{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VHKYLRALLBPGHXL52KMSOJ5XUP","short_pith_number":"pith:VHKYLRAL","canonical_record":{"source":{"id":"2307.13368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-25T09:39:59Z","cross_cats_sorted":[],"title_canon_sha256":"bc8494895763431820d2d32439d63057ca9568fa15afa888de7a265e207186c0","abstract_canon_sha256":"6af984158720bd581ab6d2afff1279cfd8ed60e09cfcb497e223c8581ce13e3a"},"schema_version":"1.0"},"canonical_sha256":"a9d585c40b585e63dd7dd2992727b7a3eede0f9ada09b7d4b267e0f3cbc815af","source":{"kind":"arxiv","id":"2307.13368","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.13368","created_at":"2026-07-05T06:34:12Z"},{"alias_kind":"arxiv_version","alias_value":"2307.13368v1","created_at":"2026-07-05T06:34:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13368","created_at":"2026-07-05T06:34:12Z"},{"alias_kind":"pith_short_12","alias_value":"VHKYLRALLBPG","created_at":"2026-07-05T06:34:12Z"},{"alias_kind":"pith_short_16","alias_value":"VHKYLRALLBPGHXL5","created_at":"2026-07-05T06:34:12Z"},{"alias_kind":"pith_short_8","alias_value":"VHKYLRAL","created_at":"2026-07-05T06:34:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VHKYLRALLBPGHXL52KMSOJ5XUP","target":"record","payload":{"canonical_record":{"source":{"id":"2307.13368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-25T09:39:59Z","cross_cats_sorted":[],"title_canon_sha256":"bc8494895763431820d2d32439d63057ca9568fa15afa888de7a265e207186c0","abstract_canon_sha256":"6af984158720bd581ab6d2afff1279cfd8ed60e09cfcb497e223c8581ce13e3a"},"schema_version":"1.0"},"canonical_sha256":"a9d585c40b585e63dd7dd2992727b7a3eede0f9ada09b7d4b267e0f3cbc815af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:12.939304Z","signature_b64":"lhG2oKatBFZ+pyzXURjCelxDWxpeVjzzw1tYL+2WjyjfyQG6a6uWmC792az+bVATLoF+euRZxhUZYwpMau/qDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9d585c40b585e63dd7dd2992727b7a3eede0f9ada09b7d4b267e0f3cbc815af","last_reissued_at":"2026-07-05T06:34:12.938888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:12.938888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.13368","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":"2026-07-05T06:34:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h6mJB7ji0HWp+gfb9knFZW2NvzS0wDRP+u6AmqNTvJHMDMDcuiIMgc+Ga+Ka1+vxw93R6zfXD5Q0qbPdX1ZXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:41:46.403923Z"},"content_sha256":"3688d3b92df32c4d1a7586c6f677cca95dde3f9c18cb6d7d7ac999451ef1d07f","schema_version":"1.0","event_id":"sha256:3688d3b92df32c4d1a7586c6f677cca95dde3f9c18cb6d7d7ac999451ef1d07f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VHKYLRALLBPGHXL52KMSOJ5XUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Kefa: A Knowledge Enhanced and Fine-grained Aligned Speaker for Navigation Instruction Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haitian Zeng, Wenguan Wang, Xiaohan Wang, Yi Yang","submitted_at":"2023-07-25T09:39:59Z","abstract_excerpt":"We introduce a novel speaker model \\textsc{Kefa} for navigation instruction generation. The existing speaker models in Vision-and-Language Navigation suffer from the large domain gap of vision features between different environments and insufficient temporal grounding capability. To address the challenges, we propose a Knowledge Refinement Module to enhance the feature representation with external knowledge facts, and an Adaptive Temporal Alignment method to enforce fine-grained alignment between the generated instructions and the observation sequences. Moreover, we propose a new metric SPICE-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13368","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/2307.13368/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":"2026-07-05T06:34:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/b7AzjjEOwGQqwd5ejeCMy0yIh1evjgbtE6uZjgrvlp5C/9DlmcCR561VZGXNGjVg1/WXRn+9mqlq5VpRc0OCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:41:46.404792Z"},"content_sha256":"309907bd122dd9599c1dc3db5487523ecfcc5957cd26c8686bbb82f1e9b55b39","schema_version":"1.0","event_id":"sha256:309907bd122dd9599c1dc3db5487523ecfcc5957cd26c8686bbb82f1e9b55b39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VHKYLRALLBPGHXL52KMSOJ5XUP/bundle.json","state_url":"https