{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:DSY6P3XU5DZJYZ236KU2NYZIEX","short_pith_number":"pith:DSY6P3XU","canonical_record":{"source":{"id":"1701.03126","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-11T19:16:42Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"d7f11ca171ee1b4ef9b7993297f6be5cb6c8b328b26e3ab0fe17dbc93e53acf8","abstract_canon_sha256":"d90449f150a964dee4afcf9dbacf2f4053c9a0a3259c9b31d45b227a1e05f3cb"},"schema_version":"1.0"},"canonical_sha256":"1cb1e7eef4e8f29c675bf2a9a6e32825fc8717625f48fccc52e9d69a3b868703","source":{"kind":"arxiv","id":"1701.03126","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.03126","created_at":"2026-05-18T00:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"1701.03126v2","created_at":"2026-05-18T00:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.03126","created_at":"2026-05-18T00:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"DSY6P3XU5DZJ","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DSY6P3XU5DZJYZ23","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DSY6P3XU","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:DSY6P3XU5DZJYZ236KU2NYZIEX","target":"record","payload":{"canonical_record":{"source":{"id":"1701.03126","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-11T19:16:42Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"d7f11ca171ee1b4ef9b7993297f6be5cb6c8b328b26e3ab0fe17dbc93e53acf8","abstract_canon_sha256":"d90449f150a964dee4afcf9dbacf2f4053c9a0a3259c9b31d45b227a1e05f3cb"},"schema_version":"1.0"},"canonical_sha256":"1cb1e7eef4e8f29c675bf2a9a6e32825fc8717625f48fccc52e9d69a3b868703","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:59.505338Z","signature_b64":"v00M711SRXfHjrxGXYhmDfTFGT406gkiEX4iZ1XG1u/DOpXt5lljOqx4jvPMsUCtDP0SfMHvlHlHIWN4VbBJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cb1e7eef4e8f29c675bf2a9a6e32825fc8717625f48fccc52e9d69a3b868703","last_reissued_at":"2026-05-18T00:48:59.504693Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:59.504693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.03126","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BRSdTkq/JzlvRJ96KXR2pah2PZ4T4ZO1INqZXoc7megaSJoAMoJOrVJRWz8dP976VB40sovntGYZUsZIr44DCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:28:39.298104Z"},"content_sha256":"b818281ebb57688db547a8c97cac581fb36774bb4d47871c56c6323096acc014","schema_version":"1.0","event_id":"sha256:b818281ebb57688db547a8c97cac581fb36774bb4d47871c56c6323096acc014"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:DSY6P3XU5DZJYZ236KU2NYZIEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention-Based Multimodal Fusion for Video Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chiori Hori, John R. Hershey, Kazuhiro Sumi, Takaaki Hori, Teng-Yok Lee, Tim K. Marks","submitted_at":"2017-01-11T19:16:42Z","abstract_excerpt":"Currently successful methods for video description are based on encoder-decoder sentence generation using recur-rent neural networks (RNNs). Recent work has shown the advantage of integrating temporal and/or spatial attention mechanisms into these models, in which the decoder net-work predicts each word in the description by selectively giving more weight to encoded features from specific time frames (temporal attention) or to features from specific spatial regions (spatial attention). In this paper, we propose to expand the attention model to selectively attend not just to specific times or s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.03126","kind":"arxiv","version":2},"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":"2026-05-18T00:48:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gkm/lZVBqa7mQdvjarFQO9+iDCNU0HD0QU3fFjyeyXhZ3j2SmpTEPpv5wsX1UwoZ8eDLhi0joNXWBWQtmaPPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:28:39.298537Z"},"content_sha256":"36b713ebc18e35d2861722be92a422afcd752ce377bb575001fbd4942ccbd96d","schema_version":"1.0","event_id":"sha256:36b713ebc18e35d2861722be92a422afcd752ce377bb575001fbd4942ccbd96d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSY6P3XU5DZJYZ236KU2NYZIEX/bundle.json","state_url":"https://pith.science/pith/DSY6P3XU5DZJYZ236KU2NYZIEