c159d9a6dfeb2fa4177d72b6141cdf0bfcc04a614062ccccfca841f275433ff3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ot41Li0Wod+/bY8Gkh8NBddtAP8TQkPUqoPKX0KeGv30gLJ9HCI/6Dkq2Z0neueY0gw6zRgM2FdCyEi3ZaMfBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T06:29:48.128923Z","bundle_sha256":"dbee16cf81f1b4c334ec2f1d9529a62b3a5e99c451e8b03f6a8c6a304d6418b0"}}