{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OUQRESA4WBG2KWOTO2F37MNTQA","short_pith_number":"pith:OUQRESA4","canonical_record":{"source":{"id":"1605.05440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-18T05:00:12Z","cross_cats_sorted":[],"title_canon_sha256":"c41a3c73aab70c9349b28049c48032e16d718e3aa50027c6bcd7b5e0491db7c1","abstract_canon_sha256":"3fb1b0c5a6a8521ba92c84a036726a5c106f93a653d60c3cbd283bed0fb55941"},"schema_version":"1.0"},"canonical_sha256":"752112481cb04da559d3768bbfb1b38006494a7baf9c7ed63dd04fc8bf2a81a7","source":{"kind":"arxiv","id":"1605.05440","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.05440","created_at":"2026-05-18T01:14:34Z"},{"alias_kind":"arxiv_version","alias_value":"1605.05440v1","created_at":"2026-05-18T01:14:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.05440","created_at":"2026-05-18T01:14:34Z"},{"alias_kind":"pith_short_12","alias_value":"OUQRESA4WBG2","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OUQRESA4WBG2KWOT","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OUQRESA4","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OUQRESA4WBG2KWOTO2F37MNTQA","target":"record","payload":{"canonical_record":{"source":{"id":"1605.05440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-18T05:00:12Z","cross_cats_sorted":[],"title_canon_sha256":"c41a3c73aab70c9349b28049c48032e16d718e3aa50027c6bcd7b5e0491db7c1","abstract_canon_sha256":"3fb1b0c5a6a8521ba92c84a036726a5c106f93a653d60c3cbd283bed0fb55941"},"schema_version":"1.0"},"canonical_sha256":"752112481cb04da559d3768bbfb1b38006494a7baf9c7ed63dd04fc8bf2a81a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:34.943105Z","signature_b64":"dmlVAE+Ss+Eee4seYROmlI+S2zMwjsBoMtSJSgssyGd+CpsQl3OBql5TcAXEgy0SH8TM8toHjBfbfEd1+jujCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"752112481cb04da559d3768bbfb1b38006494a7baf9c7ed63dd04fc8bf2a81a7","last_reissued_at":"2026-05-18T01:14:34.942414Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:34.942414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.05440","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":"2026-05-18T01:14:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQkgE8IIT8ydKE/rT6J937Yq3WVo2V30Y7AOas2kQB6G+2fgJjC5bmvwZIuzXriplbfQIlNS3dCzWiIw5vbWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:00:32.691429Z"},"content_sha256":"e66d1db907dd8d9d0c43d40b9b556e1e565a556115a89981da5d17e1b456115e","schema_version":"1.0","event_id":"sha256:e66d1db907dd8d9d0c43d40b9b556e1e565a556115a89981da5d17e1b456115e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OUQRESA4WBG2KWOTO2F37MNTQA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Caption To Narrative: Video Captioning With Multiple Sentences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Shin, Katsunori Ohnishi, Tatsuya Harada","submitted_at":"2016-05-18T05:00:12Z","abstract_excerpt":"Recent advances in image captioning task have led to increasing interests in video captioning task. However, most works on video captioning are focused on generating single input of aggregated features, which hardly deviates from image captioning process and does not fully take advantage of dynamic contents present in videos. We attempt to generate video captions that convey richer contents by temporally segmenting the video with action localization, generating multiple captions from multiple frames, and connecting them with natural language processing techniques, in order to generate a story-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.05440","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":""},"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":"2026-05-18T01:14:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UwH8Ga+UK/4CAA45Lomcl5GYtcIGlzbg3zmb/3r8nMpY1UrsxFHjOd625JMLCiQNBgKk8UFjYh0VW/2b0XBcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:00:32.692071Z"},"content_sha256":"1d702c9a4d0b2f5daecdd177ff5b182f17b597b9c0d5b7abc4761344442394fe","schema_version":"1.0","event_id":"sha256:1d702c9a4d0b2f5daecdd177ff5b182f17b597b9c0d5b7abc4761344442394fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUQRESA4WBG2KWOTO2F37MNTQA/bundle.json","state_url":"https