{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5CBGFORVH3NQ7GF3XJGUQQCVB6","short_pith_number":"pith:5CBGFORV","canonical_record":{"source":{"id":"2106.14118","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-27T00:49:02Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"0ba699081fa231141f1a5a395b2f647364acde95f81a87f145f440d113d13581","abstract_canon_sha256":"a426d9ad2dc4655f9d6a0f60cea9ee011ab0ac1978347183a36c70ba6ba893d2"},"schema_version":"1.0"},"canonical_sha256":"e88262ba353edb0f98bbba4d4840550fb2de00af4bfe040e3a8ab625d3893aae","source":{"kind":"arxiv","id":"2106.14118","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14118","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14118v4","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14118","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"5CBGFORVH3NQ","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"5CBGFORVH3NQ7GF3","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"5CBGFORV","created_at":"2026-07-05T03:23:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5CBGFORVH3NQ7GF3XJGUQQCVB6","target":"record","payload":{"canonical_record":{"source":{"id":"2106.14118","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-27T00:49:02Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"0ba699081fa231141f1a5a395b2f647364acde95f81a87f145f440d113d13581","abstract_canon_sha256":"a426d9ad2dc4655f9d6a0f60cea9ee011ab0ac1978347183a36c70ba6ba893d2"},"schema_version":"1.0"},"canonical_sha256":"e88262ba353edb0f98bbba4d4840550fb2de00af4bfe040e3a8ab625d3893aae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:12.170018Z","signature_b64":"K7a9iHCJBS9tn073pl4YuQm497QGb2/oYdfWBlPpsten/hfFuwLFt66oiVCezICrldX3VF9188D1KDYHpTYvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e88262ba353edb0f98bbba4d4840550fb2de00af4bfe040e3a8ab625d3893aae","last_reissued_at":"2026-07-05T03:23:12.169603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:12.169603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.14118","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:23:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+QGXrQ8FzrkkhzacXi4pZmXCW+bYiu+U2nLUjZ0zD1i2aK9laz1snZUDJZrHXw7zFnbsd0lE8ONWo7v/yhhuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:35:18.099348Z"},"content_sha256":"b48adce68c8f736807a6fe3d3918783082e118a0d0f33dd070cf2225e7f0722a","schema_version":"1.0","event_id":"sha256:b48adce68c8f736807a6fe3d3918783082e118a0d0f33dd070cf2225e7f0722a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5CBGFORVH3NQ7GF3XJGUQQCVB6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Anurag Bagchi, Dolton Fernandes, Jazib Mahmood, Ravi Kiran Sarvadevabhatla","submitted_at":"2021-06-27T00:49:02Z","abstract_excerpt":"State of the art architectures for untrimmed video Temporal Action Localization (TAL) have only considered RGB and Flow modalities, leaving the information-rich audio modality totally unexploited. Audio fusion has been explored for the related but arguably easier problem of trimmed (clip-level) action recognition. However, TAL poses a unique set of challenges. In this paper, we propose simple but effective fusion-based approaches for TAL. To the best of our knowledge, our work is the first to jointly consider audio and video modalities for supervised TAL. We experimentally show that our scheme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14118","kind":"arxiv","version":4},"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/2106.14118/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":"2026-07-05T03:23:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kh217aUXRzD20fnk8DVNDIHDUlEFZOWciyKUzzpapuABl6XMMTqZ6rd6UCxi7cVCR7Xx61b14RDXb/u8/gv5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:35:18.099910Z"},"content_sha256":"25d3c1e22fadcf1504a50944d44c9a241ac463d83d033822fdaa0373517c0906","schema_version":"1.0","event_id":"sha256:25d3c1e22fadcf1504a50944d44c9a241ac463d83d033822fdaa0373517c0906"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5CBGFORVH3NQ7GF3XJGUQQCVB6/bundle.json","state_url":"https://pith.science/pith/5CBGFORVH3NQ7GF3XJGUQQCVB6