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSY6P3XU5DZJYZ236KU2NYZIEX/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":"2026-05-26T02:28:39Z","links":{"resolver":"https://pith.science/pith/DSY6P3XU5DZJYZ236KU2NYZIEX","bundle":"https://pith.science/pith/DSY6P3XU5DZJYZ236KU2NYZIEX/bundle.json","state":"https://pith.science/pith/DSY6P3XU5DZJYZ236KU2NYZIEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSY6P3XU5DZJYZ236KU2NYZIEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DSY6P3XU5DZJYZ236KU2NYZIEX","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":"d90449f150a964dee4afcf9dbacf2f4053c9a0a3259c9b31d45b227a1e05f3cb","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-11T19:16:42Z","title_canon_sha256":"d7f11ca171ee1b4ef9b7993297f6be5cb6c8b328b26e3ab0fe17dbc93e53acf8"},"schema_version":"1.0","source":{"id":"1701.03126","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.03126","created_at":"2026-05-18T00:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"1701.03126v2","created_at":"2026-05-18T00:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.03126","created_at":"2026-05-18T00:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"DSY6P3XU5DZJ","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DSY6P3XU5DZJYZ23","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DSY6P3XU","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:36b713ebc18e35d2861722be92a422afcd752ce377bb575001fbd4942ccbd96d","target":"graph","created_at":"2026-05-18T00:48:59Z","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":"Currently successful methods for video description are based on encoder-decoder sentence generation using recur-rent neural networks (RNNs). Recent work has shown the advantage of integrating temporal and/or spatial attention mechanisms into these models, in which the decoder net-work predicts each word in the description by selectively giving more weight to encoded features from specific time frames (temporal attention) or to features from specific spatial regions (spatial attention). In this paper, we propose to expand the attention model to selectively attend not just to specific times or s","authors_text":"Chiori Hori, John R. Hershey, Kazuhiro Sumi, Takaaki Hori, Teng-Yok Lee, Tim K. Marks","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-11T19:16:42Z","title":"Attention-Based Multimodal Fusion for Video Description"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.03126","kind":"arxiv","version":2},"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:b818281ebb57688db547a8c97cac581fb36774bb4d47871c56c6323096acc014","target":"record","created_at":"2026-05-18T00:48:59Z","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":"d90449f150a964dee4afcf9dbacf2f4053c9a0a3259c9b31d45b227a1e05f3cb","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-11T19:16:42Z","title_canon_sha256":"d7f11ca171ee1b4ef9b7993297f6be5cb6c8b328b26e3ab0fe17dbc93e53acf8"},"schema_version":"1.0","source":{"id":"1701.03126","kind":"arxiv","version":2}},"canonical_sha256":"1cb1e7eef4e8f29c675bf2a9a6e32825fc8717625f48fccc52e9d69a3b868703","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cb1e7eef4e8f29c675bf2a9a6e32825fc8717625f48fccc52e9d69a3b868703","first_computed_at":"2026-05-18T00:48:59.504693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:59.504693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v00M711SRXfHjrxGXYhmDfTFGT406gkiEX4iZ1XG1u/DOpXt5lljOqx4jvPMsUCtDP0SfMHvlHlHIWN4VbBJCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:59.505338Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.03126","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b818281ebb57688db547a8c97cac581fb36774bb4d47871c56c6323096acc014","sha256:36b713ebc18e35d2861722be92a422afcd752ce377bb575001fbd4942ccbd96d"],"state_sha256":"047f967638ae0a7ba064bdf7cef9bb8d638a92efbec8e2871e34ddca91b38bf9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NwBLdNAnyD+NUYTZbiz5jCnsBWvZadxIi4z2IGcrGGjVij+eE6MH4l+jDjeD0l4TDHpe4RwJUD0Fyh6Pl8QPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:28:39.301767Z","bundle_sha256":"dc234057fb0059f6fe896c2681f7f2da25ca6227759477a314bed92ea9cb9917"}}