://pith.science/pith/OUQRESA4WBG2KWOTO2F37MNTQA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUQRESA4WBG2KWOTO2F37MNTQA/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":"2026-05-28T23:00:32Z","links":{"resolver":"https://pith.science/pith/OUQRESA4WBG2KWOTO2F37MNTQA","bundle":"https://pith.science/pith/OUQRESA4WBG2KWOTO2F37MNTQA/bundle.json","state":"https://pith.science/pith/OUQRESA4WBG2KWOTO2F37MNTQA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUQRESA4WBG2KWOTO2F37MNTQA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OUQRESA4WBG2KWOTO2F37MNTQA","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":"3fb1b0c5a6a8521ba92c84a036726a5c106f93a653d60c3cbd283bed0fb55941","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-18T05:00:12Z","title_canon_sha256":"c41a3c73aab70c9349b28049c48032e16d718e3aa50027c6bcd7b5e0491db7c1"},"schema_version":"1.0","source":{"id":"1605.05440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.05440","created_at":"2026-05-18T01:14:34Z"},{"alias_kind":"arxiv_version","alias_value":"1605.05440v1","created_at":"2026-05-18T01:14:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.05440","created_at":"2026-05-18T01:14:34Z"},{"alias_kind":"pith_short_12","alias_value":"OUQRESA4WBG2","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OUQRESA4WBG2KWOT","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OUQRESA4","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:1d702c9a4d0b2f5daecdd177ff5b182f17b597b9c0d5b7abc4761344442394fe","target":"graph","created_at":"2026-05-18T01:14:34Z","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":"Recent advances in image captioning task have led to increasing interests in video captioning task. However, most works on video captioning are focused on generating single input of aggregated features, which hardly deviates from image captioning process and does not fully take advantage of dynamic contents present in videos. We attempt to generate video captions that convey richer contents by temporally segmenting the video with action localization, generating multiple captions from multiple frames, and connecting them with natural language processing techniques, in order to generate a story-","authors_text":"Andrew Shin, Katsunori Ohnishi, Tatsuya Harada","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-18T05:00:12Z","title":"Beyond Caption To Narrative: Video Captioning With Multiple Sentences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.05440","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:e66d1db907dd8d9d0c43d40b9b556e1e565a556115a89981da5d17e1b456115e","target":"record","created_at":"2026-05-18T01:14:34Z","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":"3fb1b0c5a6a8521ba92c84a036726a5c106f93a653d60c3cbd283bed0fb55941","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-18T05:00:12Z","title_canon_sha256":"c41a3c73aab70c9349b28049c48032e16d718e3aa50027c6bcd7b5e0491db7c1"},"schema_version":"1.0","source":{"id":"1605.05440","kind":"arxiv","version":1}},"canonical_sha256":"752112481cb04da559d3768bbfb1b38006494a7baf9c7ed63dd04fc8bf2a81a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"752112481cb04da559d3768bbfb1b38006494a7baf9c7ed63dd04fc8bf2a81a7","first_computed_at":"2026-05-18T01:14:34.942414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:14:34.942414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dmlVAE+Ss+Eee4seYROmlI+S2zMwjsBoMtSJSgssyGd+CpsQl3OBql5TcAXEgy0SH8TM8toHjBfbfEd1+jujCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:14:34.943105Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.05440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e66d1db907dd8d9d0c43d40b9b556e1e565a556115a89981da5d17e1b456115e","sha256:1d702c9a4d0b2f5daecdd177ff5b182f17b597b9c0d5b7abc4761344442394fe"],"state_sha256":"0b94cd2b2be0719aa0df2db02224376a8a4c437ab7300e6907e800e98f1be249"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcbJd+yYeRpFCdM0wDRSyGjwwaV0G7l5ibNGCH26apDzax0ghFCEdPTX9q+Jm3di7SBV9SwO4w2Ht6IYHYfnCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:00:32.695598Z","bundle_sha256":"0a6ce46ca7b86d0a812feca8779595bfc177207a7b2c72215bebd4d8a91d12d7"}}