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5CBGFORVH3NQ7GF3XJGUQQCVB6/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":"2026-08-08T09:35:18Z","links":{"resolver":"https://pith.science/pith/5CBGFORVH3NQ7GF3XJGUQQCVB6","bundle":"https://pith.science/pith/5CBGFORVH3NQ7GF3XJGUQQCVB6/bundle.json","state":"https://pith.science/pith/5CBGFORVH3NQ7GF3XJGUQQCVB6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5CBGFORVH3NQ7GF3XJGUQQCVB6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5CBGFORVH3NQ7GF3XJGUQQCVB6","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":"a426d9ad2dc4655f9d6a0f60cea9ee011ab0ac1978347183a36c70ba6ba893d2","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-27T00:49:02Z","title_canon_sha256":"0ba699081fa231141f1a5a395b2f647364acde95f81a87f145f440d113d13581"},"schema_version":"1.0","source":{"id":"2106.14118","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14118","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14118v4","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14118","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"5CBGFORVH3NQ","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"5CBGFORVH3NQ7GF3","created_at":"2026-07-05T03:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"5CBGFORV","created_at":"2026-07-05T03:23:12Z"}],"graph_snapshots":[{"event_id":"sha256:25d3c1e22fadcf1504a50944d44c9a241ac463d83d033822fdaa0373517c0906","target":"graph","created_at":"2026-07-05T03:23:12Z","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/2106.14118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State of the art architectures for untrimmed video Temporal Action Localization (TAL) have only considered RGB and Flow modalities, leaving the information-rich audio modality totally unexploited. Audio fusion has been explored for the related but arguably easier problem of trimmed (clip-level) action recognition. However, TAL poses a unique set of challenges. In this paper, we propose simple but effective fusion-based approaches for TAL. To the best of our knowledge, our work is the first to jointly consider audio and video modalities for supervised TAL. We experimentally show that our scheme","authors_text":"Anurag Bagchi, Dolton Fernandes, Jazib Mahmood, Ravi Kiran Sarvadevabhatla","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-27T00:49:02Z","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14118","kind":"arxiv","version":4},"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:b48adce68c8f736807a6fe3d3918783082e118a0d0f33dd070cf2225e7f0722a","target":"record","created_at":"2026-07-05T03:23:12Z","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":"a426d9ad2dc4655f9d6a0f60cea9ee011ab0ac1978347183a36c70ba6ba893d2","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-27T00:49:02Z","title_canon_sha256":"0ba699081fa231141f1a5a395b2f647364acde95f81a87f145f440d113d13581"},"schema_version":"1.0","source":{"id":"2106.14118","kind":"arxiv","version":4}},"canonical_sha256":"e88262ba353edb0f98bbba4d4840550fb2de00af4bfe040e3a8ab625d3893aae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e88262ba353edb0f98bbba4d4840550fb2de00af4bfe040e3a8ab625d3893aae","first_computed_at":"2026-07-05T03:23:12.169603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:23:12.169603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K7a9iHCJBS9tn073pl4YuQm497QGb2/oYdfWBlPpsten/hfFuwLFt66oiVCezICrldX3VF9188D1KDYHpTYvBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:23:12.170018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.14118","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b48adce68c8f736807a6fe3d3918783082e118a0d0f33dd070cf2225e7f0722a","sha256:25d3c1e22fadcf1504a50944d44c9a241ac463d83d033822fdaa0373517c0906"],"state_sha256":"37146e616f83958c14c6568b2d82b5a59df2a20d21fc479202062672a53b9625"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T7fXQ0UfSB2WrTMQwFeWD2ym0suiI906ww1UB+hPo2tFy2XehFwWFcBMUR+f0Sao10j9+XNE10BnekqshtI7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:35:18.103543Z","bundle_sha256":"79fd49324c5628f79ad1bc92ee0200885ecabf688923a8c878dc728471e2ed66"}}