://pith.science/pith/VHKYLRALLBPGHXL52KMSOJ5XUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VHKYLRALLBPGHXL52KMSOJ5XUP/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":"2026-08-06T04:41:46Z","links":{"resolver":"https://pith.science/pith/VHKYLRALLBPGHXL52KMSOJ5XUP","bundle":"https://pith.science/pith/VHKYLRALLBPGHXL52KMSOJ5XUP/bundle.json","state":"https://pith.science/pith/VHKYLRALLBPGHXL52KMSOJ5XUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VHKYLRALLBPGHXL52KMSOJ5XUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VHKYLRALLBPGHXL52KMSOJ5XUP","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":"6af984158720bd581ab6d2afff1279cfd8ed60e09cfcb497e223c8581ce13e3a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-25T09:39:59Z","title_canon_sha256":"bc8494895763431820d2d32439d63057ca9568fa15afa888de7a265e207186c0"},"schema_version":"1.0","source":{"id":"2307.13368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.13368","created_at":"2026-07-05T06:34:12Z"},{"alias_kind":"arxiv_version","alias_value":"2307.13368v1","created_at":"2026-07-05T06:34:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13368","created_at":"2026-07-05T06:34:12Z"},{"alias_kind":"pith_short_12","alias_value":"VHKYLRALLBPG","created_at":"2026-07-05T06:34:12Z"},{"alias_kind":"pith_short_16","alias_value":"VHKYLRALLBPGHXL5","created_at":"2026-07-05T06:34:12Z"},{"alias_kind":"pith_short_8","alias_value":"VHKYLRAL","created_at":"2026-07-05T06:34:12Z"}],"graph_snapshots":[{"event_id":"sha256:309907bd122dd9599c1dc3db5487523ecfcc5957cd26c8686bbb82f1e9b55b39","target":"graph","created_at":"2026-07-05T06:34:12Z","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/2307.13368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel speaker model \\textsc{Kefa} for navigation instruction generation. The existing speaker models in Vision-and-Language Navigation suffer from the large domain gap of vision features between different environments and insufficient temporal grounding capability. To address the challenges, we propose a Knowledge Refinement Module to enhance the feature representation with external knowledge facts, and an Adaptive Temporal Alignment method to enforce fine-grained alignment between the generated instructions and the observation sequences. Moreover, we propose a new metric SPICE-","authors_text":"Haitian Zeng, Wenguan Wang, Xiaohan Wang, Yi Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-25T09:39:59Z","title":"Kefa: A Knowledge Enhanced and Fine-grained Aligned Speaker for Navigation Instruction Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13368","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":"sha256:3688d3b92df32c4d1a7586c6f677cca95dde3f9c18cb6d7d7ac999451ef1d07f","target":"record","created_at":"2026-07-05T06:34:12Z","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":"6af984158720bd581ab6d2afff1279cfd8ed60e09cfcb497e223c8581ce13e3a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-25T09:39:59Z","title_canon_sha256":"bc8494895763431820d2d32439d63057ca9568fa15afa888de7a265e207186c0"},"schema_version":"1.0","source":{"id":"2307.13368","kind":"arxiv","version":1}},"canonical_sha256":"a9d585c40b585e63dd7dd2992727b7a3eede0f9ada09b7d4b267e0f3cbc815af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9d585c40b585e63dd7dd2992727b7a3eede0f9ada09b7d4b267e0f3cbc815af","first_computed_at":"2026-07-05T06:34:12.938888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:12.938888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lhG2oKatBFZ+pyzXURjCelxDWxpeVjzzw1tYL+2WjyjfyQG6a6uWmC792az+bVATLoF+euRZxhUZYwpMau/qDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:12.939304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.13368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3688d3b92df32c4d1a7586c6f677cca95dde3f9c18cb6d7d7ac999451ef1d07f","sha256:309907bd122dd9599c1dc3db5487523ecfcc5957cd26c8686bbb82f1e9b55b39"],"state_sha256":"965b5df5423327060f0711f2ee720c0af1b0cedd341e4b5d16fb38252df39ed4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HTntmooJhN7z3gflB6VF2rRpmDljjql5EpyYO3Z8ER1ZYCVfsGqBpdFnUW6j2bSvCK1r0IeNa8hD3b/Pe329CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:41:46.411348Z","bundle_sha256":"b1b4b75798ec297d0297c7fdd827effc04851d9ca1ce87ca166a2cce1c24b77d"}}